Entropy-Based Maximally Stable Extremal Regions Robust to Blurring
Maximally stable extremal regions (MSER) is a state-of-the-art method in local feature detection.However,this method is sensitive to blurring because in region boundary the intensity value will vary more slowly, which undermines the stability criterion the MSER relies on.In this paper, we propose a method to improve the MSER method,making it more robust to image blur.To find back in the blurred image the regions missed by MSER, we utilize the fact that the entropy of the probability distribution function of intensity values increase rapidly when the local region expands across the boundary, while the entropy in the central part keeps small.We use the entropy averaged by region area as a measure to re-estimate regions missed by MSER.Experiments show that when dealing with blunred images, our method has better performance than the original MSER, with little extra computational effort.
Maximally Stable Extremal Regions Blurring Entropy
Huiwen Cai Xiaoyan Wang Yangsheng Wang
Digital Interactive Media Laboratory, Institute of Automation, Chinese Academy of Sciences, Beijing, College of Computer Scienceand Technology, Zhejiang University of Technology, Hangzhou, 310023
国内会议
长春
英文
1-7
2011-09-25（万方平台首次上网日期，不代表论文的发表时间）