This application is related to patent application: “A METHOD AND SYSTEM FOR PERFORMING WHITE BALANCING OPERATIONS ON CAPTURED IMAGES,” concurrently filed with this application, which is herein incorporated by reference in its entirety.
Embodiments of the present invention are generally related to the field of devices capable of digitally capturing images.
Modern digital cameras offer a feature known as “automatic white balancing” which is a process used to adjust the color balance of an image captured by the camera under varying illumination conditions. Conventional white balancing algorithms attempt to attain the same high level of color constancy associated with most human color perception systems by removing unrealistic color casts captured by the camera when acquiring the image. In doing so, these algorithms generally first determine a scene illuminant used to illuminate the captured image. Once determined, the scene illuminant's impact on the captured scene may be neutralized to obtain a more color balanced, aesthetically pleasing image.
Often, in determining the illuminant, conventional white balancing algorithms require a calibration process in which the user must first capture a reference image so that future images captured by the camera may be white balanced. However, these algorithms are often not equipped to handle situations in which the camera may not be able to perform these calibrations. For example, the camera may not have access to scenes with these required reference points and, thus, may produce unappealing resultant images. As a result, the user may have to manually manipulate each image of interest in order to attain a more color balanced image. This process may prove to be especially cumbersome if the user wishes to white balance several images at a time and may lead to user frustration.
Accordingly, a need exists to address the inefficiencies discussed above. Embodiments of the present invention are operable to generate a set of weights derived through crowdsourcing procedures for use in performing automatic white balancing operations on images captured by a digital camera system. Embodiments of the present invention are operable to generate a set of images which are illuminated with known and different illuminants. Using crowdsourcing procedures, embodiments of the present invention gather user feedback concerning which images from the set of images adjusted by the known illuminants are considered to be the most aesthetically pleasing. Images selected by the users are then stored within a database of selected images. Using a learning engine, embodiments of the present invention may then produce a set of weights based on the user selected images. Weights generated by embodiments of the present invention may be explicitly encoded information used by digital camera systems in selecting a scene illuminant during the performance of automatic white balancing operations.
More specifically, in one embodiment, the present invention is implemented as a method of generating weights for use in a digital camera system. The method includes generating an image set comprising a plurality of pairs of images in which images of each pair are illuminated with known and different illuminants. The method also includes using crowdsourcing procedures, gathering user input from a plurality of users concerning a most pleasing image of each pair of images displayed to the plurality of users and storing the user input into a database of selected images. In one embodiment, the method of gathering further includes capturing a result of a user vote for the most pleasing image of each pair of images. In one embodiment, the method of gathering further includes screening the plurality of users for color selection competency. In one embodiment, the method of gathering further includes displaying the plurality of pairs of images to the users in which the displaying process includes randomizing a display ordering of the plurality of pairs of images displayed to the plurality of users.
Furthermore, the method includes generating a set of weights for use in the camera system for selecting a proper illuminant for a newly captured image using a learning engine operable to receive input from the database. In one embodiment, the learning engine uses a support vector machine procedure. In one embodiment, the method of generating a set of weights further includes generating an updated set of weights in response to new user input. In one embodiment, the method of generating a set of weights further comprises receiving input from the database in a random order.
In one embodiment, the present invention is implemented as a system for generating weights for use in a camera system. The system includes a generation module residing on a server system, in which the generation module is operable to generate an image set comprising a plurality of pairs of images in which images of each pair are illuminated with known and different illuminants. The system also includes a crowdsourcing module residing on the server system, in which the crowdsourcing module is operable to gather user input from a plurality of users concerning a most pleasing image of each pair of images displayed to the plurality of users using crowdsourcing procedures and storing the user input into a database of selected images.
In one embodiment, the crowdsourcing module is further operable to capture votes from the plurality of users to determine the most pleasing image of each pair of images. In one embodiment, the crowdsourcing module is further operable to screen the plurality of users for color selection competency. In one embodiment, the crowdsourcing module is further operable to randomize a display ordering of the plurality of pairs of images prior to being displayed to the plurality of users.
Furthermore, the system also includes a learning module residing on the server system, in which the learning module is operable to process the database and responsive thereto produce therefrom a set of weights for use in the camera system for selecting a proper illuminant for a captured image. In one embodiment, the learning module uses a support vector machine procedure. In one embodiment, the learning module is further operable to generate an updated set of weights in response to updated user input. In one embodiment, the learning module is operable to receive input from the database in a random order.
In another embodiment, the present invention is implemented as a method of generating weights for use in a camera system. The method includes receiving a classified image set comprising a plurality of pairs of images in which images of each pair are illuminated with known and different illuminants. The method also includes using a server system, gathering user input using crowdsourcing procedures from a plurality of users concerning a most pleasing image of each pair of images displayed to the plurality of users and storing the user input into a database of selected images.
In one embodiment, the method of gathering further comprises receiving input from user votes concerning the most pleasing image of each pair of images. In one embodiment, the method of gathering further comprises screening the plurality of users for color selection competency. In one embodiment, the method of gathering further comprises displaying the plurality of pairs of images to the users in which the displaying process comprises randomizing a display ordering of the plurality of pairs of images prior to being displayed to the plurality of users.
