Image encoding and synthesis
First Claim
Patent Images
1. An apparatus for encoding a moving image including a human face comprising:
- means for receiving video input data;
means for output of data representing one frame of the image;
identification means arranged in operation for each frame of the image to identify that part of the input data corresponding to the mouth of the face represented and(a) in a first phase of operation to compare the mouth data parts of each frame with those of other frames to select a representative set of mouth data parts, to store the selected parts and to output the selected parts;
(b) in a second phase to compare the mouth data part of each frame with those of the stored set and to generate a codeword indicating which member of the set the mouth data part of that frame most closely resembles.
0 Assignments
0 Petitions
Accused Products
Abstract
Visual images of the face of a speaker are processed to extract during a learning sequence a still frame of the image and a set of typical mouth shapes. Encoding of a sequence to be transmitted, recorded etc. is then achieved by matching the changing mouth shapes to those of the set and generating codewords identifying them. Alternatively, the codewords may be generated to accompany real or synthetic speech using a look- up table relating speech parameters to codewords. In a receiver, the still frames and set of mouth shapes are stored and received codewords used to select successive mouth shapes to be incorporated in the still frame.
104 Citations
17 Claims
-
1. An apparatus for encoding a moving image including a human face comprising:
-
means for receiving video input data; means for output of data representing one frame of the image; identification means arranged in operation for each frame of the image to identify that part of the input data corresponding to the mouth of the face represented and (a) in a first phase of operation to compare the mouth data parts of each frame with those of other frames to select a representative set of mouth data parts, to store the selected parts and to output the selected parts; (b) in a second phase to compare the mouth data part of each frame with those of the stored set and to generate a codeword indicating which member of the set the mouth data part of that frame most closely resembles. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A receiver for decoding a moving image including a human face, the receiver comprising:
-
frame store means for receiving and storing data representing one frame of the image; means for repetitive readout of the frame store to produce a video signal; further store means receiving and storing a set of selected mouth data parts; and control means arranged in operation to receive input codewords and in response to each codeword to read out the corresponding mouth data part from the further store and to effect insertion of that data into the data supplied to the readout means. - View Dependent Claims (10, 11, 12, 13)
-
-
14. A speech synthesiser including means for synthesis of a moving image including a human face, comprising;
-
(a) means for storage and output of the image of a face; (b) means for storage and output of a set of mouth data blocks each corresponding to the mouth area of the face and representing a respective different mouth shape; (c) speech synthesis mans responsive to input information identifying words or parts of words to be spoken; (d) means storing a table relating words or part of words to codewords identifying mouth data blocks or sequences thereof; (e) control means responsive to the said input information to select for output the corresponding codewords or codeword sequences from the table. - View Dependent Claims (15, 17)
-
-
16. An apparatus for synthesis of a moving image, comprising:
-
(a) means for storage and output of the image of a face; (b) means for storage and output of a set of mouth data blocks each corresponding to the mouth area of the face and representing a respective different mouth shape; (c) an audio input for receiving speech signals and frequency analysis means responsive to such signals to produce sequences of spectral parameters; (d) means storing a table relating spectral parameter sequences to codewords identifying mouth data blocks or sequences thereof; (e) control means responsive to the said spectral parameters to select for output the corresponding codewords or codeword sequences from the table.
-
Specification