Patent Application
20070014485
Not Applicable
Not Applicable
Not Applicable
The present invention relates to modifying video images, in particular varying features of a person on live video.
Software has existed for some time to modify images, such as a person's face. U.S. Pat. No. 5,825,941 is an example of software allowing a patient to see the effects of proposed plastic surgery before it is done. Other software allows users to modify static pictures that can be saved and printed, such as by varying the features of the face or morphing two faces together. US Published Application No. 20050026685 shows a system for morphing video game characters. US Published Application No. 20040201666 shows using user voice or other inputs to modify a virtual character.
A variety of applications are directed to modifying avatars for use with instant messaging. These applications allow a user to personalize the avatar image that is the representation of the user. For example, U.S. Published Application No. 20030043153 shows determining facial expressions from a webcam video feed and mapping those expressions to an avatar. An animation vector is mapped to a target mix vector. Each morph target may represent a facial expression, such as a neutral facial expression, a surprised facial expression, an angry facial expression, and a smiling facial expression.
The present invention provides a method for modifying, or morphing, a video image. A video feed is received which include an image of a person's face. A number of facial features are detected from the video feed. One or more of those facial features are selected and modified, with the modification being applied to the video feed to produce a morphed image. For example, the morphing can produce fun effects such as oversized or too small eyes, lips, etc.
In one embodiment, the user can choose to modify particular features directly. For example, the user can thicken the lips, widen the mouth, etc. The user can then do similar modifications separately to the eyes, nose, ears, etc. Additionally, the user can select to have a hat or other accessories superimposed over the face.
In another embodiment, the user can select from multiple expressions. The selected expression would then automatically change the particular features required to achieve that expression. For example, the expression for a smile can cause the lips and mouth to raise in the smile expression, and additionally can cause smile lines or dimples and a twinkling appearance in the eyes. Alternately another “expression” such as a younger age could cause the smoothing of the skin to eliminate wrinkles, modification of the facial features to produce a more defined chin, eyes, etc.
In one embodiment, a video feed from a web cam, such as a USB video feed is provided through a camera driver to feature recognition software. That software then provides the location of the identified features to a separate morphing software module. The morphing software module then responds to user inputs to select and apply modifications to the various facial features. These modifications are then applied to the video feed, to produce an output video feed which is only slightly delayed in real time.
System
The modified video pipe can be used by any application that uses live video input. This includes instant messaging applications (MSN Messenger, Yahoo Messenger, AOL messenger, etc.) as well as video capture applications (when—for example—an artist is capturing the video to the disk). This means that the morphing can be applied before the video is captured to the disk and stored or before it is sent to the interlocutor on the other side of the communication channel. This is because the morphing engine is integrated into the system-level part of the software, which makes it transparent to the applications using the video stream that lay above the system layer at the user layer. In this way the present invention is generic—i.e. it can coexist with any video application and modify its input according to the settings on quick assistant.
Computer 14 includes a camera driver 16 which receives the live video and provides it to feature recognition software module 18. Feature recognition module 18 could be any software which extracts information regarding facial features from a video image, such as the software produced by Neven Vision, a machine vision technology company with offices in Santa Monica, Calif.
The detected information regarding facial features is provided to a morphing module 20. The morphing module responds to user inputs to select facial features, determine the type of morphing, and apply the morphing. The user input can be provided through any peripheral, such as keyboard 22 or mouse 24 with associated keyboard driver 26 and mouse driver 28. After the morphing has been applied, the video feed is provided to application software 30. The application software could be an instant messenger application, a video conferencing application, or any other application which uses video. In one embodiment, the delay caused by the use of the feature recognition and morphing software is less than one frame of video.
Morphing Quick Assistant
Options
The morphing module allows a virtual makeover to be applied to a person. The size of the eyes can be changed, and their location can be modified slightly. The iris color can be changed. The lips could be made wider or narrower, or could be accentuated in other ways. A variety of other modifications are available.
Manual Selection
When Lips Enhancement is selected the box 58 of
Expression Selection
Preview Screen
Variations
In one embodiment, the deformation applied to a face (e.g., ‘fuller lips’) would move with the subject. In some prior art applications, the deformation is applied to frontal face. In an embodiment of the present invention, the 3D position of the head and the features is localized and the deformation is adjusted from a frontal position to the actual position of the user. Thus, even if the face is not frontal, the deformation (e.g. full lips) is maintained when the subject rotates his head so the lips or other feature would still look natural, but they would be ‘fuller’. This is accomplished with a 3D image being stored and modified for each feature, or with algorithms for adjustment in 3D on the fly being used.
In one embodiment, the present invention is able to apply the modifications to live video on the fly with a delay of less than one frame. This is possible because only certain features of the face are morphed or modified, not the entire face. In one embodiment, less than 20% or less than 10% of the video is modified. This limits the amount of processing necessary and increases the speed at which the morphing can be done.
In another embodiment, the user selects the morphing to be applied before the video is fed to the application software program. In another embodiment, the user can also do the adjustments on the fly, morphing or changing the video image in the middle of an instant messenger conversation, for example.
In one embodiment, the invention is integrated into the video pipe so that it is transparent to any application program. The application program need not be modified to accommodate the present invention, which is applied at the driver level of the video feed.
In another embodiment, popular morphing combinations are stored as a macro or particular expression. These are provided on a website which is accessible by users, and users can create their own and upload them to the website for sharing with other users. Morphing to produce features similar to those of celebrities can be stored as a macro on the web site for downloading.
In one embodiment, such as for a conference call with multiple people present, the morphing can be applied independently to different facial features. Thus, one person could be made to have wider eyes, another can be made smile all the time, another could be made to be anger, and another could be made to look younger.
In addition, an entire image can be morphed with, for example, effects similar to those found in a fun house mirror room. By keeping the effects simple, they can be applied in real time without undue delay. Delay is also cut down by the ability to bypass the facial feature detection software, since this is not needed when the entire image is morphed. In one embodiment, the morphing causes a delay of less than 20 milliseconds.
As will be understood as those of skill in the art, the present invention could be embodied in other specific forms without departing from the essential characteristics of the invention. For example, the morphing could be applied to features of the face of a pet, such as a dog, or any other image. The morphing module could also be made to appear upon initiation of an application program which uses still pictures, such as the sending of snapshots from a cell phone. The morphing engine could be made to appear anytime a video feed is requested by an application program, or only for certain types of application programs. Accordingly, reference should be made to the appended claims which set forth the scope of the claimed invention.
