Minimum Description Length Shape Model Based on Bio-inspired Features

摘要：

This paper proposes an enhanced MDL Shape Model to solve the point correspondence problem. The current MDL methods build models mainly based on shape information and may get bad models. Motivated by the biologically inspired features (BIF), which inspired by visual cortex, we compute the C1 response on the master node and add the cost of BIF across training set to the objective function of MDL Shape Models. Experiments show that our method can get better model and point correspondence.

关键词： MDL shape model biologically inspired features statistical shape models gabor filters visual cortex

作者: Shaoyu Wang Yongfeng Huang Zhidong Qin Xiaoyong Liao Youjun Luo

作者单位: School of Computer Science and TechnologyDonghua UniversityShanghai, China Department of System DesignFukong Hualong Microsystem Technology Co.,LTDShanghai, China Department of System Design Fukong Hualong Microsystem Technology Co.,LTD Shanghai, China

会议类型: 国际会议

会议名称: 2010 3rd International Conference on Advanced Computer Theory and Engineering(2010年第三届先进计算机理论与工程国际会议 ICACTE 2010)

会议地点: 成都

会议语种:英文

页码: 1-4

在线出版日期: 2010-08-20（万方平台首次上网日期，不代表论文的发表时间）