改进单尺度Retinex的光照人脸识别陈薇.pdfVIP

Computer Engineering and Applications 计算机工程与应用 2013 ，49 （12） 151 改进单尺度Retinex 的光照人脸识别 1 2 3 2 陈 薇 ，赵方田 ，陈 侃 ，张明敏 1 2 3 2 CHEN Wei , ZHAO Fangtian , CHEN Kan , ZHANG Mingmin 1.浙江育英职业技术学院 信息技术与应用系，杭州 310018 2.浙江大学 计算机学院，杭州 310058 3.东软集团（上海）有限公司 政府事业部，杭州 310012 1.Department of Information Technology and Application, Zhejiang Yuying College of Vocational Technology, Hangzhou 310018, China 2.College of Computer, Zhejiang University, Hangzhou 310058, China 3.Department of Government, Neusoft Corporation（Shanghai）Co., Ltd, Hangzhou 310012, China CHEN Wei, ZHAO Fangtian, CHEN Kan, et al. Face recognition in change of illumination based on improved Retinex algorithm. Computer Engineering and Applications, 2013, 49 （12）：151-154. Abstract ：The classic Retinex algorithms hypothesize that the illumination of scene changes small. When the light changes strong, it is easy to produce a “Halo ”phenomenon. In order to improve the face recognition rate in the change of illumination, this paper proposes an improved Retinex algorithm for face recognition. The face image is enhanced by nonlinear global and lo- cal, and then bilateral filtering is used instead of Gauss filtering for Retinex algorithm, and Retinex algorithm is used to elimi- nate the influence of illumination. K near algorithm is used to build face classifier. The results show that the proposed algorithm can reduce time complexity, enhance the image effect compared with the similar algorithms, and improve the face recognition rate. It has solved the problem of “Halo ”very well. Key words ：Retinex algorithm; bilateral filtering; illumination preprocessing; face recognition 摘 要：经典Retinex 算法假设场景中光照是平缓变化的，当光照变化比较强烈时，易产生“光晕”现象，为了提高光照条件 变化下的人脸识别率，提出一种改进单尺度Retinex 的光照人脸识别方法。采用双曲正切函数代替Retinex 的对数函数对 人脸图像进行亮度和对比度非线性增强；利用双边滤波代替Retinex 的高斯