Title :
Lip modeling for visual speech recognition
Author :
Rao, Ram R. ; Mersereau, Russell M.
Author_Institution :
Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
fDate :
31 Oct-2 Nov 1994
Abstract :
In this paper, we describe an algorithm for modeling the shape of the mouth, and extracting meaningful dimensions for use by automatic lipreading systems. One advantage of this technique lies in the ability to normalize the model to compensate for scale and rotation. An error function is defined which relates the model to the image, and minimization of the error yields the best fit model. This is similar to deformable templates, but we attempt to perform the minimization in closed form. Visual only recognition was performed with features extracted from the model, and the recognition system achieved 85% accuracy on a two word discrimination task
Keywords :
feature extraction; image processing; speech processing; speech recognition; vision; algorithm; automatic lipreading systems; closed form minimization; deformable templates; error function; feature extraction; image; lip modeling; mouth shape; recognition accuracy; recognition system; rotation compensation; scale compensation; visual only recognition; visual speech recognition; word discrimination task; Acoustic noise; Automatic speech recognition; Detectors; Feature extraction; Image edge detection; Lips; Mouth; Nonlinear filters; Shape; Speech recognition;
Conference_Titel :
Signals, Systems and Computers, 1994. 1994 Conference Record of the Twenty-Eighth Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-8186-6405-3
DOI :
10.1109/ACSSC.1994.471520
