基于自商图像的人脸图像增强  

Face image enhancement based on self-quotient Image

作　　者：施水才[1,2] 杨忱[1] 王涛[1,2] 吕学强[1,2] 

机构地区：[1]北京信息科技大学中文信息处理研究中心,北京100101 [2]北京拓尔思信息技术股份有限公司,北京100101

出　　处：《计算机工程与应用》2013年第13期142-144,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(No.60872133);北京市自然科学基金(No.4092015);北京市教委科技发展计划项目(No.KM201110772021);国家科技支撑计划课题(No.2011BAH11B03)

摘　　要：为了降低光照对人脸识别效果的影响,通过多层次自商图像的方法获得反射系数。将原图作为输入图像采用反锐化掩模滤波的方式进行增强,再通过自商图像方法获得反射系数和光照成分;把光照成分作为输入图像,重复以上操作,对每次得到的反射系数按比例融合得到最终的反射系数。YaleB人脸库上的实验结果表明,该方法能在一定程度上去除光照的影响,使人脸识别率有一定的提高。In order to reduce the light on the face recognition effect, a method of obtaining reflection coefficient through the multi-level self-quotient image is proposed. Firstly, source image as input image is enhanced through the method of non-linearity unsharp masking. It can get reflection coefficient and light component through self-quotient image method. Then, the paper takes the light component as a new input image and repeats the above operations. Finally, it can obtain the final reflection coeffi-cient after all reflection coefficients got in each level is fusion. The results on YaleB face database show that the method can re-move the influence of light, make the face recognition rate has improved to a certain extent.

关 键 词：反射光照模型 自商图像 反锐化掩模滤波 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]