中文摘要：

人脸的表情识别在智能人机交互应用中具有重要意义. 本文提出了一种基于肤色增强和分块PC A的 人脸检测及表情识别方法. 首先,使用同态滤波增强肤色图像的亮度范围及对比度,利用 YCbCr色彩空间分量 分离肤色背景区域,再通过轮廓分析确定人脸目标,最后对分割出的人脸进行均衡化处理,并引入分块主成分分析 （PCA）算法进行表情识别. 结果表明,该方法在光线较弱以及背景较复杂的情况下均能有效地进行人脸检测 与表情识别,相对于传统的 LBP方法可提高识别率约为2.3%.

英文摘要：

The facial expression recognition is of great significance in the application of intelligent man-machine interaction.This paper has proposed the face detection and expression recognition method based on the skin color enhancement and block PCA. Firstly, the skin color image luminance range is broadened and the contrast ratio is strengthened by the homo-morphic filtering method. Secondly,the skin color background region is separated through YCbCrThirdly, the face target is determined by the contour analysis. Finally, the equalization processing is made of the segmented face and the princijDal component analysis（ PCA） is imported to accomplisli the facial expressmental results show that in case of tlie weaker light and more complicated background, the face detection and facial expres-sion recognition botli can be achieved efectively through the metliod proposed in this paper,has improved 2.3% compared with the traditional LBP method.