Furthermore, the method also includes generating a set of weights for use in the camera system for selecting a proper illuminant for a newly captured image using a learning engine operable to receive input from the database. In one embodiment, the learning engine uses a support vector machine procedure. In one embodiment, the method of generating a set of weights further comprises generating an updated set of weights in response to updated user input. In one embodiment, the method of generating a set of weights further comprises receiving input from the database in a random order.
The accompanying drawings, which are incorporated in and form a part of this specification and in which like numerals depict like elements, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the disclosure.
Reference will now be made in detail to the various embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings. While described in conjunction with these embodiments, it will be understood that they are not intended to limit the disclosure to these embodiments. On the contrary, the disclosure is intended to cover alternatives, modifications and equivalents, which may be included within the spirit and scope of the disclosure as defined by the appended claims. Furthermore, in the following detailed description of the present disclosure, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be understood that the present disclosure may be practiced without these specific details. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to unnecessarily obscure aspects of the present disclosure.
Portions of the detailed description that follow are presented and discussed in terms of a process. Although operations and sequencing thereof are disclosed in a figure herein (e.g.,
As used in this application the terms controller, module, system, and the like are intended to refer to a computer-related entity, specifically, either hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a module can be, but is not limited to being, a process running on a processor, an integrated circuit, an object, an executable, a thread of execution, a program, and or a computer. By way of illustration, both an application running on a computing device and the computing device can be a module. One or more modules can reside within a process and/or thread of execution, and a component can be localized on one computer and/or distributed between two or more computers. In addition, these modules can be executed from various computer readable media having various data structures stored thereon.
As presented in
According to one embodiment, raw image 309 may be an image used by server system 100 for purposes of generating an image set for use as training data to train illuminant learning module 162. These images may be used by illuminant learning module 162 for purposes of mapping potential scene illuminant sources to scenes captured by a camera device. These images may be captured using any digital device capable of capturing an image such as a digital camera, mobile phone, tablet or the like.
With reference to
The adjustment process may involve manipulating the color channel values (e.g., RGB values) of the pixels of a trial image generated using predetermined color intensity values associated with a classified illuminant source. For example, image generation module 266 may be configured to use values associated with sunlight to adjust the color channel values of the pixels comprising trial image A1 (“adjusted trial image A1” 311). Similarly, image generation module 266 may use values associated with florescent light to adjust the color channel values of pixels comprising trial image A2 (“adjusted trial image A2” 312).
With further reference to
In one embodiment, crowdsourcing application 325 may be an application (e.g., web based) that engages users (via interfacing module 325-3) to participate in surveys to determine which adjusted image the user believes to be the most aesthetically pleasing. User participation may be encouraged through monetary remuneration (e.g., micropayments) or other forms of incentives. Users may interact with crowdsourcing application 325 using a web browser installed locally on the user's personal computer, laptop, mobile device or the like. In one embodiment, crowdsourcing application 325 may be an application that engages user participation through texting technology (e.g., MMS technology) in which user feedback is collected in response to picture messages sent to the user.
Furthermore, to maintain the integrity of the data collected from the group of users, crowdsourcing application 325 may apply user preconditioning techniques using screening module 325-2. Screening module 325-2 may perform various tests on users prior to their participation in the survey. For instance, color blindness tests may be used to determine the participating user's color detection competency in distinguishing adjusted images displayed before the user. Also, user veracity tests may be used to determine a user's truthfulness with regards to answering questions posed to the user. Furthermore, equipment functionality tests may be used to determine whether the crowdsourcing application can interact with the user and detect selections made by the user (e.g., display screen functionality tests).
As illustrated in the embodiment depicted in
In one embodiment, the user may express feedback through placement of a mark next to the adjusted image (e.g., checkmark placed within a radio field). According to one embodiment, users using touchscreen display screens may touch the image displayed to express a preference towards a particular adjusted trial image. In another embodiment, the user may provide feedback by ranking the adjusted trial images displayed. For instance, images rated as the most aesthetically pleasing may receive a higher rank than images deemed less aesthetically pleasing.
With further reference to
Embodiments of the present invention may also include the functionality to use machine learning to explicitly encode scene illuminants determined through crowdsourcing procedures. According to one embodiment, vector data 111 may be fed into illuminant learning module 162 which may use the vector data received to generate a weight function that produces weight values (e.g., crowdsourced weight data 161) for use in white balancing newly captured images. In this manner, crowdsourced weight data 161 may be explicitly encoded scene information used by camera devices for selecting a proper illuminant when performing white balancing operations. For instance, crowdsourced weight data 161 may be explicitly encoded information used by a camera device to classify bright scenes, where blue is a predominant scene color, as an “outside” scene in which sunlight is determined to be the scene illuminant. When generating crowdsourced weight data 161, illuminant learning module 162 may access raw image data associated with vector data from image database 205. Illuminant learning module 162 may use well-known machine learning algorithms (e.g., support vector machines, neural networks, decision trees) when computing crowdsourced weight data 161.
