【作者】 孙劲光； 李扬；

【Author】 SUN Jin-guang ,LI Yang School of Electronic and Information Engineering,Liaoning Technical University,Huludao Liaoning 125105,China

【机构】 辽宁工程技术大学电子与信息工程学院；

【摘要】 为了提高在复杂光照条件变化下的人脸识别率,提出一种基于Mean-Shift平滑滤波的Retinex算法并将该算法用于人脸识别的光照预处理中。该算法通过局部非线性对比度增强对原图像增强,并利用Mean-Shift平滑滤波代替传统Retinex中的高斯滤波对光照估计,能够消除Retinex算法中不能解决的光晕现象。在CAS_PEAL人脸库的实验结果表明,该算法不仅比传统的光照预处理算法具有更好的光照预处理效果,而且能够有效提高人脸识别率。更多还原

【Abstract】 In order to improve the face recognition rate with complex illumination conditions changing,a Retinex algorithm based on Mean-Shift smoothing filtering was proposed and applied to illumination pretreatment of face recognition.The original image was enhanced by this method with local nonlinear contrast enhancement,illumination was evaluated by Mean-Shift smoothing filtering instead of Gaussian filter in traditional Retinex and the problem that halo formation couldn’t be removed by Retinex algorithm was solved.The result of experiment in CAS_PEAL face library shows that,the algorithm has better illumination pretreatment effect than tradition algotirhms,and also can improve the face recognition rate.更多还原