This application relates generally to image analysis and more particularly to image analysis for data collected from a remote computing device.
People spend a tremendous amount of time on the internet, mostly by viewing interacting with web pages. Website analytics have been performed by analyzing the amount of time which a person spends on a webpage, and the path through the internet which has been taken by the person. This type of analysis has been used to evaluate the value and benefit of web pages and the respective styles of these pages.
The evaluation of mental states is key to understanding individuals and the way in which they react to the world around them. Mental states run a broad gamut from happiness to sadness, from contentedness to worry, from excitement to calmness, among numerous others. These mental states are experienced in response to everyday events such as frustration during a traffic jam, boredom while standing in line, impatience while waiting for a cup of coffee, and even as people interact with their computers and the internet. Individuals perceive and empathize with other people by evaluating and understanding their mental states, but automated evaluation of mental states is far more challenging. An empathetic person may perceive another person being anxious or joyful and respond accordingly. The ability and means by which one person perceives another's emotional state is often quite difficult to summarize and has often been communicated as having a “gut feel.”
Many mental states, such as confusion, concentration, and worry, may be identified to aid in the understanding of an individual or group of people. People can collectively respond with fear or anxiety, such as after witnessing a catastrophe. Likewise, people can collectively respond with happy enthusiasm, such as when their sports team obtains a victory. Certain facial expressions and head gestures may be used to identify a mental state that a person is experiencing. Limited automation has been performed in the evaluation of mental states based on facial expressions. Certain physiological conditions may provide telling indications of a person's state of mind and have been used in a crude fashion, as in an apparatus used for lie detector or polygraph tests.
Analysis of people, as they interact with the internet, can be performed by gathering mental states through evaluation of facial expressions, head gestures, and physiological conditions. This analysis can be connected to specific interactions with web pages or portions of a given web page. A computer implemented method for analyzing web-enabled application traffic is disclosed comprising: collecting mental state data from a plurality of people as they interact with a rendering; uploading information, to a server, based on the mental state data from the plurality of people who interact with the rendering; receiving aggregated mental state information on the plurality of people who interact with the rendering; and displaying the aggregated mental state information with the rendering. The aggregated mental state information can include norms derived from the plurality of people. The norms can be based on contextual information. The method can further comprise associating the aggregated mental state information with the rendering. The method can further comprise inferring of mental states based on the mental state data collected from the plurality of people. The rendering can be one of a group comprising a button, an advertisement, a banner ad, a drop down menu, and a data element on a web-enabled application. The rendering can be one of a group comprising a landing page, a checkout page, a webpage, a website, a web-enabled application, a video on a web-enabled application, a game on a web-enabled application, and a virtual world. The collecting mental state data can involve capturing of one of a group comprising physiological data and facial data. A webcam can be used to capture one or more of the facial data and the physiological data. The physiological data can be used to determine autonomic activity. The autonomic activity can be one of a group comprising heart rate, respiration, and heart rate variability. The facial data can include information on one or more of a group comprising facial expressions, action units, head gestures, smiles, brow furrows, squints, lowered eyebrows, raised eyebrows, and attention. The method can further comprise tracking of eyes to identify the rendering with which interacting is accomplished. The tracking of eyes can identify a portion of the rendering on which the eyes are focused. A webcam can be used to track the eyes. The method can further comprise recording of eye dwell-time on the rendering and associating information on the eye dwell-time to the rendering and to the mental states. The interacting can include one of a group comprising viewing, clicking, and mousing over. The method can further comprise opting in, by an individual from the plurality of people, to allowing facial information to be aggregated. The method can further comprise opting in, by an individual from the plurality of people, to allowing uploading of information to the server.
Aggregation of the aggregated mental state information can be accomplished using computational aggregation. In some embodiments, aggregation of the aggregated mental state information is performed on a demographic basis so that mental state information is grouped based on the demographic basis. The method can further comprise creating a visual representation of one or more of the aggregated mental state information and mental state information on an individual from the plurality of people. The visual representation can display the aggregated mental state information on a demographic basis. The method can further comprise animating an avatar to represent one or more of the aggregated mental state information and mental state information on an individual from the plurality of people. The method can further comprise synchronizing the aggregated mental state information with the rendering. The method can further comprise capturing contextual information about the rendering. The contextual information can include one or more of a timeline, a progression of webpages, or an actigraph. The mental states can include one of a group comprising frustration, confusion, disappointment, hesitation, cognitive overload, focusing, being engaged, attending, boredom, exploration, confidence, trust, delight, and satisfaction.
In embodiments, a computer program product is embodied in a non-transitory computer readable medium for analyzing web-enabled application traffic, the computer program product comprising code which can cause one or more processors to perform operations of: collecting mental state data from a plurality of people as they interact with a rendering; uploading information, to a server, based on the mental state data from the plurality of people who interact with the rendering; receiving aggregated mental state information on the plurality of people who interact with the rendering; and displaying the aggregated mental state information with the rendering. In embodiments, a system for analyzing web-enabled application traffic comprises: a memory which stores instructions; one or more processors attached to the memory wherein the one or more processors, when executing the instructions which are stored, are configured to: collect mental state data from a plurality of people as they interact with a rendering; upload information, to a server, based on the mental state data from the plurality of people who interact with the rendering; receive aggregated mental state information on the plurality of people who interact with the rendering; and display the aggregated mental state information with the rendering.
In some embodiments, a method for analyzing web-enabled application traffic comprises: receiving mental state data collected from a plurality of people as they interact with a rendering, receiving aggregated mental state information on the plurality of people who interact with the rendering; and displaying the aggregated mental state information with the rendering. In some embodiments, a computer implemented method for analyzing web-enabled application traffic comprises: receiving mental state data collected from a plurality of people as they interact with a rendering, aggregating mental state information on the plurality of people who interact with the rendering; associating the aggregated mental state information with the rendering; and providing the aggregated mental state information to a requester. In embodiments, a computer implemented method for analyzing renderings on electronic displays comprises: interacting with a rendering on an electronic display by a first person; capturing data on the first person into a computer system as the first person interacts with the rendering on the electronic display; inferring of mental states for the first person who interacted with the rendering based on the data which was captured for the first person; uploading information to a server on the data which was captured on the first person; interacting with the rendering by a second person; capturing data on the second person as the second person interacts with the rendering; inferring of mental states for the second person who interacted with the rendering based on the data which was captured for the second person; uploading information to the server on the data which was captured on the second person; aggregating information on the mental states of the first person with the mental states of the second person resulting in aggregated mental state information; and associating the aggregated mental state information to the rendering with which the first person and the second person interacted.
Various features, aspects, and advantages of numerous embodiments will become more apparent from the following description.
The following detailed description of certain embodiments may be understood by reference to the following figures wherein:
The present disclosure provides a description of various methods and systems for analyzing people's mental states as they interact with websites and other features on the internet. A mental state can be an emotional state or a cognitive state. Examples of emotional states include happiness or sadness, and examples of cognitive states include concentration or confusion. Observing, capturing, and analyzing these mental states can yield significant information about people's reactions to websites that far exceed current capabilities in website analytics.
A challenge solved by this disclosure is the analysis of mental states within a web-oriented environment. Information on mental states can be collected on a client machine and either uploaded to a server in a raw format or analyzed and abstracted, then uploaded. The cloud-based system can perform analysis on the mental states as an individual or group of individuals interacts with videos, advertisements, webpages, and the like based on the mental state information which was uploaded. The mental state information can be aggregated across a group of people to provide summaries on people's mental states as they interact with web-enabled applications. The aggregated information can provide normative criteria that are important for comparing customer experiences across different applications and across common experiences within many applications, such as online payment or point of sale. The applications can be webpages, websites, web portals, mobile device applications, dedicated applications, and similar web-oriented tools and capabilities. The aggregated mental state information can be downloaded to the original client machine where the mental state information was uploaded from or alternately downloaded to another client machine for presentation. Mental states, which have been inferred based on the mental state information, can then be presented on a client machine display along with a rendering showing the material with which people interacted.
The flow 100 continues with collecting mental state data 122 from a plurality of people as they interact with a rendering. Mental state data that can be collected includes physiological data, facial data, other images, sounds, timelines of user activity, or any other information gathered about an individual's interaction with the rendering. Thus, the collecting mental state data involves capturing of one of a group comprising physiological data and facial data, in some embodiments. Mental state information can include the mental state data and any type of inferred information about the individuals including, but not limited to, frustration, confusion, disappointment, hesitation, cognitive overload, focusing, being engaged, attending, boredom, exploration, confidence, trust, delight, or satisfaction. An example of a rendering can be a checkout page on a website. If the total bill or the means of shipping is not clear, an individual can exhibit a mental state of confusion or uncertainty. In another example, a rendering can be a video trailer for a movie that will soon be released. An individual can find the plot line and action engaging, thereby exhibiting corresponding mental states such as attention and engagement, which can be collected along with and/or inferred from the mental state data.
An individual can opt in 124 to the collection of mental states or mental state data either before or after data is collected. In one embodiment, an individual is asked permission to collect mental states prior to viewing or interacting with a rendering. In another embodiment, an individual is asked permission to collect mental states after the rendering is interacted with or viewed. In this case, any information collected on mental states would be discarded if permission were not granted. In another embodiment, an individual is asked a general question about permission for collecting of mental states prior to viewing or interacting with a rendering and then a confirmation permission is requested after the rendering is interacted with or viewed. The intent of these opting-in permission requests would be to give the individual control over whether mental states and/or mental state data were collected and, further, what type of information can be used. In some embodiments, however, no opt-in permission is obtained, or the opt-in can be implicit due to the circumstances of the interaction. The flow 100 includes analyzing the facial data 126, wherein the analyzing is based on a plurality of image classifiers. In embodiments, the analyzing includes using an image classifier from the plurality of image classifiers to detect one or more faces in the facial data. In some embodiments, the analyzing further includes using an image classifier from the plurality of image classifiers to detect facial features or facial landmarks in the facial data.