Furthermore, embodiments of the present invention may be configured to use scenes and processes constructed for purposes of maximizing the learning potential of illuminant learning module 162. As such, embodiments of the present invention may utilize a more sophisticated knowledge base when encoding scene illuminant determinations as a priori data (e.g., crowdsourced weight data 161) loaded onto a camera device. For instance, in one embodiment, vector data 111 may be fed to illuminant learning module 162 in a random order to maximize the ability of illuminant learning module 162 to learn the content of the raw images and, thus, minimize any learning bias. In one embodiment, the technique of randomization may include randomizing the orientation of the image associated with vector data 111 as it is being fed into illuminant learning module 162. In another embodiment, the raw image data itself may also be randomized in a manner such that color combinations included within the image data may be de-correlated prior to being fed into illuminant learning module 162. Furthermore, crowdsourced weight data 161 may be loaded and stored within a camera device in-factory during production of the camera device. Also, in response to receiving new image data post-production, illuminant learning module 162 may also be able to generate an updated set of crowdsourced weight data 161 that may be downloadable from server system 100 for use in a camera device during a synchronization process between the server system and the camera device. These synchronizations may take place during predetermined intervals or upon the user's request for synchronization.
At step 406, a fixed number of raw images and known illuminant sources are determined by the evaluator.
At step 407, each raw image is corrected by at least 2 of the known illuminant sources in a predetermined manner by the evaluator to produce a plurality of adjusted trial images.
At step 408, each user is presented with a precondition test to determine whether both the user and the user's equipment satisfy conditions enabling the user to participate in the image selection process.
At step 409, each illuminated image is broadcasted over a communication network to users in an unbiased, random order using a crowdsourcing application.
At step 410, a determination is made as to whether both the user and the equipment used by the user satisfy preconditions enabling the user to select a corrected image. If both the user and the equipment used by the user do not satisfy the preconditions, then the user is prevented from participating in the survey, as detailed in step 411. If both the user and the equipment used by the user do satisfy the preconditions, then each user selects an adjusted trial image that the user determines as the most aesthetically pleasing from a group of adjusted trial images displayed before the user, as detailed in step 412.
At step 411, both the user and the equipment used by the user have been determined to not satisfy the preconditions and, therefore, the user is prevented from participating in the survey.
At step 412, both the user and the equipment used by the user have been determined to satisfy the preconditions and, therefore, each user selects an adjusted trial image that the user determines as the most aesthetically pleasing from a group of adjusted trial images displayed before the user.
At step 413, each user's selection is recorded and communicated to a server over the communication network. Both the illuminant used to manipulate the adjusted trial image receiving the most number of votes as well as the image data associated with the raw image are stored in a database resident on the server system.
At step 414, the data stored in the database at step 413 is fed into the illuminant source learning module for further computation.
At step 415, using the inputs received, the illuminant source learning module computes an array of crowdsourced weight data that may be stored within memory resident on a camera system.
With reference to
Camera system 200 may capture illuminated scene 240 through lens 225, which may be coupled to image sensor 245. According to one embodiment, image sensor 245 may comprise an array of pixel sensors that are each capable of acquiring color channel data from illuminated scene 240. Each pixel sensor of image sensor 245 may be configured to capture a specific color intensity that is emitted from the color space of illuminated scene 240 (e.g., RGB values). Furthermore, the color channel data captured from illuminated scene 240 may be stored in current image memory buffer 207 for further processing by components of camera system 200.
Illuminant source estimation module 166 may determine a likely illuminant using the sampled image data stored within current image memory buffer 207 and the crowdsourced weight data 161 stored within crowdsourced data memory buffer 261. As discussed supra, the loading of crowdsourced weight data 161 on to camera system 200 may occur in-factory during the manufacture of camera system 200. Camera system 200 may also be operable to receive an updated set of crowdsourced weights through periodic synchronizations between camera system 200 and server system 100 over a communication network. In one embodiment, an updated set of weights may be generated (e.g., through illuminant learning module 162 of server system 100) in response to newly captured images taken by camera system 200. For instance, camera system 200 may accumulate a set of images which may then be subsequently uploaded to server system 100 during a synchronization period. Once uploaded, illuminant learning module 162 may learn the content of these newly captured images using the learning algorithms described herein. Upon completion of the learning phase, illuminant learning module 162 may proceed to compute an updated set of weights. This updated set of weights may then be available for download during the next synchronization period between camera system 200 and server system 100.
Furthermore, in a similar manner, adjustments made to the newly captured images taken by camera system 200 may also be used in generating an updated set of weights. For instance, using either camera system 200 or photo editing software independent of camera system 200, a user may adjust a set of images which may then be subsequently uploaded to server system 100 during a synchronization period. Once uploaded, illuminant learning module 162 may then learn the content of the user adjusted set of images. Upon completion of the learning phase, illuminant learning module 162 may then proceed to compute an updated set of weights, which may be available for download during the next synchronization period between camera system 200 and server system 100.
According to one embodiment, illuminant source estimation module 166 may determine a likely illuminant source based on a summation of the sampled image data and the crowdsourced weight data 161. This summation process may be expressed by the following formula:
Σn=1m WnIn
in which illuminant source estimation module 166 may sum each weight W from crowdsourced weight data 161 in combination with the sampled image data I (e.g., pixel coordinate values) of the image capturing illuminated scene 240. Furthermore, the number of weights m may be determined by illuminant learning module 162.
