Method and System for Immersing Face Images into a Video Sequence
2 Assignments
0 Petitions
Accused Products
Abstract
The present invention is a system and method for immersing facial images of people captured automatically from an image or a sequence of images into a live video playback sequence. This method allows viewers to perceive a participation in the viewed “movie” segment. A format is defined for storing the video such that this live playback of the video sequence is possible. A plurality of Computer Vision algorithms in the invention processes a plurality of input image sequences from the means for capturing images, which is pointed at the users in the vicinity of the system and performs the head detection and tracking. The interaction in the invention can be performed either in real-time or off-line depending on the embodiment of the invention in an uncontrolled background.
38 Citations
53 Claims
-
1-33. -33. (canceled)
-
34. An apparatus, comprising:
-
a processor; memory; and software, stored in the memory that, in response to execution by the processor, causes the apparatus to perform operations comprising; receiving a plurality of input images, extracting one or more facial images from the plurality of input images, generating demographic classifications using the one or more facial images, replacing at least one replaceable actor image with at least one of the one or more facial images, based on the demographic classifications, and creating a movie using the replaced at least one replaceable actor image. - View Dependent Claims (35, 36, 37, 38, 39, 40, 41, 42, 43)
-
-
44. A computer-readable storage medium, configured to store software that, in response to execution by a processor, causes the processor to perform operations comprising:
-
receiving a plurality of input images, extracting one or more facial images from the plurality of input images, generating demographic classifications using the one or more facial images, replacing at least one replaceable actor image with at least one of the one or more facial images, based on the demographic classifications, and creating a movie using the replaced at least one replaceable actor image. - View Dependent Claims (45, 46, 47, 48, 49, 50, 51, 52, 53)
-
Specification