In the human language communication process, facial expression and lip shape change of the teller contains extremely rich language information. Previous research about lip-reading recognition focused on proposing the theoretical method to analyze rules of lip shapes. However, little evidence appears that the real lip reading recognition system was implemented. For getting moving lip features, principal component analysis and mouth changing rate were put forward by this paper. We implement a lip language recognition system by using image processing technology, neural network algorithm, and database to help people and computer understand lip language. The dynamic image variation of the lip shape changing could be detected in this system. The results indicated that this method could recognize effectively and correctly 62 Chinese words with 55 users and practically enhanced the lip language recognition.
Keywords
Lip Reading, Dynamic Image Recognition, Principal Component Analysis
User
Information