Using the results of the summation process, illuminant source estimation module 166 may then proceed to compare the weighted sampled data of the image capturing illuminated scene 240 to a corresponding set of values associated with likely illuminant sources stored within illuminant value data structure 166-1. According to one embodiment of the present invention, the weighted sampled data of the image capturing illuminated scene 240 used for the comparison may consist of a group of pixel coordinates, with each pixel coordinate having a set of RGB values. The RGB values of this group may be compared to the RGB values of a corresponding group of pixel coordinates stored within illuminant value data structure 166-1 belonging to a particular illuminant source. According to one embodiment, if the RGB values of the weighted sampled data are within a RGB value threshold of a particular illuminant, illuminant source estimation module 166 may determine that illuminant to be the likely illuminant. Embodiments of the present invention are not limited by the manner in which these groups of pixel coordinates are selected nor by the method of calculating the RGB values (e.g., averaging the RGB values) for the selected group. Furthermore, pixel coordinate values of the likely illuminant sources stored within illuminant value data structure 166-1 may be predetermined.
With further reference to
Using the confidence score that is calculated, white balance computation module 168 may then compare the score to a predetermined confidence score threshold. According to one embodiment, based on this comparison, a determination may be made as to which illuminant source estimation algorithm camera system 200 will use for performing automatic white balancing operations on the image capturing illuminated scene 240. Color correction module 168-2 may adjust the RGB values of the image capturing illuminated scene 240 based on the results of the comparison.
For instance, if the confidence score is within the predetermined confidence score threshold, white balance computation module 168 may use the illuminant source determined by illuminant source estimation module 166 using crowdsourced weight data 161. Accordingly, color correction module 168-2 may read the RGB values associated with the illuminant source determined when adjusting the RGB values of the image capturing illuminated scene 240. However, if the confidence score is below the predetermined confidence score threshold, white balance computation module 168 may be configured to use default automatic white balancing operations local to camera system 200. In this instance, illuminant source estimation module 166 may use default illuminant source estimation algorithm 168-1 when determining a likely illuminant. Accordingly, color correction module 168-2 may then proceed to read the RGB values associated with the illuminant source determined using this algorithm when adjusting the RGB values of the image capturing illuminated scene 240.
At step 701, crowdsourced weight data is loaded on to the camera system.
At step 702, the camera system captures an image which is then sampled for further processing by components of the camera system.
At step 703, image data from the sampled image is delivered to the illuminant source estimation module which also accesses the crowdsourced weighted data stored in the crowdsourced weight data memory buffer in the camera to perform summation operations to determine the likely illuminant source.
At step 704, a confidence score is calculated for the determination made at step 703 in order to determine which illuminant source estimation algorithm the white balance computation module will use when performing white balancing operations on the image captured at step 702.
At step 705, a determination is made as to whether the confidence score calculated at step 704 is within a predetermined threshold. If the score is not within the predetermined threshold, then the white balance computation module will use the camera system's default illuminant source estimation algorithm to determine the likely illuminant source, as detailed in step 706. If the score is within the predetermined threshold, then the white balance computation module will use the likely illuminant source determined at step 703, as detailed in step 707.
At step 706, the score is determined to not be within the predetermined threshold and, therefore, the white balancing computation module will use the camera system's default illuminant source estimation algorithm to determine the likely illuminant source.
At step 707, the score is determined to be within the predetermined threshold and, therefore, the white balancing computation module will use the likely illuminant source determined at step 703.
At step 708, using the determined likely illuminant source, the white balancing computation module performs white balancing operations on the image captured at step 702 and outputs a white balance resultant image.
At step 709, the camera system receives updated crowdsourced weight data from a remote server system.
While the foregoing disclosure sets forth various embodiments using specific block diagrams, flowcharts, and examples, each block diagram component, flowchart step, operation, and/or component described and/or illustrated herein may be implemented, individually and/or collectively, using a wide range of hardware, software, or firmware (or any combination thereof) configurations. In addition, any disclosure of components contained within other components should be considered as examples because many other architectures can be implemented to achieve the same functionality.
The process parameters and sequence of steps described and/or illustrated herein are given by way of example only. For example, while the steps illustrated and/or described herein may be shown or discussed in a particular order, these steps do not necessarily need to be performed in the order illustrated or discussed. The various example methods described and/or illustrated herein may also omit one or more of the steps described or illustrated herein or include additional steps in addition to those disclosed.
While various embodiments have been described and/or illustrated herein in the context of fully functional computing systems, one or more of these example embodiments may be distributed as a program product in a variety of forms, regardless of the particular type of computer-readable media used to actually carry out the distribution. The embodiments disclosed herein may also be implemented using software modules that perform certain tasks. These software modules may include script, batch, or other executable files that may be stored on a computer-readable storage medium or in a computing system. These software modules may configure a computing system to perform one or more of the example embodiments disclosed herein. One or more of the software modules disclosed herein may be implemented in a cloud computing environment. Cloud computing environments may provide various services and applications via the Internet. These cloud-based services (e.g., software as a service, platform as a service, infrastructure as a service) may be accessible through a Web browser or other remote interface. Various functions described herein may be provided through a remote desktop environment or any other cloud-based computing environment.
