Title :
Study on Lipreading Recognition Based on Computer Vision
Author_Institution :
Sch. of Control & Comput. Eng., North China Electr. Power Univ., Beijing, China
Abstract :
The method of extracting characteristic parameters of lip according to lip template was presented. A dynamic clustering algorithm to classify the lip-shape based on the criteria of the least square error sum was proposed, and dynamic state sequence that described the lip movement was obtained by the improved ant colony algorithm. The lip-reading dynamic pattern recognition was performed by DTW algorithm. Experiments show the method of lip-reading recognition has satisfactory result in classifying isolated syllables.
Keywords :
computer vision; least squares approximations; object recognition; pattern clustering; speaker recognition; DTW algorithm; characteristic parameter extraction; computer vision; dynamic clustering algorithm; dynamic state sequence; dynamic time warping; least square error sum; lip movement; lipreading dynamic pattern recognition; Classification algorithms; Clustering algorithms; Feature extraction; Heuristic algorithms; Shape; Training; Visualization;
Conference_Titel :
Information Engineering and Computer Science (ICIECS), 2010 2nd International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-7939-9
Electronic_ISBN :
2156-7379
DOI :
10.1109/ICIECS.2010.5677823