The mental states and rendering context can be uploaded to a server 130. The process thus can include uploading information to a server, based on the mental state data, from the plurality of people who interact with the rendering. The uploading can only be for the actual data collected, and/or the uploading can be for inferred mental states. The collection of mental states 122 and capturing of rendering context 120 can be performed locally on a client computer. Alternatively, the physiological and/or facial data can be captured locally and uploaded to a server where further analysis is performed to infer the mental states. An individual can opt in 132 for allowing the uploading of information to the server. Thus, the process can include opting in, by an individual from the plurality of people, to allowing uploading of mental state data to the server. The information can also include context; thus, the process can also include opting in, by an individual from the plurality of people, to allowing uploading of information to the server. In some embodiments, the collected mental states are displayed to the individual prior to uploading of information. The individual can then be asked permission to upload the information. In some embodiments, an individual is further permission after uploading or is asked to confirm that the uploading which was performed is still acceptable. If permission is not granted during this opt-in 132 phase, then the information would be deleted from the server and not used any further. The flow 100 includes comparing a plurality of mental state event temporal signatures 134 against the information that was uploaded. In embodiments, multiple mental state event temporal signatures have been obtained from previous analysis of numerous people. The mental state event temporal signatures can include information on rise time to facial expression intensity, fall time from facial expression intensity, duration of a facial expression, and so on. In some embodiments, the mental state event temporal signatures are associated with certain demographics, ethnicities, cultures, etc. The mental state event temporal signatures can be used to identify one or more of sadness, stress, happiness, anger, frustration, confusion, disappointment, hesitation, cognitive overload, focusing, engagement, attention, boredom, exploration, confidence, trust, delight, disgust, skepticism, doubt, satisfaction, excitement, laughter, calmness, curiosity, humor, depression, envy, sympathy, embarrassment, poignancy, or mirth. The mental state event temporal signatures can be used to identify liking or satisfaction with a media presentation, for instance. The mental state event temporal signatures, in another example, can be used to correlate with appreciating a second media presentation.
Mental states can be aggregated 140 between multiple individuals. A single rendering can be interacted with or viewed by numerous people. The mental states can be collected for these people and then aggregated together so that an overall reaction by the people can be determined. The aggregation can occur in the same system/process or a different system/process than the system/process used to collect mental state or can occur on a server. The aggregated information on the mental states can then be sent between systems or between processes on the same system. Thus, the process can include receiving aggregated mental state information on the plurality of people who interact with the rendering. In some embodiments, the aggregated mental state information is based on the comparing of the plurality of mental state event temporal signatures. The comparing of the plurality of mental state event temporal signatures against the information that was uploaded can result in identification of a particular mental state. This mental state would correspond to an occurrence of a facial expression or series of expressions which match the particular mental state event temporal signature. A plurality of people can have common or similar facial expressions, or series of expressions, and these expressions match the particular mental state event temporal signature. Individuals can opt in 142 to having their mental state information aggregated with others. In some embodiments, an individual grants permission for their mental states to be aggregated or otherwise used in analysis. Thus, the process can include opting in, by an individual from the plurality of people, to allowing information on the face to be aggregated. This information can include all facial data or can include only part of the information. For instance, some individuals can choose to have video of their faces excluded but other information on facial action units, head gestures, and the like included. In some embodiments, the aggregating is accomplished using computational aggregation. In some embodiments, analysis is integrated over several web pages, over multiple renderings, or over a period of time. For example, a checkout experience can include four web pages and the objective is to capture the reaction to this group of four web pages. Thus, the analysis can include integrating the inferred mental states for the four pages for an individual. Further, the inferred mental states for these four pages can be aggregated and thereby combined for the multiple individuals.
The flow 100 can continue with displaying the aggregated mental states with the rendering 150. Thus, the process can include displaying the aggregated mental state information with the rendering. The information associated can include facial video, other facial data, physiological data, and inferred mental states. In some embodiments, the mental states are synchronized with the rendering using a timeline, webpage sequence order, or another rendering context. The process can therefore continue with associating the aggregated mental state information with the rendering.
Mental states can be inferred based on physiological data, such as physiological data from the sensor, or inferred based on facial expressions and head gestures observed by a webcam. The mental states can be analyzed based on arousal and valence. Arousal can range from being highly activated, such as when someone is agitated, to being entirely passive, such as when someone is bored. Valence can range from being very positive, such as when someone is happy, to being very negative, such when someone is angry. Physiological data can include electrodermal activity (EDA) or skin conductance or galvanic skin response (GSR), accelerometer readings, skin temperature, heart rate, heart rate variability, and other types of analysis of a human being. In embodiments, a webcam is used to capture the physiological data. It will be understood that both here and elsewhere in this document, physiological information can be obtained either by sensor or by facial observation. Facial data can include facial actions and head gestures used to infer mental states. Further, the data can include information on hand gestures or body language and body movements such as visible fidgets. In some embodiments, these movements are captured by cameras or by sensor readings. Facial data can include tilting the head to the side, leaning forward, a smile, a frown, as well as many other gestures or expressions.
In some embodiments, electrodermal activity is collected continuously, every second, four times per second, eight times per second, 32 times per second, or on some other periodic basis. The electrodermal activity can be recorded. The recording can be to a disk, a tape, onto flash memory, into a computer system, or streamed to a server. The electrodermal activity can be analyzed 230 to indicate arousal, excitement, boredom, or other mental states based on changes in skin conductance. Skin temperature can be collected on a periodic basis and can be recorded. The skin temperature can be analyzed 232 and can indicate arousal, excitement, boredom, or other mental states based on changes in skin temperature. Accelerometer data can be collected and indicate one, two, or three dimensions of motion. The accelerometer data can be recorded. The accelerometer data can be analyzed 234 and can indicate a sleep pattern, a state of high activity, a state of lethargy, or another state based on accelerometer data. The various data collected by the sensor 212 can be used along with the facial data captured by the webcam. Thus, in some embodiments, mental state data is collected by capturing of one of a group comprising physiological data and facial data.
Analysis of action units, gestures, and mental states 442 can be accomplished using the captured images of the person 420. The action units can be used to identify smiles, frowns, and other facial indicators of mental states. The gestures, including head gestures, can indicate interest or curiosity. For example, a head gesture of moving toward the electronic display 410 can indicate increased interest or a desire for clarification. Based on the captured images, analysis of physiological data 444 can be performed. Respiration, heart rate, heart rate variability, perspiration, temperature, and other physiological indicators of mental state can be observed by analyzing the images. Therefore, in various embodiments, a webcam is used to capture one or more of the facial data and the physiological data.
In some embodiments, a webcam is used to track the eyes. Tracking of eyes 446 to identify the rendering with which interacting is accomplished can be performed. In some embodiments, the tracking of the eyes identifies a portion of the rendering on which the eyes are focused. Thus, various embodiments perform tracking of eyes to identify one of the rendering and a portion of the rendering, by which interacting is accomplished. In this manner, by tracking of eyes, mental states can be associated with a specific rendering or portion of the rendering. For example, if a button on a webpage is unclear as to its function, a person can indicate confusion. By tracking of eyes, it will be clear that the confusion is over the button in question, rather than some other portion of the web page. Likewise, if a banner ad is present, by tracking of eyes, the portion of the banner ad which exhibits the highest arousal and positive valence can be determined. Further, in some embodiments, the process includes recording of eye dwell-time on the rendering and associating information on the eye dwell-time to the rendering and to the mental states. The eye dwell-time can be used to augment the mental state information to indicate the level of interest in certain renderings or portion of renderings.
In other embodiments, computerized direct recognition 535 of facial expressions and head gestures or mental states is performed. When direct recognition is performed, feature recognition and classification can be included in the process. An analysis of mental states 540 can be performed. The mental states can include frustration, confusion, disappointment, hesitation, cognitive overload, focusing, being engaged, attending, boredom, exploration, confidence, trust, delight, and satisfaction, as well many others.
The mental states can be aggregated 640 with other people's mental state information which was collected. In some embodiments, aggregating mental state information on the plurality of people who interact with the rendering is accomplished. Receiving aggregated mental state information, based on the mental state data from the plurality of people who interact with the rendering, is accomplished in other embodiments, where the aggregating is done on a different system. Each of the people can have interacted with or viewed the same rendering. The mental states are collected and synchronized with information about the rendering. The synchronization can be based on a timeline, a sequence of web pages viewed, an eye tracking of a rendering or portion of a rendering, or some other synchronization technique. The aggregation can be by means of scaling of collected information. The aggregation can be combining of various mental states that were inferred. The aggregation can be a combination of electrodermal activity, heart rate, heart rate variability, respiration, or some other physiological reading. The aggregation can involve computational aggregation. In some embodiments, aggregation involves noise cleaning of the data through techniques involving a low pass and/or a high pass filter or a band pass filter on the data. Normalization can occur to remove any noise spikes on the data. Noise spikes are frequently removed through nonlinear filtering, such as robust statistics or morphological filters. Time shifts can occur to put the data collected on the same effective timeline. In some embodiments, this time shifting is referred to as time warping. Normalization and time warping can be interchanged in order. The data collected can be averaged. Robust statistics such as median values can be obtained. Using these techniques, outliers are removed and data below a certain threshold is discarded. Finally, visualization and display can be performed on the data. For example, electrodermal activity measurements can be aggregated using the techniques described above so that a quantitative set of numbers representing a group of people's responses can be determined. Additionally, in some embodiments, non-linear stretching is used to focus on a small range of information. For example, a specific time range can be of particular interest due to the mental state response. Therefore, the time before and after this time can be compressed, while the time range of interest is expanded. In some embodiments, the aggregated mental state information includes norms derived from the plurality of people. The norms can be based on contextual information, where the contextual information can be based on information from the rendering, information from sensors, or the like. In embodiments, norms are derived based on the mental state event temporal signatures. In embodiments, the flow 600 further comprises collecting further mental state data from a first individual and comparing the further mental state data from the first individual 642 with the aggregated mental state information. The collecting of the further mental state data can be accomplished by video collection of facial data. The comparing can be used to identify common characteristics or differences between the individual and a population of people. In some embodiments, the flow 600 further comprises collecting additional further mental state data from a second individual and comparing the additional further mental state data from the second individual with the aggregated mental state information. The comparing can also identify differences between the first and the second individuals. In embodiments, the first individual and the second individual are part of the plurality of people. In other embodiments, the first individual and the second individuals are part of a different population and the comparing is used to target various products or services provided through a web-enabled application.
