A PCA based Visual DCT Feature Extraction Method for Lip-Reading

Abstract—This paper proposes a new technique for face detection and lip feature extraction. A real-time field-programmable gate array (FPGA) implementation of the two proposed techniques is also presented. Face detection is based on a naive Bay

实现一种结合颜色空间、变换及变形模板的自动唇部定位及唇轮廓提取、跟踪方法首先在空间建立肤色模型进行人脸检测、定位, 并由人脸几何特征进行唇部粗定位然后结合唇色模型进行变换使肤、唇色差别明显化, 提出根据亮度信息对变换结果预处理后用法进行图像分割, 经唇色模型进一步验证后实现唇部精定位再使用变形模板来进行嘴唇轮廓特征提取, 为增强内轮廓定位的鲁棒性, 对经亮度预处理和唇色模型验证得到的口腔区域边缘图进行曲线拟合来实现内轮廓定位最后, 将唇读图像序列中上一帧的唇部定位结果拓展后作为当前帧的预测区域再

提取唇部特征作为用于识别的特征向量从而识别出简单的唇语-Lip feature extraction for recognition as a feature vector to identify simple lips