The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Many modifications and variations are possible in view of the above disclosure. The embodiments were chosen and described in order to best explain the principles of the invention and its practical applications, to thereby enable others skilled in the art to best utilize the invention and various embodiments with various modifications as may be suited to the particular use contemplated.
Embodiments according to the invention are thus described. While the present disclosure has been described in particular embodiments, it should be appreciated that the invention should not be construed as limited by such embodiments, but rather construed according to the below claims.
Number | Name | Date | Kind |
---|---|---|---|
3904818 | Kovac | Sep 1975 | A |
4253120 | Levine | Feb 1981 | A |
4646251 | Hayes et al. | Feb 1987 | A |
4739495 | Levine | Apr 1988 | A |
4771470 | Geiser et al. | Sep 1988 | A |
4920428 | Lin et al. | Apr 1990 | A |
4987496 | Greivenkamp, Jr. | Jan 1991 | A |
5175430 | Enke et al. | Dec 1992 | A |
5261029 | Abi-Ezzi et al. | Nov 1993 | A |
5305994 | Matsui et al. | Apr 1994 | A |
5387983 | Sugiura et al. | Feb 1995 | A |
5475430 | Hamada et al. | Dec 1995 | A |
5513016 | Inoue | Apr 1996 | A |
5608824 | Shimizu et al. | Mar 1997 | A |
5652621 | Adams, Jr. et al. | Jul 1997 | A |
5793433 | Kim et al. | Aug 1998 | A |
5878174 | Stewart et al. | Mar 1999 | A |
5903273 | Mochizuki et al. | May 1999 | A |
5905530 | Yokota et al. | May 1999 | A |
5995109 | Goel et al. | Nov 1999 | A |
6016474 | Kim et al. | Jan 2000 | A |
6078331 | Pulli et al. | Jun 2000 | A |
6111988 | Horowitz et al. | Aug 2000 | A |
6118547 | Tanioka | Sep 2000 | A |
6141740 | Mahalingaiah et al. | Oct 2000 | A |
6151457 | Kawamoto | Nov 2000 | A |
6175430 | Ito | Jan 2001 | B1 |
6252611 | Kondo | Jun 2001 | B1 |
6256038 | Krishnamurthy | Jul 2001 | B1 |
6281931 | Tsao et al. | Aug 2001 | B1 |
6289103 | Sako et al. | Sep 2001 | B1 |
6314493 | Luick | Nov 2001 | B1 |
6319682 | Hochman | Nov 2001 | B1 |
6323934 | Enomoto | Nov 2001 | B1 |
6392216 | Peng-Tan | May 2002 | B1 |
6396397 | Bos et al. | May 2002 | B1 |
6438664 | McGrath et al. | Aug 2002 | B1 |
6486971 | Kawamoto | Nov 2002 | B1 |
6584202 | Montag et al. | Jun 2003 | B1 |
6683643 | Takayama et al. | Jan 2004 | B1 |
6707452 | Veach | Mar 2004 | B1 |
6724423 | Sudo | Apr 2004 | B1 |
6724932 | Ito | Apr 2004 | B1 |
6737625 | Baharav et al. | May 2004 | B2 |
6760080 | Moddel et al. | Jul 2004 | B1 |
6785814 | Usami et al. | Aug 2004 | B1 |
6806452 | Bos et al. | Oct 2004 | B2 |
6839062 | Aronson et al. | Jan 2005 | B2 |
6856441 | Zhang et al. | Feb 2005 | B2 |
6891543 | Wyatt | May 2005 | B2 |
6900836 | Hamilton, Jr. | May 2005 | B2 |
6950099 | Stollnitz et al. | Sep 2005 | B2 |
7009639 | Une et al. | Mar 2006 | B1 |
7015909 | Morgan III et al. | Mar 2006 | B1 |
7023479 | Hiramatsu et al. | Apr 2006 | B2 |
7088388 | MacLean et al. | Aug 2006 | B2 |
7092018 | Watanabe | Aug 2006 | B1 |
7106368 | Daiku et al. | Sep 2006 | B2 |
7133041 | Kaufman et al. | Nov 2006 | B2 |
7133072 | Harada | Nov 2006 | B2 |
7221779 | Kawakami et al. | May 2007 | B2 |
7227586 | Finlayson et al. | Jun 2007 | B2 |
7245319 | Enomoto | Jul 2007 | B1 |
7305148 | Spampinato et al. | Dec 2007 | B2 |
7343040 | Chanas et al. | Mar 2008 | B2 |
7486844 | Chang et al. | Feb 2009 | B2 |
7502505 | Malvar et al. | Mar 2009 | B2 |
7580070 | Yanof et al. | Aug 2009 | B2 |
7587391 | Bostock | Sep 2009 | B1 |
7626612 | John et al. | Dec 2009 | B2 |
7627193 | Alon et al. | Dec 2009 | B2 |
7671910 | Lee | Mar 2010 | B2 |
7728880 | Hung et al. | Jun 2010 | B2 |
7750956 | Wloka | Jul 2010 | B2 |
7817187 | Silsby et al. | Oct 2010 | B2 |
7859568 | Shimano et al. | Dec 2010 | B2 |