The flow 600 continues by associating the aggregated mental state information with the rendering 650. The rendering, such as a web page, video, or some other web-enabled application, can have aggregated mental states associated with the rendering. In this manner, a web page button can be associated with confusion, a video trailer associated with anticipation, or a check-out page or pages associated with confidence. Likewise, certain times in a video can be associated with positive mental states, while other times in a video can be associated with negative mental states.
The mental states can be shared 660. The aggregated mental state information can be shared with an individual or group of people. Mental state information from an individual can be shared with another individual or group of people. In some embodiments, providing the aggregated mental state information to a requester is accomplished, while displaying the aggregated mental state information with the rendering is accomplished in other embodiments. This sharing of information can be help people see what other people liked and disliked. Similarly, content can be recommended 662. For example, a video trailer which evoked a strong arousal and a positive valence can be recommended to others who share similar mental states for other video trailers. Additionally, an avatar can be animated 664 based on the mental states. The animation can be of just a face, a head, an upper half of a person, or a whole person. The animation can be based on an individual's mental state information. Alternatively, the animation can be based on the aggregated mental state information. In embodiments, mental state information for an individual is compared with the aggregated mental states. Differences between the individual and the aggregated mental states can be highlighted.
The flow 700 continues with the capture of information 720. The information captured can include facial data, physiological data, accelerometer data, or some other data. The information is analyzed 730 to infer mental states. The analysis can involve client computer analysis of facial data, head gestures, physiological data, accelerometer data, and other collected data. The results of the analysis can be presented 740 to the individual. For example, the mental states and collected information can be presented. Based on the permission requested, the client computer can determine that it is acceptable to upload 750 the captured information and/or the analysis results. A further request for permission can be requested at this time, based on the presented analysis 740, such as to allow the opting-in by an individual from the plurality of people, or to allow uploading of mental state data. If permission is not obtained for uploading of the analysis or information, the analysis or information can be discarded 760. If the permission to upload is obtained, the information and/or analysis can be provided to a web service 770. The web service can provide additional analysis, aggregate the mental state information, or provide for sharing of the analysis or mental state information.
Various information and analysis results can also be shown. In some embodiments, the additional information is shown in the display window 800 below the rendering 810 and the video 820. Any type of information can be shown, including mental state information from an individual, aggregated mental state information from a group of people, or other information about the rendering 810, the video 820, the individual or group of people from whom the mental state information was captured, or any other type of information. Thus, a visual representation of one or more of the aggregated mental state information and mental state information on an individual from the plurality of people is created, in some embodiments. The mental state information can include any type of mental state information described herein, including electrodermal activity, accelerometer readings, frown markers, smile markers, as well as numerous other possible physiological and mental state indicators. By way of example, in the display window 800, a smile marker track 830 is provided. Where a narrow line on the smile marker track 830 exists, a hint of smile was detected. Where a solid dark line is shown, a broad smile, lasting for a while, was detected. This smile marker track can have a timeline 832, as shown, and the timeline 832 can also have a slider bar 840, as shown. The slider bar 840 can be moved to various points on the timeline 832 and the rendering 810 and the video 820 can each show what occurred at that point in time. By further example, an electrodermal activity track 850 is shown as well. While the display window 800 can show an individual, this window or set of windows can create a visual representation of the aggregated mental state information as well. For instance, once electrodermal activity information has been aggregated for a group of people, the aggregated electrodermal activity can be displayed for the rendering 810. As stated earlier, numerous displays of information and analysis are possible in this window or set of windows. These displays can be for the individual or for an aggregated group of people.
Various information and aggregated analysis results can be shown including, for example, electrodermal activity, accelerometer readings, frown markers, smile markers, as well as numerous other possible physiological and mental state indicators. By way of example, in the display window 900, a smile marker track 930 is provided. Where a narrow line on the smile marker track 930 exists, a hint of smile was detected as a majority response of the multiple people. Where a solid dark line is shown, a broad smile that lasts for a long time was detected as a majority response of multiple people. This smile marker track can have a timeline 932, as shown, and the timeline 932 can also have a slider bar 940, as shown. The slider bar 940 can be moved to various points on the timeline 932 and the rendering 910 can show what occurred at that point in time, synchronizing the aggregated mental state information with the rendering. By further example, an aggregated electrodermal activity track 950 can also be included. As stated earlier, numerous displays of information and analysis are possible in this window or set of windows. In some embodiments, each of these portions are individual floating windows which can be repositioned as the user desires.
Some embodiments include the ability for a user to select a particular type of mental state information for display using various buttons or other selection methods. In the example shown, the smile mental state information is shown as the user might have previously selected the Smile button 1140. Other types of mental state information that are available for user selection in various embodiments include the Lowered Eyebrows button 1142, the Eyebrow Raise button 1144, the Attention button 1146, the Valence Score button 1148, or other types of mental state information, depending on the embodiment. An Overview button 1149 can be available to allow a user to show graphs of the multiple types of mental state information simultaneously.
Because the Smile option 1140 has been selected in the example shown, a smile graph 1150 can be shown against a baseline 1152 showing the aggregated smile mental state information of the plurality of individuals from whom mental state data was collected for the rendering 1110. A male smile graph 1154 and a female smile graph 1156 can be shown so that the visual representation displays the aggregated mental state information on a demographic basis. The various demographic based graphs can be indicated using various line types, as shown, or can be indicated using color or another method of differentiation. A slider 1158 can allow a user to select a particular time of the timeline and show the value of the chosen mental state for that particular time. The slider can show the same line type or color as the demographic group whose value is shown.
In some embodiments, various types of demographic based mental state information are selected using the demographic button 1160. Such demographics can include gender, age, race, income level, or any other type of demographic, including dividing the respondents into those respondents that had a higher reaction from those with lower reactions. A graph legend 1162 can be displayed indicating the various demographic groups, the line type or color for each group, the percentage of total respondents and or absolute number of respondents for each group, and/or other information about the demographic groups. The mental state information can be aggregated according to the demographic type selected. Thus, for some embodiments, aggregation of the aggregated mental state information is performed on a demographic basis so that mental state information is grouped based on the demographic basis.
In some embodiments, graphical smiley face icons 1240, 1242, and 1244 are shown, providing an indication of the amount of a smile or another facial expression. A first very broad smiley face icon 1240 can indicate a very large smile being observed. A second normal smiley face icon 1242 can indicate a smile being observed. A third face icon 1244 can indicate no smile. Each of the icons can correspond to a region on the y-axis 1220 that indicate the probability or intensity of a smile.
The eyes can be tracked 1322 to determine where the first person 1312 is focused on the display. The flow 1300 includes uploading information 1324 to a server on the data which was captured on the first person. Permission can again be asked before the upload of information.
The flow 1300 continues with interacting with the rendering 1330 by a second person 1332. In some embodiments, there is a query for the second person 1332 to opt in 1334 to the process of capturing data. If allowable by the second person, the flow 1300 can continue by capturing context and capturing data 1340 on the second person as the second person interacts with the rendering. The eyes can be tracked 1342 to determine where the second person 1332 is focused on the display. The flow 1300 can include uploading information 1344 to the server on the data which was captured on the second person. Permission can again be asked before the upload of information.
The flow 1300 continues with the inferring of mental states 1350 for the first person who interacted with the rendering, based on the data which was captured for the first person, and inferring of mental states 1350 for the second person who interacted with the rendering, based on the data which was captured for the second person. This inferring 1350 can be done on the client computers of the first and second person, respectively. Alternatively, the inferring of mental states 1350 can be performed on the server computer after the upload of information or on some other computer with access to the uploaded information. The inferring of mental states can be based on one of a group comprising physiological data and facial data, in some embodiments, and can include inferring of mental states based on the mental state data collected from the plurality of people. The inferring of mental states is based on both physiological data and facial data, in some embodiments. The mental states can be synchronized with the rendering 1352. In one embodiment, this synchronization correlates the mental states with a timeline that is part of a video. In embodiments, the synchronization correlates the mental states with a specific web page or a certain sequence of web pages. The synchronization 1352 can be performed on the first and second person's client computers, respectively, can be performed on a server computer after uploading, or can be performed by some other computer.
The flow 1300 continues with aggregating 1354 information on the mental states of the first person with the mental states of the second person, resulting in aggregated mental state information. The aggregating 1354 can include computational aggregation. The aggregation can be performed using one or more processors. The aggregation can include combining electrodermal activity or other readings from multiple people. The flow 1300 continues with associating to the rendering 1356 the aggregated mental state information 1354 with which the first person and the second person interacted. The associating of the aggregated mental state information 1356 allows recall and further analysis of the rendering and peoples' mental state reactions to the rendering. The flow 1300 continues with visualization 1358 of the aggregated and/or associated mental state information. This visualization can include graphical or textual presentation. The visualization can also include a presentation in the form of an avatar. The flow 1300 can continue with any number of people's data being captured, mental states being inferred, and all other steps in the flow.
