作者: Xinjun Ma , Hongjun Zhang , Yuanyuan Li
关键词:
摘要: Lip-reading has potential attractive applications in information security, speech recognition, secret communication and so forth. To build an automatic lip-reading system, one key issue is how to locate the lip region, particularly under variant light condition. Therefore, a new localization algorithm proposed this paper, which contains three steps: face detection, rough precise localization. Among them, main point, based on transformation of YIQ color model template matching. Compared with threshold segment space transformation, matching more robust conditions. Besides, Q component can further increase contrast skin decrease effect illumination. Experimental results demonstrate that efficient