7860382 | Grip | Dec 2010 | B2 |
8238695 | Davey et al. | Aug 2012 | B1 |
8698918 | Silverstein et al. | Apr 2014 | B2 |
9307213 | Pieper | Apr 2016 | B2 |
20010001234 | Addy et al. | May 2001 | A1 |
20010012113 | Yoshizawa et al. | Aug 2001 | A1 |
20010012127 | Fukuda et al. | Aug 2001 | A1 |
20010015821 | Namizuka et al. | Aug 2001 | A1 |
20010019429 | Oteki et al. | Sep 2001 | A1 |
20010021278 | Fukuda et al. | Sep 2001 | A1 |
20010033410 | Helsel et al. | Oct 2001 | A1 |
20010050778 | Fukuda et al. | Dec 2001 | A1 |
20010054126 | Fukuda et al. | Dec 2001 | A1 |
20020012131 | Oteki et al. | Jan 2002 | A1 |
20020015111 | Harada | Feb 2002 | A1 |
20020018244 | Namizuka et al. | Feb 2002 | A1 |
20020027670 | Takahashi et al. | Mar 2002 | A1 |
20020033887 | Hieda et al. | Mar 2002 | A1 |
20020041383 | Lewis, Jr. et al. | Apr 2002 | A1 |
20020044778 | Suzuki | Apr 2002 | A1 |
20020054374 | Inoue et al. | May 2002 | A1 |
20020063802 | Gullichsen et al. | May 2002 | A1 |
20020105579 | Levine et al. | Aug 2002 | A1 |
20020126210 | Shinohara et al. | Sep 2002 | A1 |
20020146136 | Carter, Jr. | Oct 2002 | A1 |
20020149683 | Post | Oct 2002 | A1 |
20020158971 | Daiku et al. | Oct 2002 | A1 |
20020167202 | Pfalzgraf | Nov 2002 | A1 |
20020167602 | Nguyen | Nov 2002 | A1 |
20020191694 | Ohyama et al. | Dec 2002 | A1 |
20020196470 | Kawamoto et al. | Dec 2002 | A1 |
20030035100 | Dimsdale et al. | Feb 2003 | A1 |
20030067461 | Fletcher et al. | Apr 2003 | A1 |
20030122825 | Kawamoto | Jul 2003 | A1 |
20030142222 | Hordley | Jul 2003 | A1 |
20030146975 | Joung et al. | Aug 2003 | A1 |
20030169353 | Keshet et al. | Sep 2003 | A1 |
20030169918 | Sogawa | Sep 2003 | A1 |
20030197701 | Teodosiadis et al. | Oct 2003 | A1 |
20030218672 | Zhang et al. | Nov 2003 | A1 |
20030222995 | Kaplinsky et al. | Dec 2003 | A1 |
20030223007 | Takane | Dec 2003 | A1 |
20040001061 | Stollnitz et al. | Jan 2004 | A1 |
20040001234 | Curry et al. | Jan 2004 | A1 |
20040032516 | Kakarala | Feb 2004 | A1 |
20040066970 | Matsugu | Apr 2004 | A1 |
20040100588 | Hartson et al. | May 2004 | A1 |
20040101313 | Akiyama | May 2004 | A1 |
20040109069 | Kaplinsky et al. | Jun 2004 | A1 |
20040189875 | Zhai et al. | Sep 2004 | A1 |
20040218071 | Chauville et al. | Nov 2004 | A1 |
20040247196 | Chanas et al. | Dec 2004 | A1 |
20050007378 | Grove | Jan 2005 | A1 |
20050007477 | Ahiska | Jan 2005 | A1 |
20050030395 | Hattori | Feb 2005 | A1 |
20050046704 | Kinoshita | Mar 2005 | A1 |
20050099418 | Cabral et al. | May 2005 | A1 |
20050175257 | Kuroki | Aug 2005 | A1 |
20050185058 | Sablak | Aug 2005 | A1 |
20050213128 | Imai et al. | Sep 2005 | A1 |
20050238225 | Jo et al. | Oct 2005 | A1 |
20050243181 | Castello et al. | Nov 2005 | A1 |
20050248671 | Schweng | Nov 2005 | A1 |
20050261849 | Kochi et al. | Nov 2005 | A1 |
20050286097 | Hung et al. | Dec 2005 | A1 |
20060050158 | Irie | Mar 2006 | A1 |
20060061658 | Faulkner et al. | Mar 2006 | A1 |
20060087509 | Ebert et al. | Apr 2006 | A1 |
20060103728 | Ishigami et al. | May 2006 | A1 |
20060119710 | Ben-Ezra et al. | Jun 2006 | A1 |
20060133697 | Uvarov et al. | Jun 2006 | A1 |
20060176375 | Hwang et al. | Aug 2006 | A1 |
20060197664 | Zhang et al. | Sep 2006 | A1 |
20060274171 | Wang | Dec 2006 | A1 |
20060290794 | Bergman et al. | Dec 2006 | A1 |
20060293089 | Herberger et al. | Dec 2006 | A1 |
20070091188 | Chen et al. | Apr 2007 | A1 |
20070147706 | Sasaki et al. | Jun 2007 | A1 |
20070171288 | Inoue et al. | Jul 2007 | A1 |
20070236770 | Doherty et al. | Oct 2007 | A1 |
20070247532 | Sasaki | Oct 2007 | A1 |
20080030587 | Helbing | Feb 2008 | A1 |
20080062164 | Bassi et al. | Mar 2008 | A1 |
20080231726 | John | Sep 2008 | A1 |
20090002517 | Yokomitsu et al. | Jan 2009 | A1 |
20090010539 | Guarnera et al. | Jan 2009 | A1 |