As the user 1510 is monitored, the user 1510 might move due to the nature of the task, boredom, discomfort, distractions, or for another reason. As the user moves, the camera with a view of the user's face can be changed. Thus, as an example, if the user 1510 is looking in a first direction, the line of sight 1524 from the webcam 1522 is able to observe the user's face, but if the user is looking in a second direction, the line of sight 1534 from the mobile camera 1530 is able to observe the user's face. Furthermore, in other embodiments, if the user is looking in a third direction, the line of sight 1544 from the phone camera 1542 is able to observe the user's face, and if the user is looking in a fourth direction, the line of sight 1554 from the tablet camera 1552 is able to observe the user's face. If the user is looking in a fifth direction, the line of sight 1564 from the wearable camera 1562, which can be a device such as the glasses 1560 shown and can be worn by another user or an observer, is able to observe the user's face. If the user is looking in a sixth direction, the line of sight 1574 from the wearable watch-type device 1570, with a camera 1572 included on the device, is able to observe the user's face. In other embodiments, the wearable device is another device, such as an earpiece with a camera, a helmet or hat with a camera, a clip-on camera attached to clothing, or any other type of wearable device with a camera or other sensor for collecting expression data. The user 1510 can also use a wearable device including a camera for gathering contextual information and/or collecting expression data on other users. Because the user 1510 can move her or his head, the facial data can be collected intermittently when she or he is looking in a direction of a camera. In some cases, multiple people can be included in the view from one or more cameras, and some embodiments include filtering out faces of one or more other people to determine whether the user 1510 is looking toward a camera. All or some of the expression data can be continuously or sporadically available from the various devices and other devices.
The captured video data can include facial expressions and can be analyzed on a computing device such as the video capture device or on another separate device. The analysis could take place on one of the mobile devices discussed above, on a local server, on a remote server, and so on. In embodiments, some of the analysis takes place on the mobile device, while other analysis takes place on a server device. The analysis of the video data can include the use of a classifier. The video data can be captured using one of the mobile devices discussed above and sent to a server or another computing device for analysis. However, the captured video data including expressions can also be analyzed on the device which performed the capturing. The analysis can be performed on a mobile device where the videos were obtained with the mobile device and wherein the mobile device includes one or more of a laptop computer, a tablet, a PDA, a smartphone, a wearable device, and so on. In another embodiment, the analyzing comprises using a classifier on a server or another computing device other than the capturing device.
Classification can be based on various types of algorithms, heuristics, codes, procedures, statistics, and so on. Many techniques exist for performing classification. This classification of one or more observations into one or more groups can be based on distributions of the data values, probabilities, and so on. Classifiers can be binary, multiclass, linear, and so on. Algorithms for classification can be implemented using a variety of techniques, including neural networks, kernel estimation, support vector machines, use of quadratic surfaces, and so on. Classification can be used in many application areas such as computer vision, speech and handwriting recognition, and so on. Classification can be used for biometric identification of one or more people in one or more frames of one or more videos.
Returning to
A second video frame 1602 is also shown. The second video frame 1602 includes a frame boundary 1630, a first face 1632, and a second face 1634. The second video frame 1602 also includes a bounding box 1640 and the facial landmarks, or points, 1642, 1644, and 1646. In other embodiments, multiple facial landmarks are generated and used for facial tracking of the two or more faces of a video frame, such as the shown second video frame 1602. Facial points from the first face can be distinguished from other facial points. In embodiments, the other facial points include facial points of one or more other faces. The facial points can correspond to the facial points of the second face. The distinguishing of the facial points of the first face and the facial points of the second face can be used to distinguish between the first face and the second face, to track either or both of the first face and the second face, and so on. Other facial points can correspond to the second face. As mentioned above, multiple facial points can be determined within a frame. One or more of the other facial points that are determined can correspond to a third face. The location of the bounding box 1640 can be estimated, where the estimating can be based on the location of the generated bounding box 1620 shown in the first video frame 1600. The three facial points shown, facial points, or landmarks, 1642, 1644, and 1646, might lie within the bounding box 1640 or might not lie partially or completely within the bounding box 1640. For instance, the second face 1634 might have moved between the first video frame 1600 and the second video frame 1602. Based on the accuracy of the estimating of the bounding box 1640, a new estimation can be determined for a third, future frame from the video, and so on. The evaluation can be performed, all or in part, on semiconductor based logic.
Several live streaming social media apps and platforms can be used for transmitting video. One such video social media app is Meerkat™ that can link with a user's Twitter™ account. Meerkat™ enables a user to stream video using a handheld, networked electronic device coupled to video capabilities. Viewers of the live stream can comment on the stream using tweets that can be seen by and responded to by the broadcaster. Another popular app is Periscope™ that can transmit a live recording from one user to that user's Periscope™ account and other followers. The Periscope™ app can be executed on a mobile device. The user's Periscope™ followers can receive an alert whenever that user begins a video transmission. Another live-stream video platform is Twitch™ that can be used for video streaming of video gaming and broadcasts of various competitions and events.
The example 1700 shows a user 1710 broadcasting a video live stream to one or more people as shown by the person 1750, the person 1760, and the person 1770. A portable, network-enabled, electronic device 1720 can be coupled to a forward-facing camera 1722. The portable electronic device 1720 can be a smartphone, a PDA, a tablet, a laptop computer, and so on. The camera 1722 coupled to the device 1720 can have a line-of-sight view 1724 to the user 1710 and can capture video of the user 1710. The captured video can be sent to an analysis or recommendation engine 1740 using a network link 1726 to the Internet 1730. The network link can be a wireless link, a wired link, and so on. The recommendation engine 1740 can recommend to the user 1710 an app and/or platform that can be supported by the server and can be used to provide a video live stream to one or more followers of the user 1710. In the example 1700, the user 1710 has three followers: the person 1750, the person 1760, and the person 1770. Each follower has a line-of-sight view to a video screen on a portable, networked electronic device. In other embodiments, one or more followers follow the user 1710 using any other networked electronic device, including a computer. In the example 1700, the person 1750 has a line-of-sight view 1752 to the video screen of a device 1754; the person 1760 has a line-of-sight view 1762 to the video screen of a device 1764, and the person 1770 has a line-of-sight view 1772 to the video screen of a device 1774. The portable electronic devices 1754, 1764, and 1774 can each be a smartphone, a PDA, a tablet, and so on. Each portable device can receive the video stream being broadcasted by the user 1710 through the Internet 1730 using the app and/or platform that can be recommended by the recommendation engine 1740. The device 1754 can receive a video stream using the network link 1756, the device 1764 can receive a video stream using the network link 1766, the device 1774 can receive a video stream using the network link 1776, and so on. The network link can be a wireless link, a wired link, a hybrid link, and so on. Depending on the app and/or platform that can be recommended by the recommendation engine 1740, one or more followers, such as the followers 1750, 1760, 1770, and so on, can reply to, comment on, and otherwise provide feedback to the user 1710 using their devices 1754, 1764, and 1774, respectively.
The human face provides a powerful communications medium through its ability to exhibit a myriad of expressions that can be captured and analyzed for a variety of purposes. In some cases, media producers are acutely interested in evaluating the effectiveness of message delivery by video media. Such video media includes advertisements, political messages, educational materials, television programs, movies, government service announcements, etc. Automated facial analysis can be performed on one or more video frames containing a face in order to detect facial action. Based on the facial action detected, a variety of parameters can be determined, including affect valence, spontaneous reactions, facial action units, and so on. The parameters that are determined can be used to infer or predict emotional and mental states. For example, determined valence can be used to describe the emotional reaction of a viewer to a video media presentation or another type of presentation. Positive valence provides evidence that a viewer is experiencing a favorable emotional response to the video media presentation, while negative valence provides evidence that a viewer is experiencing an unfavorable emotional response to the video media presentation. Other facial data analysis can include the determination of discrete emotional states of the viewer or viewers.
Facial data can be collected from a plurality of people using any of a variety of cameras. A camera can include a webcam, a video camera, a still camera, a thermal imager, a CCD device, a phone camera, a three-dimensional camera, a depth camera, a light field camera, multiple webcams used to show different views of a person, or any other type of image capture apparatus that can allow captured data to be used in an electronic system. In some embodiments, the person is permitted to “opt-in” to the facial data collection. For example, the person can agree to the capture of facial data using a personal device such as a mobile device or another electronic device by selecting an opt-in choice. Opting-in can then turn on the person's webcam-enabled device and can begin the capture of the person's facial data via a video feed from the webcam or other camera. The video data that is collected can include one or more persons experiencing an event. The one or more persons can be sharing a personal electronic device or can each be using one or more devices for video capture. The videos that are collected can be collected using a web-based framework. The web-based framework can be used to display the video media presentation or event as well as to collect videos from multiple viewers who are online. That is, the collection of videos can be crowdsourced from those viewers who elected to opt-in to the video data collection.
The videos captured from the various viewers who chose to opt-in can be substantially different in terms of video quality, frame rate, etc. As a result, the facial video data can be scaled, rotated, and otherwise adjusted to improve consistency. Human factors further play into the capture of the facial video data. The facial data that is captured might or might not be relevant to the video media presentation being displayed. For example, the viewer might not be paying attention, might be fidgeting, might be distracted by an object or event near the viewer, or otherwise inattentive to the video media presentation. The behavior exhibited by the viewer can prove challenging to analyze due to viewer actions including eating, speaking to another person or persons, speaking on the phone, etc. The videos collected from the viewers might also include other artifacts that pose challenges during the analysis of the video data. The artifacts can include items such as eyeglasses (because of reflections), eye patches, jewelry, and clothing that occludes or obscures the viewer's face. Similarly, a viewer's hair or hair covering can present artifacts by obscuring the viewer's eyes and/or face.
