文献类型：会议论文

英文题名：Llumination estimation combining physical and statistical approaches

作者：Yuan, Jia-Zheng[1]; Tian, Li-Yan[2]; Bao, Hong[1]; Huang, Jing-Hua[1]; Zhang, Rui-Zhe[1]

第一作者：Yuan, Jia-Zheng

通讯作者：Yuan, J.-Z.

机构：[1] Institute of Information Technology, Beijing Union University, Beijing 100101, China; [2] College of Application Science and Technology, Beijing Union University, Beijing 100101, China

第一机构：北京联合大学智慧城市学院

通讯机构：[1]Institute of Information Technology, Beijing Union University, Beijing 100101, China|[1141734]北京联合大学智慧城市学院;[11417]北京联合大学;

会议论文集：3rd International Symposium on Intelligent Information Technology Application, IITA 2009

会议日期：November 21, 2009 - November 22, 2009

会议地点：NanChang, China

语种：英文

外文关键词：Color - Color computer graphics - Edge detection - Feature extraction - Motion compensation - Nearest neighbor search - Statistics

摘要：Illumination estimation for color constancy is an important problem in computer vision. Existing algorithms can be divided into two groups: physics-based algorithms and statistics-based approaches. In this paper, the advantages of the two kinds are integrated. At first, a novel statistic-based algorithm called Illumination Estimation using K-nearest-neighbor (IE-KNN) is proposed. And then the physics-based Grey-Edge algorithm is used to extract image features for IE-KNN. One of the most important aims of this paper is to reduce the feature dimension in traditional statistics-based approaches. The experimental results show that this combined physical and statistical algorithm is effective and can achieved much better color constancy result. ? 2009 IEEE.