Image analysis – Pattern recognition – Feature extraction
Patent
1995-06-09
1997-10-21
Boudreau, Leo
Image analysis
Pattern recognition
Feature extraction
382118, 382159, 382193, 382202, G06K 946, G06K 932, G06K 900, G06K 962
Patent
active
056804814
ABSTRACT:
A facial feature extraction method and apparatus uses the variation in light intensity (gray-scale) of a frontal view of a speaker's face. The sequence of video images are sampled and quantized into a regular array of 150.times.150 pixels that naturally form a coordinate system of scan lines and pixel position along a scan line. Left and right eye areas and a mouth are located by thresholding the pixel gray-scale and finding the centroids of the three areas. The line segment joining the eye area centroids is bisected at right angle to form an axis of symmetry. A straight line through the centroid of the mouth area that is at right angle to the axis of symmetry constitutes the mouth line. Pixels along the mouth line and the axis of symmetry in the vicinity of the mouth area form a horizontal and vertical gray-scale profile, respectively. The profiles could be used as feature vectors but it is more efficient to select peaks and valleys (maximas and minimas) of the profile that correspond to the important physiological speech features such as lower and upper lip, mouth corner, and mouth area positions and pixel values and their time derivatives as visual vector components. Time derivatives are estimated by pixel position and value changes between video image frames. A speech recognition system uses the visual feature vector in combination with a concomitant acoustic vector as inputs to a time-delay neural network.
REFERENCES:
patent: 3999006 (1976-12-01), Takeuchi et al.
patent: 4109237 (1978-08-01), Hill
patent: 4228465 (1980-10-01), Stone et al.
patent: 4449189 (1984-05-01), Feix et al.
patent: 4625329 (1986-11-01), Ishikawa et al.
patent: 4773024 (1988-09-01), Faggin et al.
patent: 4931865 (1990-06-01), Scarampi
patent: 4975960 (1990-12-01), Petajan
patent: 4975969 (1990-12-01), Tal
patent: 4975978 (1990-12-01), Ando et al.
patent: 5008946 (1991-04-01), Ando
patent: 5012522 (1991-04-01), Lambert
patent: 5063603 (1991-11-01), Burt
patent: 5412738 (1995-05-01), Brunelli et al.
Ben P. Yuhas et al., "Integration of Acoustic and Visual Speech Signals Using Neural Networks," IEEE Communications Magazine, pp. 65-71 (Nov. 1989).
Alex Waibel, "Modular Construction of Time-Delay Neural Networks for Speech Recognition," Massachusetts Institute of Technology, pp. 39-46 (1989).
Eric Petajan et al., "An Improved Automatic Lipreading System to Enhance Speech Recognition," CHI '88, p.19-25 (1988).
Yuhas et al. "Integration of Acoustic and Visual Speech Signals Using Neural Networks" IEEE Comm. Mag. vol. 27, No. 11, Nov. 1989, pp. 65-71.
Stork et al. "Neural Network Lipreading System for Improved Speech Recognition" IJCNN, vol. 2, Jun. 1992, pp. 289-295.
Kalivas et al. "Motion Compensated Enhancement of Noisy Image Sequences" ICASSP90, vol. 4, Apr. 1990, pp. 2121-2124.
Silsbee et al. "Automatic Lipreading" Proc. 30th Annual Rocky Mountain Bioeng Symp. Apr. 1993, pp. 415-422.
Alex Pentland et al., "Lip Reading: Automatic Visual Recognition of Spoken Words" M.I.T. Media Lab Vision Science Technical Report 117, pp. 1-9 (Jan. 15, 1989).
Carol Lee De Filippo, PhD et al., "New Reflections on Speechreading," The Volta Review, vol. 90, No. 5 (Sep. 1988).
Barbara Dodd et al., "Hearing by Eye: the Psychology of Lip-reading," Lawrence Erlbaum Associates Ltd. (1987).
Prasad K. Venkatesh
Stork David G.
Boudreau Leo
Davis Monica S.
Ricoh Company, Ltd
Ricoh Corporation
LandOfFree
Facial feature extraction method and apparatus for a neural netw does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Facial feature extraction method and apparatus for a neural netw, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Facial feature extraction method and apparatus for a neural netw will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1013343