The captured facial data can be analyzed using the facial action coding system (FACS). The FACS seeks to define groups or taxonomies of facial movements of the human face. The FACS encodes movements of individual muscles of the face, where the muscle movements often include slight, instantaneous changes in facial appearance. The FACS encoding is commonly performed by trained observers but can also be performed on automated, computer-based systems. Analysis of the FACS encoding can be used to determine emotions of the persons whose facial data is captured in the videos. The FACS is used to encode a wide range of facial expressions that are anatomically possible for the human face. The FACS encodings include action units (AUs) and related temporal segments that are based on the captured facial expression. The AUs are open to higher order interpretation and decision-making. These AUs can be used to recognize emotions experienced by the observed person. Emotion-related facial actions can be identified using the emotional facial action coding system (EMFACS) and the facial action coding system affect interpretation dictionary (FACSAID). For a given emotion, specific action units can be related to the emotion. For example, the emotion of anger can be related to AUs 4, 5, 7, and 23, while happiness can be related to AUs 6 and 12. Other mappings of emotions to AUs have also been previously associated. The coding of the AUs can include an intensity scoring that ranges from A (trace) to E (maximum). The AUs can be used for analyzing images to identify patterns indicative of a particular mental and/or emotional state. The AUs range in number from 0 (neutral face) to 98 (fast up-down look). The AUs include so-called main codes (inner brow raiser, lid tightener, etc.), head movement codes (head turn left, head up, etc.), eye movement codes (eyes turned left, eyes up, etc.), visibility codes (eyes not visible, entire face not visible, etc.), and gross behavior codes (sniff, swallow, etc.). Emotion scoring can be included where intensity is evaluated, as well as specific emotions, moods, or mental states.
The coding of faces identified in videos captured of people observing an event can be automated. The automated systems can detect facial AUs or discrete emotional states. The emotional states can include amusement, fear, anger, disgust, surprise, and sadness. The automated systems can be based on a probability estimate from one or more classifiers, where the probabilities can correlate with an intensity of an AU or an expression. The classifiers can be used to identify into which of a set of categories a given observation can be placed. In some cases, the classifiers can be used to determine a probability that a given AU or expression is present in a given frame of a video. The classifiers can be used as part of a supervised machine learning technique, where the machine learning technique can be trained using “known good” data. Once trained, the machine learning technique can proceed to classify new data that is captured.
The supervised machine learning models can be based on support vector machines (SVMs). An SVM can have an associated learning model that is used for data analysis and pattern analysis. For example, an SVM can be used to classify data that can be obtained from collected videos of people experiencing a media presentation. An SVM can be trained using “known good” data that is labeled as belonging to one of two categories (e.g. smile and no-smile). The SVM can build a model that assigns new data into one of the two categories. The SVM can construct one or more hyperplanes that can be used for classification. The hyperplane that has the largest distance from the nearest training point can be determined to have the best separation. The largest separation can improve the classification technique by increasing the probability that a given data point can be properly classified.
In another example, a histogram of oriented gradients (HoG) can be computed. The HoG can include feature descriptors and can be computed for one or more facial regions of interest. The regions of interest of the face can be located using facial landmark points, where the facial landmark points can include outer edges of nostrils, outer edges of the mouth, outer edges of eyes, etc. A HoG for a given region of interest can count occurrences of gradient orientation within a given section of a frame from a video, for example. The gradients can be intensity gradients and can be used to describe an appearance and a shape of a local object. The HoG descriptors can be determined by dividing an image into small, connected regions, also called cells. A histogram of gradient directions or edge orientations can be computed for pixels in the cell. Histograms can be contrast-normalized based on intensity across a portion of the image or the entire image, thus reducing any influence from illumination or shadowing changes between and among video frames. The HoG can be computed on the image or on an adjusted version of the image, where the adjustment of the image can include scaling, rotation, etc. The image can be adjusted by flipping the image around a vertical line through the middle of a face in the image. The symmetry plane of the image can be determined from the tracker points and landmarks of the image.
In embodiments, an automated facial analysis system identifies five facial actions or action combinations in order to detect spontaneous facial expressions for media research purposes. Based on the facial expressions that are detected, a determination can be made with regard to the effectiveness of a given video media presentation, for example. The system can detect the presence of the AUs or the combination of AUs in videos collected from a plurality of people. The facial analysis technique can be trained using a web-based framework to crowdsource videos of people as they watch online video content. The video can be streamed at a fixed frame rate to a server. Human labelers can code for the presence or absence of facial actions including a symmetric smile, unilateral smile, asymmetric smile, and so on. The trained system can then be used to automatically code the facial data collected from a plurality of viewers experiencing video presentations (e.g. television programs).
Spontaneous asymmetric smiles can be detected in order to understand viewer experiences. Related literature indicates that as many asymmetric smiles occur on the right hemi face as do on the left hemi face, for spontaneous expressions. Detection can be treated as a binary classification problem, where images that contain a right asymmetric expression are used as positive (target class) samples and all other images as negative (non-target class) samples. Classifiers perform the classification, including classifiers such as support vector machines (SVM) and random forests. Random forests can include ensemble-learning methods that use multiple learning algorithms to obtain better predictive performance. Frame-by-frame detection can be performed to recognize the presence of an asymmetric expression in each frame of a video. Facial points can be detected, including the top of the mouth and the two outer eye corners. The face can be extracted, cropped and warped into a pixel image of specific dimension (e.g. 96×96 pixels). In embodiments, the inter-ocular distance and vertical scale in the pixel image are fixed. Feature extraction can be performed using computer vision software such as OpenCV™. Feature extraction can be based on the use of HoGs. HoGs can include feature descriptors and can be used to count occurrences of gradient orientation in localized portions or regions of the image. Other techniques can be used for counting occurrences of gradient orientation, including edge orientation histograms, scale-invariant feature transformation descriptors, etc. The AU recognition tasks can also be performed using Local Binary Patterns (LBP) and Local Gabor Binary Patterns (LGBP). The HoG descriptor represents the face as a distribution of intensity gradients and edge directions and is robust in its ability to translate and scale. Differing patterns, including groupings of cells of various sizes and arranged in variously sized cell blocks, can be used. For example, 4×4 cell blocks of 8×8 pixel cells with an overlap of half of the block can be used. Histograms of channels can be used, including nine channels or bins evenly spread over 0-180 degrees. In this example, the HoG descriptor on a 96×96 image is 25 blocks×16 cells×9 bins=3600, the latter quantity representing the dimension. AU occurrences can be rendered. The videos can be grouped into demographic datasets based on nationality and/or other demographic parameters for further detailed analysis. This grouping and other analyses can be facilitated via semiconductor based logic.
The facial regions that can be collected by the camera 1930, sensor, or combination of cameras and/or sensors can include any of a variety of facial features. The facial features that can be included in the facial regions that are collected can include eyebrows 1940, eyes 1942, a nose 1944, a mouth 1946, ears, hair, texture, tone, and so on. Multiple facial features can be included in one or more facial regions. The number of facial features that can be included in the facial regions can depend on the desired amount of data to be captured, whether a face is in profile, whether the face is partially occluded or obstructed, etc. The facial regions that can include one or more facial features can be analyzed to determine facial expressions. The analysis of the facial regions can also include determining probabilities of occurrence of one or more facial expressions. The facial features that can be analyzed can also include textures, gradients, colors, shapes, etc. The facial features can be used to determine demographic data, where the demographic data can include age, ethnicity, culture, gender, etc. Multiple textures, gradients, colors, shapes, and so on, can be detected by the camera 1930, sensor, or combination of cameras and sensors. Texture, brightness, and color, for example, can be used to detect boundaries in an image for detection of a face, facial features, facial landmarks, and so on.
A texture in a facial region can include facial characteristics, skin types, and so on. In some instances, a texture in a facial region can include smile lines, crow's feet, wrinkles, and so on. Another texture that can be used to evaluate a facial region can include a smooth portion of skin such as a smooth portion of a check. A gradient in a facial region can include values assigned to local skin texture, shading, etc. A gradient can be used to encode, for example, a texture, by computing magnitudes in a local neighborhood or portion of an image. The computed values can be compared to discrimination levels, threshold values, and so on. The gradient can be used to determine gender, facial expression, etc. A color in a facial region can include eye color, skin color, hair color, and so on. A color can be used to determine demographic data, where the demographic data can include ethnicity, culture, age, gender, etc. A shape in a facial region can include shape of a face, eyes, nose, mouth, ears, and so on. As with color in a facial region, shape in a facial region can be used to determine demographic data including ethnicity, culture, age, gender, and so on.
The facial regions can be detected based on detection of edges, boundaries, and so on, of features that can be included in an image. The detection can be based on various types of analysis of the image. The features that can be included in the image can include one or more faces. A boundary can refer to a contour in an image plane where the contour can represent ownership of a particular picture element (pixel) from one object, feature, etc. in the image, to another object, feature, and so on, in the image. An edge can be a distinct, low-level change of one or more features in an image. That is, an edge can be detected based on a change, including an abrupt change, in color, brightness, etc. within an image. In embodiments, image classifiers are used for the analysis. The image classifiers can include algorithms, heuristics, and so on, and can be implemented using functions, classes, subroutines, code segments, etc. The classifiers can be used to detect facial regions, facial features, and so on. As discussed above, the classifiers can be used to detect textures, gradients, color, shapes, edges, etc. Any classifier can be used for the analysis, including, but not limited to, density estimation, support vector machines (SVM), logistic regression, classification trees, and so on. By way of example, consider facial features that can include the eyebrows 1940. One or more classifiers can be used to analyze the facial regions that can include the eyebrows to determine a probability for either a presence or an absence of an eyebrow furrow. The probability can include a posterior probability, a conditional probability, and so on. The probabilities can be based on Bayesian Statistics or another statistical analysis technique. The presence of an eyebrow furrow can indicate the person from whom the facial data can be collected is annoyed, confused, unhappy, and so on. In another example, consider facial features that can include a mouth 1946. One or more classifiers can be used to analyze the facial region that can include the mouth to determine a probability for either a presence or an absence of mouth edges turned up to form a smile. Multiple classifiers can be used to determine one or more facial expressions.