20090116750 | Lee et al. | May 2009 | A1 |
20090160957 | Deng et al. | Jun 2009 | A1 |
20090257677 | Cabral et al. | Oct 2009 | A1 |
20100048242 | Rhoads et al. | Feb 2010 | A1 |
20100214436 | Kim et al. | Aug 2010 | A1 |
20100266201 | Cabral et al. | Oct 2010 | A1 |
20110096190 | Silverstein et al. | Apr 2011 | A1 |
20110225566 | Muharsky | Sep 2011 | A1 |
20120127334 | Imai | May 2012 | A1 |
20130083216 | Jiang et al. | Apr 2013 | A1 |
20130212094 | Naguib et al. | Aug 2013 | A1 |
20130294680 | Harada | Nov 2013 | A1 |
20150002692 | Cabral et al. | Jan 2015 | A1 |
20150002693 | Cabral et al. | Jan 2015 | A1 |
20150131902 | Arnone | May 2015 | A1 |
Number | Date | Country |
---|---|---|
1275870 | Dec 2000 | CN |
0392565 | Oct 1990 | EP |
1449169 | May 2003 | EP |
1378790 | Jul 2004 | EP |
1447977 | Aug 2004 | EP |
1550980 | Jul 2005 | EP |
2045026 | Oct 1980 | GB |
2363018 | May 2001 | GB |
61187467 | Aug 1986 | JP |
62151978 | Jul 1987 | JP |
07015631 | Jan 1995 | JP |
8036640 | Feb 1996 | JP |
08079622 | Mar 1996 | JP |
2001052194 | Feb 2001 | JP |
2002207242 | Jul 2002 | JP |
2003085542 | Mar 2003 | JP |
2004221838 | Aug 2004 | JP |
2005094048 | Apr 2005 | JP |
2005182785 | Jul 2005 | JP |
2005520442 | Jul 2005 | JP |
2006025005 | Jan 2006 | JP |
2006086822 | Mar 2006 | JP |
2006094494 | Apr 2006 | JP |
2006121612 | May 2006 | JP |
2006134157 | May 2006 | JP |
2007019959 | Jan 2007 | JP |
2007148500 | Jun 2007 | JP |
2007233833 | Sep 2007 | JP |
2007282158 | Oct 2007 | JP |
2008085388 | Apr 2008 | JP |
2008277926 | Nov 2008 | JP |
2009021962 | Jan 2009 | JP |
1020040043156 | May 2004 | KR |
1020060068497 | Jun 2006 | KR |
1020070004202 | Jan 2007 | KR |
03043308 | May 2003 | WO |
2004063989 | Jul 2004 | WO |
2007056459 | May 2007 | WO |
2007093864 | Aug 2007 | WO |
Entry |
---|
J. Bolz, P. Schroder; “rapid evaluation of catmull-clark subdivision surfaces”; Web 3D '02, Feb. 2002. |
J. Stam; “Exact Evaluation of Catmull-clark subdivision surfaces at arbitrary parameter values”; Jul. 1998; Computer Graphics; vol. 32; pp. 395-404. |
Keith R. Slavin; Application as Filed entitled “Efficient Method for Reducing Noise and Blur in a Composite Still Image From a Rolling Shutter Camera”; Application No. 12069669; Filed Feb. 11, 2008. |
Ko et al., “Fast Digital Image Stabilizer Based on Gray-Coded Bit-Plane Matching”, IEEE Transactions on Consumer Electronics, vol. 45, No. 3, pp. 598-603, Aug. 1999. |
Ko, et al., “Digital Image Stabilizing Algorithms Basd on Bit-Plane Matching”, IEEE Transactions on Consumer Electronics, vol. 44, No. 3, pp. 617-622, Aug. 1988. |
Krus, M., Bourdot, P., Osorio, A., Guisnel, F., Thibault, G., Adaptive tessellation of connected primitives for interactive walkthroughs in complex industrial virtual environments, Jun. 1999, Proceedings of the Eurographics workshop, pp. 1-10. |
Kumar, S., Manocha, D., Interactive display of large scale trimmed NURBS models, 1994, University of North Carolina at Chapel Hill, Technical Report, p. 1-36. |
Kuno et al. “New Interpolation Method Using Discriminated Color Correlation for Digital Still Cameras” IEEE Transac. On Consumer Electronics, vol. 45, No. 1, Feb. 1999, pp. 259-267. |
Loop, C., DeRose, T., Generalized B-Spline surfaces o arbitrary topology, Aug. 1990, SIGRAPH 90, pp. 347-356. |
M. Halstead, M. Kass, T. DeRose; “efficient, fair interolation using catmull-clark surfaces”; Sep. 1993; Computer Graphics and Interactive Techniques, Proc; pp. 35-44. |
Morimoto et al., “Fast Electronic Digital Image Stabilization for Off-Road Navigation”, Computer Vision Laboratory, Center for Automated Research University of Maryland, Real-Time Imaging, vol. 2, pp. 285-296, 1996. |
Paik et al., “An Adaptive Motion Decision system for Digital Image Stabilizer Based on Edge Pattern Matching”, IEEE Transactions on Consumer Electronics, vol. 38, No. 3, pp. 607-616, Aug. 1992. |
