Extraction of lip movement image signals from sucessive image frames

This paper is concerned with the extraction of lip movement image signals from successive image frames. It is suggests the possibility that lip movement image signals can be utilized while detecting the speech block of speech recognition procedures. The image frames are acquired from the PC image camera with the assumption that facial movement is limited during the conversation. First of all, one new lip movement image frame generated with comparing two successive image frames each other. Second, the fine image noises are removed. And residual images are separated into different areas. Each fitness rate is calculated by comparing the lip feature data as objectly separated images. It is analyzed whether or not there is the lip movement image through verification to the objects, three images that their fitness rate is high. As a result of linking the speech & image processing system, the interworking rate of 99.3% was shown even in the various image environments. It was visually confirmed that lip movement image signals are tracked, and its utilization possibility in speech block extraction process.