The flow 2000 begins by obtaining training image samples 2010. The image samples can include a plurality of images of one or more people. Human coders who are trained to correctly identify AU codes based on the FACS can code the images. The training or “known good” images can be used as a basis for training a machine learning technique. Once trained, the machine learning technique can be used to identify AUs in other images that can be collected using a camera, a sensor, and so on. The flow 2000 continues with receiving an image 2020. The image 2020 can be received from a camera, a sensor, and so on. As previously discussed, the camera or cameras can include a webcam, where a webcam can include a video camera, a still camera, a thermal imager, a CCD device, a phone camera, a three-dimensional camera, a depth camera, a light field camera, multiple webcams used to show different views of a person, or any other type of image capture apparatus that can allow captured data to be used in an electronic system. The image that is received can be manipulated in order to improve the processing of the image. For example, the image can be cropped, scaled, stretched, rotated, flipped, etc. in order to obtain a resulting image that can be analyzed more efficiently. Multiple versions of the same image can be analyzed. In some cases, the manipulated image and a flipped or mirrored version of the manipulated image can be analyzed alone and/or in combination to improve analysis. The flow 2000 continues with generating histograms 2030 for the training images and the one or more versions of the received image. The histograms can be based on a HoG or another histogram. As described in previous paragraphs, the HoG can include feature descriptors and can be computed for one or more regions of interest in the training images and the one or more received images. The regions of interest in the images can be located using facial landmark points, where the facial landmark points can include outer edges of nostrils, outer edges of the mouth, outer edges of eyes, etc. A HoG for a given region of interest can count occurrences of gradient orientation within a given section of a frame from a video.
The flow 2000 continues with applying classifiers 2040 to the histograms. The classifiers can be used to estimate probabilities, where the probabilities can correlate with an intensity of an AU or an expression. In some embodiments, the choice of classifiers used is based on the training of a supervised learning technique to identify facial expressions. The classifiers can be used to identify into which of a set of categories a given observation can be placed. The classifiers can be used to determine a probability that a given AU or expression is present in a given image or frame of a video. In various embodiments, the one or more AUs that are present include AU01 inner brow raiser, AU12 lip corner puller, AU38 nostril dilator, and so on. In practice, the presence or absence of multiple AUs can be determined. The flow 2000 continues with computing a frame score 2050. The score computed for an image, where the image can be a frame from a video, can be used to determine the presence of a facial expression in the image or video frame. The score can be based on one or more versions of the image 2020 or a manipulated image. The score can be based on a comparison of the manipulated image to a flipped or mirrored version of the manipulated image. The score can be used to predict a likelihood that one or more facial expressions are present in the image. The likelihood can be based on computing a difference between the outputs of a classifier used on the manipulated image and on the flipped or mirrored image, for example. The classifier that is used can be used to identify symmetrical facial expressions (e.g. smile), asymmetrical facial expressions (e.g. outer brow raiser), and so on.
The flow 2000 continues with plotting results 2060. The results that are plotted can include one or more scores for one or more frames computed over a given time t. For example, the plotted results can include classifier probability results from analysis of HoGs for a sequence of images and video frames. The plotted results can be matched with a template 2062. The template can be temporal and can be represented by a centered box function or another function. A best fit with one or more templates can be found by computing a minimum error. Other best-fit techniques can include polynomial curve fitting, geometric curve fitting, and so on. The flow 2000 continues with applying a label 2070. The label can be used to indicate that a particular facial expression has been detected in the one or more images or video frames which constitute the image that was received 2020. The label can be used to indicate that any of a range of facial expressions has been detected, including a smile, an asymmetric smile, a frown, and so on. Various steps in the flow 2000 may be changed in order, repeated, omitted, or the like without departing from the disclosed concepts. Various embodiments of the flow 2000 can be included in a computer program product embodied in a non-transitory computer readable medium that includes code executable by one or more processors. Various embodiments of the flow 2000, or portions thereof, can be included on a semiconductor chip and implemented in special purpose logic, programmable logic, and so on.
The flow 2100 includes obtaining videos containing faces 2110. The videos can be obtained using one or more cameras, where the cameras can include a webcam coupled to one or more devices employed by the one or more people using the web-based framework. The flow 2100 continues with extracting features from the individual responses 2120. The individual responses can include videos containing faces observed by the one or more webcams. The features that are extracted can include facial features such as an eyebrow, a nostril, an eye edge, a mouth edge, and so on. The feature extraction can be based on facial coding classifiers, where the facial coding classifiers output a probability that a specified facial action has been detected in a given video frame. The flow 2100 continues with performing unsupervised clustering of features 2130. The unsupervised clustering can be based on an event. The unsupervised clustering can be based on a K-Means, where the K of the K-Means can be computed using a Bayesian Information Criterion (BICk), for example, to determine the smallest value of K that meets system requirements. Any other criterion for K can be used. The K-Means clustering technique can be used to group one or more events into various respective categories.
The flow 2100 includes characterizing cluster profiles 2140. The profiles can include a variety of facial expressions such as smiles, asymmetric smiles, eyebrow raisers, eyebrow lowerers, etc. The profiles can be related to a given event. For example, a humorous video can be displayed in the web-based framework and the video data of people who have opted-in can be collected. The characterization of the collected and analyzed video can depend in part on the number of smiles that occurred at various points throughout the humorous video. Similarly, the characterization can be performed on collected and analyzed videos of people viewing a news presentation. The characterized cluster profiles can be further analyzed based on demographic data. The number of smiles resulting from people viewing a humorous video can be compared to various demographic groups, where the groups can be formed based on geographic location, age, ethnicity, gender, and so on.
The flow 2100 can include determining mental state event temporal signatures 2150. The mental state event temporal signatures can include information on rise time to facial expression intensity, fall time from facial expression intensity, duration of a facial expression, and so on. In some embodiments, the mental state event temporal signatures are associated with certain demographics, ethnicities, cultures, etc. The mental state event temporal signatures can be used to identify one or more of sadness, stress, happiness, anger, frustration, confusion, disappointment, hesitation, cognitive overload, focusing, engagement, attention, boredom, exploration, confidence, trust, delight, disgust, skepticism, doubt, satisfaction, excitement, laughter, calmness, curiosity, humor, depression, envy, sympathy, embarrassment, poignancy, or mirth. Various steps in the flow 2100 may be changed in order, repeated, omitted, or the like without departing from the disclosed concepts. Various embodiments of the flow 2100 can be included in a computer program product embodied in a non-transitory computer readable medium that includes code executable by one or more processors. Various embodiments of the flow 2100, or portions thereof, can be included on a semiconductor chip and implemented in special purpose logic, programmable logic, and so on.
The cluster profiles 2202 can be generated based on the clusters that can be formed from unsupervised clustering, with time shown on the x-axis and intensity or frequency shown on the y-axis. The cluster profiles can be based on captured facial data, including facial expressions. The cluster profile 2220 can be based on the cluster 2210, the cluster profile 2222 can be based on the cluster 2212, and the cluster profile 2224 can be based on the cluster 2214. The cluster profiles 2220, 2222, and 2224 can be based on smiles, smirks, frowns, or any other facial expression. The emotional states of the people who have opted-in to video collection can be inferred by analyzing the clustered facial expression data. The cluster profiles can be plotted with respect to time and can show a rate of onset, a duration, and an offset (rate of decay). Other time-related factors can be included in the cluster profiles. The cluster profiles can be correlated with demographic information, as described above.
The server 2430 can have an internet connection for mental states or mental state information 2431, a memory 2434 which stores instructions, and one or more processors 2432 attached to the memory 2434, wherein the one or more processors 2432 can execute instructions. The server 2430 can receive mental state information collected from a plurality of people as they interact with a rendering from the client computer 2420 and can aggregate mental state information on the plurality of people who interact with the rendering. The server 2430 can also associate the aggregated mental state information with the rendering and with the collection of norms for the context being measured. In some embodiments, the server 2430 also allows a user to view and evaluate the mental state information that is associated with the rendering, but in other embodiments, an analysis computer 2440 requests the aggregated mental state information 2441 from the server 2430. The server 2430 can then provide the aggregated mental state information 2441 to a requester, the analysis computer 2440. In some embodiments, the client computer 2420 also functions as the analysis computer 2440.
The analysis computer 2440 can have a memory 2446 which stores instructions, and one or more processors 2444 attached to the memory 2446, wherein the one or more processors 2444 can execute instructions. The analysis computer can use its internet, or another computer communication method, to request the aggregated mental state information 2441 from the server. The analysis computer 2440 can receive aggregated mental state information 2441, based on the mental state data, from the plurality of people who interact with the rendering and can present the aggregated mental state information with the rendering on a display 2442. In some embodiments, the analysis computer is set up for receiving mental state data collected from a plurality of people as they interact with a rendering, in a real-time or near real-time embodiment. In at least one embodiment, a single computer incorporates the client, server and analysis functionality.
