Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)
- 2006.06a
- /
- Pages.259-260
- /
- 2006
Lip Feature Extraction using Contrast of YCbCr
YCbCr 농도 대비를 이용한 입술특징 추출
- Kim, Woo-Sung (Department of Electronics and Computer Engineering, Korea University) ;
- Min, Kyung-Won (Digital Media Research Center, Korea Electronics Technology Institute) ;
- Ko, Han-Seok (Department of Electronics and Computer Engineering, Korea University)
- Published : 2006.06.21
Abstract
Since audio speech recognition is affected by noise in real environment, visual speech recognition is used to support speech recognition. For the visual speech recognition, this paper suggests the extraction of lip-feature using two types of image segmentation and reduced ASM. Input images are transformed to YCbCr based images and lips are segmented using the contrast of Y/Cb/Cr between lip and face. Subsequently, lip-shape model trained by PCA is placed on segmented lip region and then lip features are extracted using ASM.
Keywords