| 基于全变分模型的多分辨率光照处理算法 |
| |
| 引用本文： | 王涌,庄连生,庄镇泉,李斌.基于全变分模型的多分辨率光照处理算法[J].电路与系统学报,2009,14(1). |
| |
| 作者姓名： | 王涌 庄连生 庄镇泉 李斌 |
| |
| 作者单位： | 1. 中国科学技术大学,多媒体计算与通信教育部-微软重点实验室,安徽,合肥,230026;中国科学技术大学电子科学与技术系,安徽,合肥,230027
2. 中国科学技术大学,电子科学与技术系,安徽,合肥,230027 |
| |
| 基金项目： | 多媒体计算与通信教育部-微软蘑点实验室科研基金，安徽省人才开发基金，NSFC-RGC国家自然科学基金香港联合资助项目，国家自然科学基金 |
| |
| 摘 要： | 针对人脸识别中的光照问题,本文提出一种多分辨率分层的快速处理算法.该算法建立在扩展的全变分模型的理论基础之上,具有模型简单,优化参数少等优点,并能有效的减少光晕现象.算法从快速性入手,首先将光照劣化图像进行多分辨率分层,在每一层上利用模型进行估计,从而得出整体的光照成分,然后恢复出入脸的反射系数图像,并以此作为光照不变量来进行识别.实验证明,通过多分辨率分层的方法,不仅能使系统在不同光照条件下的识别率得到提高,而且还能解决单独用TV(Total Variation)模型进行估计时处理速度较慢的缺点.
|
| 关 键 词： | 人脸识别 光照处理 全变分模型 多分辨率算法 |
A multi-resolution algorithm for illumination processing based on total variation model |
| |
| WANG Yong,ZHUANG Lian-sheng,ZHUANG Zhen-quan,LI Bin.A multi-resolution algorithm for illumination processing based on total variation model[J].Journal of Circuits and Systems,2009,14(1). |
| |
| Authors: | WANG Yong ZHUANG Lian-sheng ZHUANG Zhen-quan LI Bin |
| |
| Affiliation: | WANG Yong1,2,ZHUANG Lian-sheng2,ZHUANG Zhen-quan2,LI Bin2(1.MOE-Microsoft Key Laboratory of Multimedia Computing , Communication,University of Science , Technology of China,USTC,Hefei 230027,China,2.Department of Electronic Science & Technology,Hefei 230026,China) |
| |
| Abstract: | Illumination is one of the most difficult problems in Face Recognition.In this paper,we present a multi-resolution algorithm for illumination processing,which is based on Total Variation Model.Compared to other illumination algorithms,TV model has some advantages:(1) It has good edge-preserving property,so as to remove halo efficiently.(2)There are only a few parameters to set.But there exists an obvious defect: because TV model operates on the whole image by itself,the process of estimating the lighting im... |
| |
| Keywords: | face recognition illumination process total variation model multi-resolution |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