Each of the above methods may be executed on one or more processors on one or more computer systems. Embodiments may include various forms of distributed computing, client/server computing, and cloud based computing. Further, it will be understood that for each flow chart in this disclosure, the depicted steps or boxes are provided for purposes of illustration and explanation only. The steps may be modified, omitted, or re-ordered and other steps may be added without departing from the scope of this disclosure. Further, each step may contain one or more sub-steps. While the foregoing drawings and description set forth functional aspects of the disclosed systems, no particular arrangement of software and/or hardware for implementing these functional aspects should be inferred from these descriptions unless explicitly stated or otherwise clear from the context. All such arrangements of software and/or hardware are intended to fall within the scope of this disclosure.
The block diagrams and flowchart illustrations depict methods, apparatus, systems, and computer program products. Each element of the block diagrams and flowchart illustrations, as well as each respective combination of elements in the block diagrams and flowchart illustrations, illustrates a function, step or group of steps of the methods, apparatus, systems, computer program products and/or computer-implemented methods. Any and all such functions may be implemented by computer program instructions, by special-purpose hardware-based computer systems, by combinations of special purpose hardware and computer instructions, by combinations of general purpose hardware and computer instructions, and so on. Any and all of which may be generally referred to herein as a “circuit,” “module,” or “system.”
A programmable apparatus which executes any of the above-mentioned computer program products or computer implemented methods may include one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors, programmable devices, programmable gate arrays, programmable array logic, memory devices, application specific integrated circuits, or the like. Each may be suitably employed or configured to process computer program instructions, execute computer logic, store computer data, and so on.
It will be understood that a computer may include a computer program product from a computer-readable storage medium and that this medium may be internal or external, removable and replaceable, or fixed. In addition, a computer may include a Basic Input/Output System (BIOS), firmware, an operating system, a database, or the like that may include, interface with, or support the software and hardware described herein.
Embodiments of the present invention are not limited to applications involving conventional computer programs or programmable apparatus that run them. It is contemplated, for example, that embodiments of the presently claimed invention could include an optical computer, quantum computer, analog computer, or the like. A computer program may be loaded onto a computer to produce a particular machine that may perform any and all of the depicted functions. This particular machine provides a means for carrying out any and all of the depicted functions.
Any combination of one or more computer readable media may be utilized. The computer readable medium may be a non-transitory computer readable medium for storage. A computer readable storage medium may be electronic, magnetic, optical, electromagnetic, infrared, semiconductor, or any suitable combination of the foregoing. Further computer readable storage medium examples may include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM, Flash, MRAM, FeRAM, or phase change memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
It will be appreciated that computer program instructions may include computer executable code. A variety of languages for expressing computer program instructions may include without limitation C, C++, Java, JavaScript™, ActionScript™, assembly language, Lisp, Perl, Tcl, Python, Ruby, hardware description languages, database programming languages, functional programming languages, imperative programming languages, and so on. In embodiments, computer program instructions may be stored, compiled, or interpreted to run on a computer, a programmable data processing apparatus, a heterogeneous combination of processors or processor architectures, and so on. Without limitation, embodiments of the present invention may take the form of web-based computer software, which includes client/server software, software-as-a-service, peer-to-peer software, or the like.
In embodiments, a computer may enable execution of computer program instructions including multiple programs or threads. The multiple programs or threads may be processed more or less simultaneously to enhance utilization of the processor and to facilitate substantially simultaneous functions. By way of implementation, any and all methods, program codes, program instructions, and the like described herein may be implemented in one or more thread. Each thread may spawn other threads, which may themselves have priorities associated with them. In some embodiments, a computer may process these threads based on priority or other order.
Unless explicitly stated or otherwise clear from the context, the verbs “execute” and “process” may be used interchangeably to indicate execute, process, interpret, compile, assemble, link, load, or a combination of the foregoing. Therefore, embodiments that execute or process computer program instructions, computer-executable code, or the like may act upon the instructions or code in any and all of the ways described. Further, the method steps shown are intended to include any suitable method of causing one or more parties or entities to perform the steps. The parties performing a step, or portion of a step, need not be located within a particular geographic location or country boundary. For instance, if an entity located within the United States causes a method step, or portion thereof, to be performed outside of the United States then the method is considered to be performed in the United States by virtue of the entity causing the step to be performed.
While the invention has been disclosed in connection with preferred embodiments shown and described in detail, various modifications and improvements thereon will become apparent to those skilled in the art. Accordingly, the spirit and scope of the present invention is not to be limited by the foregoing examples, but is to be understood in the broadest sense allowable by law.
This application claims the benefit of U.S. provisional patent applications “Image Analysis Using Sub-Sectional Component Evaluation to Augment Classifier Usage” Ser. No. 62/273,896, filed Dec. 31, 2015, “Analytics for Live Streaming Based on Image Analysis within a Shared Digital Environment” Ser. No. 62/301,558, filed Feb. 29, 2016, and “Deep Convolutional Neural Network Analysis of Images for Mental States” Ser. No. 62/370,421, filed Aug. 3, 2016. This application is also a continuation-in-part of U.S. patent application “Mental State Event Signature Usage” Ser. No. 15/262,197, filed Sep. 12, 2016, which claims the benefit of U.S. provisional patent applications “Mental State Event Signature Usage” Ser. No. 62/217,872, filed Sep. 12, 2015, “Image Analysis In Support of Robotic Manipulation” Ser. No. 62/222,518, filed Sep. 23, 2015, “Analysis of Image Content with Associated Manipulation of Expression Presentation” Ser. No. 62/265,937, filed Dec. 10, 2015, “Image Analysis Using Sub-Sectional Component Evaluation To Augment Classifier Usage” Ser. No. 62/273,896, filed Dec. 31, 2015, “Analytics for Live Streaming Based on Image Analysis within a Shared Digital Environment” Ser. No. 62/301,558, filed Feb. 29, 2016, and “Deep Convolutional Neural Network Analysis of Images for Mental States” Ser. No. 62/370,421, filed Aug. 3, 2016. The patent application “Mental State Event Signature Usage” Ser. No. 15/262,197, filed Sep. 12, 2016, is also a continuation-in-part of U.S. patent application “Mental State Event Definition Generation” Ser. No. 14/796,419, filed Jul. 10, 2015, which claims the benefit of U.S. provisional patent applications “Mental State Event Definition Generation” Ser. No. 62/023,800, filed Jul. 11, 2014, “Facial Tracking with Classifiers” Ser. No. 62/047,508, filed Sep. 8, 2014, “Semiconductor Based Mental State Analysis” Ser. No. 62/082,579, filed Nov. 20, 2014, and “Viewership Analysis Based On Facial Evaluation” Ser. No. 62/128,974, filed Mar. 5, 2015. The patent application “Mental State Event Definition Generation” Ser. No. 14/796,419, filed Jul. 10, 2015 is also a continuation-in-part of U.S. patent application “Mental State Analysis Using Web Services” Ser. No. 13/153,745, filed Jun. 6, 2011, which claims the benefit of U.S. provisional patent applications “Mental State Analysis Through Web Based Indexing” Ser. No. 61/352,166, filed Jun. 7, 2010, “Measuring Affective Data for Web-Enabled Applications” Ser. No. 61/388,002, filed Sep. 30, 2010, “Sharing Affect Across a Social Network” Ser. No. 61/414,451, filed Nov. 17, 2010, “Using Affect Within a Gaming Context” Ser. No. 61/439,913, filed Feb. 6, 2011, “Recommendation and Visualization of Affect Responses to Videos” Ser. No. 61/447,089, filed Feb. 27, 2011, “Video Ranking Based on Affect” Ser. No. 61/447,464, filed Feb. 28, 2011, and “Baseline Face Analysis” Ser. No. 61/467,209, filed Mar. 24, 2011. The patent application “Mental State Event Definition Generation” Ser. No. 14/796,419, filed Jul. 10, 2015 is also a continuation-in-part of U.S. patent application “Mental State Analysis Using an Application Programming