基于图像的嘴唇特征提取及口型分类研究-计算机技术专业论文.docx

ABSTRACT Recently, computer lipreading technology has received the concern of more and more researchers, which is regarded as an auxiliary method for Automatic Speech Recognition (ASR). Lipreading research mainly includes: the basic characteristics of the mouth figure extraction, description and said, as well as lip figure recognition and understanding, it is the comprehensive understanding of the relevant information from number of channels. This paper mainly studies methods of the face location, lip area location , lip feature extraction and Mouth-shapes classification in a human face image. Firstly, based on analysis and compares of the current mainstream method of lipreading deeply, illumination compensation is performed based on the histogram equalization. Then, we constructed a skin-color model for skin detection in YCbCr color space so that the approximate face region can be obtained. Next, Fisher transformation approach is used to strengthen the gradient information of the lip region and then the lip region can be obtained based on the geometry features of human face. Secondly, Based on the separability of different components in different color spaces for lip and non-lip, a lip segmentation method based on ‘a’ component and ‘L’ component of LAB color space is used to split outer lip and inner lip. This method performance very good and it can create the threshold automatically. Then several curves based on Deformable Templates are used to make up a mathematics formulary of the lips. We proposed a method to improve match result for get the shape feature of lips. Finally, Mouth-shapes in the face image are classified into four types by the characteristics of Chinese vowel Lamiaceae: a-style, o-style, e-style and i-style. Experimental results show that our method is effective and meaningful in practice. KEY WORDS ： Lip Feature Extraction, Mouth-Shapes classification, Deformable Templates 目 录 HYPERLINK \l _bookmark0 第一章 绪论 1 HYPERLINK \l _bookmark1 1.1