System and method for eye alignment in video

Abstract

A system for image manipulation enables an improved video conferencing experience. The system includes a camera; a display screen adjacent to the camera; a processor coupled to the camera and the display screen; and a memory coupled to the processor. Instructions executable by the processor enable receiving a source image from the camera and generating a synthetic image based upon the source image. The synthetic image corresponds to a view of a virtual camera located at the display screen.

What is claimed is: 
     
         1 . A system for image manipulation, including:
 a camera;   a display screen adjacent to the camera;   a processor coupled to the camera and the display screen; and   a memory coupled to the processor, including instructions executable by the processor for:   receiving a source image from the camera; and   generating a synthetic image based upon the source image, the synthetic image corresponding to a view of a virtual camera located at the display screen.   
     
     
         2 . The system according to  claim 1 , wherein the camera and display screen are integrated into a single structure. 
     
     
         3 . The system according to  claim 1 , wherein the camera and display are independently movable, and the memory further includes instructions for estimating a location of the display screen relative to the camera. 
     
     
         4 . The system according to  claim 1 , wherein generating a synthetic image further includes:
 detecting a face in the source image; and   transforming the face according to a location of the virtual camera.   
     
     
         5 . The system according to  claim 4 , wherein transforming the face includes applying an Active Appearance Model (AAM) to the face, and modifying parameters of the AAM. 
     
     
         6 . The system according to  claim 4 , wherein generating a synthetic image further includes:
 generating a 3D model of the face; and   rotating the 3D model according to a displacement between the camera and the virtual camera.   
     
     
         7 . The system according to  claim 1 , wherein the virtual camera location is fixed centrally with respect to the display screen. 
     
     
         8 . The system according to  claim 1 , wherein the virtual camera location is determined based upon content presented on the display screen. 
     
     
         9 . The system according to  claim 1 , wherein the image comprises an image of a video sequence. 
     
     
         10 . The system according to  claim 9 , wherein the video sequence is one of a two-dimensional or a three-dimensional video sequence. 
     
     
         11 . The system according to  claim 1 , wherein the memory further includes instructions for:
 receiving a second source image from the camera; and   generating a second synthetic image based upon the source image and the second source image, the second synthetic image corresponding to the view of the virtual camera.   
     
     
         12 . The system according to  claim 1 , wherein generating the synthetic image comprises modifying metadata relating to the source image. 
     
     
         13 . The system according to  claim 12 , wherein the metadata includes camera parameters. 
     
     
         14 . A computer implemented method for video conferencing including:
 receiving, on a data interface, a source image from a camera; and   generating, by a processor, a synthetic image based upon the source image, the synthetic image corresponding to a view of a virtual camera located at a display screen, wherein the display screen is adjacent to the camera.   
     
     
         15 . The method according to  claim 14 , further including estimating a location of the display screen relative to the camera. 
     
     
         16 . The method according to  claim 14 , wherein generating a synthetic image further includes:
 detecting a face in the source image; and   transforming the face according to a location of the virtual camera.   
     
     
         17 . The method according to  claim 16 , wherein transforming the face includes applying an Active Appearance Model (AAM) to the face, and modifying parameters of the AAM. 
     
     
         18 . The method according to  claim 16 , wherein generating the synthetic image further includes:
 generating a 3D model of the face; and   rotating the 3D model according to a displacement between the camera and the virtual camera.   
     
     
         19 . The method according to  claim 16 , wherein transforming the face includes transferring facial expressions from the face to an avatar image. 
     
     
         20 . The method according to  claim 14 , wherein the virtual camera location is determined, by the processor, based upon content presented on the display screen.