Interface” Ser. No. 14/460,915, Aug. 15, 2014, which claims the benefit of U.S. provisional patent applications “Application Programming Interface for Mental State Analysis” Ser. No. 61/867,007, filed Aug. 16, 2013, “Mental State Analysis Using an Application Programming Interface” Ser. No. 61/924,252, filed Jan. 7, 2014, “Heart Rate Variability Evaluation for Mental State Analysis” Ser. No. 61/916,190, filed Dec. 14, 2013, “Mental State Analysis for Norm Generation” Ser. No. 61/927,481, filed Jan. 15, 2014, “Expression Analysis in Response to Mental State Express Request” Ser. No. 61/953,878, filed Mar. 16, 2014, “Background Analysis of Mental State Expressions” Ser. No. 61/972,314, filed Mar. 30, 2014, and “Mental State Event Definition Generation” Ser. No. 62/023,800, filed Jul. 11, 2014. The patent application “Mental State Analysis Using an Application Programming Interface” Ser. No. 14/460,915, Aug. 15, 2014 is also a continuation-in-part of U.S. patent application “Mental State Analysis Using Web Services” Ser. No. 13/153,745, filed Jun. 6, 2011, which claims the benefit of U.S. provisional patent applications “Mental State Analysis Through Web Based Indexing” Ser. No. 61/352,166, filed Jun. 7, 2010, “Measuring Affective Data for Web-Enabled Applications” Ser. No. 61/388,002, filed Sep. 30, 2010, “Sharing Affect Across a Social Network” Ser. No. 61/414,451, filed Nov. 17, 2010, “Using Affect Within a Gaming Context” Ser. No. 61/439,913, filed Feb. 6, 2011, “Recommendation and Visualization of Affect Responses to Videos” Ser. No. 61/447,089, filed Feb. 27, 2011, “Video Ranking Based on Affect” Ser. No. 61/447,464, filed Feb. 28, 2011, and “Baseline Face Analysis” Ser. No. 61/467,209, filed Mar. 24, 2011. This application is also a continuation-in-part of U.S. patent application “Image Analysis for Attendance Query Evaluation” Ser. No. 15/061,385, filed Mar. 4, 2016 which claims the benefit of U.S. provisional patent applications “Viewership Analysis Based on Facial Evaluation” Ser. No. 62/128,974, filed Mar. 5, 2015, “Mental State Event Signature Usage” Ser. No. 62/217,872, filed Sep. 12, 2015, “Image Analysis In Support of Robotic Manipulation” Ser. No. 62/222,518, filed Sep. 23, 2015, “Analysis of Image Content with Associated Manipulation of Expression Presentation” Ser. No. 62/265,937, filed Dec. 10, 2015, “Image Analysis Using Sub-Sectional Component Evaluation To Augment Classifier Usage” Ser. No. 62/273,896, filed Dec. 31, 2015, and “Analytics for Live Streaming Based on Image Analysis within a Shared Digital Environment” Ser. No. 62/301,558, filed Feb. 29, 2016. The application “Image Analysis for Attendance Query Evaluation” Ser. No. 15/061,385, filed Mar. 4, 2016 is also a continuation-in-part of U.S. patent application “Facial Tracking with Classifiers” Ser. No. 14/848,222, filed Sep. 8, 2015 which claims the benefit of U.S. provisional patent applications “Facial Tracking with Classifiers” Ser. No. 62/047,508, filed Sep. 8, 2014, “Semiconductor Based Mental State Analysis” Ser. No. 62/082,579, filed Nov. 20, 2014, and “Viewership Analysis Based On Facial Evaluation” Ser. No. 62/128,974, filed Mar. 5, 2015. The patent application “Facial Tracking with Classifiers” Ser. No. 14/848,222, filed Sep. 8, 2015 is also a continuation-in-part of U.S. patent application “Mental State Analysis Using Web Services” Ser. No. 13/153,745, filed Jun. 6, 2011, which claims the benefit of U.S. provisional patent applications “Mental State Analysis Through Web Based Indexing” Ser. No. 61/352,166, filed Jun. 7, 2010, “Measuring Affective Data for Web-Enabled Applications” Ser. No. 61/388,002, filed Sep. 30, 2010, “Sharing Affect Across a Social Network” Ser. No. 61/414,451, filed Nov. 17, 2010, “Using Affect Within a Gaming Context” Ser. No. 61/439,913, filed Feb. 6, 2011, “Recommendation and Visualization of Affect Responses to Videos” Ser. No. 61/447,089, filed Feb. 27, 2011, “Video Ranking Based on Affect” Ser. No. 61/447,464, filed Feb. 28, 2011, and “Baseline Face Analysis” Ser. No. 61/467,209, filed Mar. 24, 2011. The patent application “Facial Tracking with Classifiers” Ser. No. 14/848,222, filed Sep. 8, 2015 is also a continuation-in-part of U.S. patent application “Mental State Analysis Using an Application Programming Interface” Ser. No. 14/460,915, Aug. 15, 2014, which claims the benefit of U.S. provisional patent applications “Application Programming Interface for Mental State Analysis” Ser. No. 61/867,007, filed Aug. 16, 2013, “Mental State Analysis Using an Application Programming Interface” Ser. No. 61/924,252, filed Jan. 7, 2014, “Heart Rate Variability Evaluation for Mental State Analysis” Ser. No. 61/916,190, filed Dec. 14, 2013, “Mental State Analysis for Norm Generation” Ser. No. 61/927,481, filed Jan. 15, 2014, “Expression Analysis in Response to Mental State Express Request” Ser. No. 61/953,878, filed Mar. 16, 2014, “Background Analysis of Mental State Expressions” Ser. No. 61/972,314, filed Mar. 30, 2014, and “Mental State Event Definition Generation” Ser. No. 62/023,800, filed Jul. 11, 2014. The application “Mental State Analysis Using an Application Programming Interface” Ser. No. 14/460,915, Aug. 15, 2014 is also a continuation-in-part of U.S. patent application “Mental State Analysis Using Web Services” Ser. No. 13/153,745, filed Jun. 6, 2011, which claims the benefit of U.S. provisional patent applications “Mental State Analysis Through Web Based Indexing” Ser. No. 61/352,166, filed Jun. 7, 2010, “Measuring Affective Data for Web-Enabled Applications” Ser. No. 61/388,002, filed Sep. 30, 2010, “Sharing Affect Across a Social Network” Ser. No. 61/414,451, filed Nov. 17, 2010, “Using Affect Within a Gaming Context” Ser. No. 61/439,913, filed Feb. 6, 2011, “Recommendation and Visualization of Affect Responses to Videos” Ser. No. 61/447,089, filed Feb. 27, 2011, “Video Ranking Based on Affect” Ser. No. 61/447,464, filed Feb. 28, 2011, and “Baseline Face Analysis” Ser. No. 61/467,209, filed Mar. 24, 2011. The application “Image Analysis for Attendance Query Evaluation” Ser. No. 15/061,385, filed Mar. 4, 2016 is also a continuation-in-part of U.S. patent application “Measuring Affective Data for Web-Enabled Applications” Ser. No. 13/249,317, filed Sep. 30, 2011 which claims the benefit of U.S. provisional patent applications “Measuring Affective Data for Web-Enabled Applications” Ser. No. 61/388,002, filed Sep. 30, 2010, “Sharing Affect Data Across a Social Network” Ser. No. 61/414,451, filed Nov. 17, 2010, “Using Affect Within a Gaming Context” Ser. No. 61/439,913, filed Feb. 6, 2011, “Recommendation and Visualization of Affect Responses to Videos” Ser. No. 61/447,089, filed Feb. 27, 2011, “Video Ranking Based on Affect” Ser. No. 61/447,464, filed Feb. 28, 2011, and “Baseline Face Analysis” Ser. No. 61/467,209, filed Mar. 24, 2011. Each of the foregoing applications is hereby incorporated by reference in its entirety.
Number | Date | Country | |
---|---|---|---|
62273896 | Dec 2015 | US | |
62301558 | Feb 2016 | US | |
62370421 | Aug 2016 | US | |
62217872 | Sep 2015 | US | |
62222518 | Sep 2015 | US | |
62265937 | Dec 2015 | US | |
62273896 | Dec 2015 | US | |
62301558 | Feb 2016 | US | |
62370421 | Aug 2016 | US | |
62023800 | Jul 2014 | US | |
62047508 | Sep 2014 | US | |
62082579 | Nov 2014 | US | |
62128974 | Mar 2015 | US | |
61352166 | Jun 2010 | US | |
61388002 | Sep 2010 | US | |
61414451 | Nov 2010 | US | |
61439913 | Feb 2011 | US | |
61447089 | Feb 2011 | US | |
61447464 | Feb 2011 | US | |
61467209 | Mar 2011 | US | |
61867007 | Aug 2013 | US | |
61924252 | Jan 2014 | US | |
61916190 | Dec 2013 | US | |
61927481 | Jan 2014 | US | |
61953878 | Mar 2014 | US | |
61972314 | Mar 2014 | US | |
62023800 | Jul 2014 | US | |
61352166 | Jun 2010 | US | |
61388002 | Sep 2010 | US | |
61414451 | Nov 2010 | US | |
61439913 | Feb 2011 | US | |
61447089 | Feb 2011 | US | |
61447464 | Feb 2011 | US | |
61467209 | Mar 2011 | US | |
62128974 | Mar 2015 | US | |
62217872 | Sep 2015 | US | |
62222518 | Sep 2015 | US | |
62265937 | Dec 2015 | US | |
62273896 | Dec 2015 | US | |
62301558 | Feb 2016 | US | |
62047508 | Sep 2014 | US | |
62082579 | Nov 2014 | US | |
62128974 | Mar 2015 | US | |
61352166 | Jun 2010 | US | |
61388002 | Sep 2010 | US | |
61414451 | Nov 2010 | US | |
61439913 | Feb 2011 | US | |
61447089 | Feb 2011 | US | |
61447464 | Feb 2011 | US | |
61467209 | Mar 2011 | US | |
61867007 | Aug 2013 | US | |
61924252 | Jan 2014 | US | |
61916190 | Dec 2013 | US | |
61927481 | Jan 2014 | US | |
61953878 | Mar 2014 | US | |
61972314 | Mar 2014 | US | |
62023800 | Jul 2014 | US | |
61352166 | Jun 2010 | US | |
61388002 | Sep 2010 | US | |
61414451 | Nov 2010 | US | |
61439913 | Feb 2011 | US | |
61447089 | Feb 2011 | US | |
61447464 | Feb 2011 | US | |
61467209 | Mar 2011 | US | |
61388002 | Sep 2010 | US | |
61414451 | Nov 2010 | US | |
61439913 | Feb 2011 | US | |
61447089 | Feb 2011 | US | |
61447464 | Feb 2011 | US | |
61467209 | Mar 2011 | US |
Number | Date | Country | |
---|---|---|---|
Parent | 15262197 | Sep 2016 | US |
Child | 15393458 | US | |
Parent | 14796419 | Jul 2015 | US |
Child | 15262197 | US | |
Parent | 13153745 | Jun 2011 | US |
Child | 14796419 | US | |
Parent | 14460915 | Aug 2014 | US |
Child | 14796419 | US | |
Parent | 13153745 | Jun 2011 | US |
Child | 14460915 | US | |
Parent | 15061385 | Mar 2016 | US |
Child | 13153745 | US | |
Parent | 14848222 | Sep 2015 | US |
Child | 15061385 | US | |
Parent | 13153745 | Jun 2011 | US |
Child | 14848222 | US | |
Parent | 14460915 | Aug 2014 | US |
Child | 14848222 | US | |
Parent | 13153745 | Jun 2011 | US |
Child | 14460915 | US | |
Parent | 13249317 | Sep 2011 | US |
Child | 15061385 | US |