Parhami, Computer Arithmetic, Oxford University Press, Jun. 2000, pp. 413-418. |
S. Erturk, “Digital Image Stabilization with Sub-Image Phase Correlation Based Global Motion Estimation”, IEEE Transactions on Consumer Electronics, vol. 49, No. 4, pp. 1320-1325, Nov. 2003. |
S. Erturk, “Real-Time Digital Image Stabilization Using Kalman Filters”, http://www,ideallibrary.com, Real-Time Imaging 8, pp. 317-328, 2002. |
T. DeRose, M., Kass, T. Troung; “subdivision surfaces in character animation”; Jul. 1998; Computer Graphics and Interactive Techniques, Proc; pp. 85-94 |
Takeuchi, S., Kanai, T., Suzuki, H., Shimada, K., Kimura, F., Subdivision surface fitting with QEM-basd mesh simplificatio and reconstruction of aproximated B-Spline surfaces, 200, Eighth Pacific Conference on computer jraphics and applications pp. 2002-2012 |
Uomori et al., “Automatic Image Stabilizing System by Full-Digital Signal Processing”, vol. 36, No. 3, pp. 510-519, Aug. 1990. |
Uomori et al., “Electronic Image Stabiliztion System for Video Cameras and VCRS”, J. Soc. Motion Pict. Telev. Eng., vol. 101, pp. 66-75, 1992. |
“A Pipelined Architecture for Real-Time orrection of Barrel Distortion in Wide-Angle Camera Images”, Hau, T. Ngo, Student Member, IEEE and Vijayan K. Asari, Senior Member IEEE, IEEE Transaction on Circuits and Systems for Video Technology: vol. 15 No. 3 Mar. 2005 pp. 436-444. |
“Calibration and removal of lateral chromatic abberation in images” Mallon, et al. Science Direct Copyright 2006; 11 pages. |
“Method of Color Interpolation in a Singe Sensor Color Camera Using Green Channel Seperation” Weerasighe, et al Visual Information Processing Lab, Motorola Austrailian Research Center pp. IV-3233-IV3236, 2002. |
D. Doo, M. Sabin “Behaviour of recrusive division surfaces near extraordinary points”; Sep. 1997; Computer Aided Design; vol. 10, pp. 356-360. |
D. W. H. Doo; “A subdivision algorithm for smoothing down irregular shaped polyhedrons”; 1978; Interactive Techniques in Computer Aided Design; pp. 157-165. |
Davis, J., Marschner, S., Garr, M., Levoy, M., Filling holes in complex surfaces using volumetric diffusion, Dec. 2001, Stanford University, pp. 1-9. |
Donald D. Spencer, “Illustrated Computer Graphics Dictionary”, 1993, Camelot Publishing Company, p. 272. |
Duca et al., “A Relational Debugging Engine for Graphics Pipeline, International Conference on Computer Graphics and Interactive Techniques”, ACM SIGGRAPH Jul. 2005, pp. 453-463. |
E. Catmull, J. Clark, “recursively enerated B-Spline surfaces on arbitrary topological meshes”; Nov. 1978; Computer aided design; vol. 10; pp. 350-355. |
gDEBugger, graphicRemedy, http://www.gremedy.com, Aug. 8, 2006, pp. 1-18. |
http//en.wikipedia.org/wiki/Bayer—filter; “Bayer Filter”; Wikipedia, the free encyclopedia; pp. 1-4, May 14, 2010. |
http://en.wikipedia.org/wiki/Color—filter—array; “Color Filter Array”; Wikipedia, the free encyclopedia; pp. 1-5, May 17, 2010. |
http://en.wikipedia.org/wiki/Color—space; “Color Space”; Wikipedia, the free encyclopedia; pp. 1-4, May 14, 2010. |
http://en.wikipedia.org/wiki/Color—translation; “Color Management”; Wikipedia, the free encyclopedia; pp. 1-4, May 14, 2010. |
http://en.wikipedia.org/wiki/Demosaicing; “Demosaicing”; Wikipedia, the free encyclopedia; pp. 1-5, May 13, 2010. |
http://en.wikipedia.org/wiki/Half—tone; “Halftone”; Wikipedia, the free encyclopedia; pp. 1-5, May 13, 2010. |
http://en.wikipedia.org/wiki/L*a*b*; “Lab Color Space”; Wikipedia, the free encyclopedia; pp. 1-4, May 13, 2010. |
http://Slashdot.org/articles/07/09/06/1431217.html, Jul. 9, 2006. |
http:englishrussia.com/?p=1377, Oct. 1, 2007. |
Number | Date | Country | |
---|---|---|---|
20150002692 A1 | Jan 2015 | US |