SMBFT: A Modified Fuzzy c -Means Algorithm for Superpixel Generation

Author:

Yu Zhen1ORCID,Tian Cuihuan2ORCID,Ji Shiyong3,Wei Benzheng4,Yin Yilong5ORCID

Affiliation:

1. Shandong Rural Credit Union, Jinan 250014, China

2. Health Management Center, QiLu Hospital of Shandong University, and School of Medicine, Shandong University, Jinan 250012, China

3. Twenty-two Institute of China Electronics Technology Group Corporation, Qingdao 266107, China

4. College of Science and Technology, Shandong University of Traditional Chinese Medicine, Jinan 250355, China

5. School of Software Engineering, Shandong University, Jinan 250101, China

Abstract

Most traditional superpixel segmentation methods used binary logic to generate superpixels for natural images. When these methods are used for images with significantly fuzzy characteristics, the boundary pixels sometimes cannot be correctly classified. In order to solve this problem, this paper proposes a Superpixel Method Based on Fuzzy Theory (SMBFT), which uses fuzzy theory as a guide and traditional fuzzy c -means clustering algorithm as a baseline. This method can make full use of the advantage of the fuzzy clustering algorithm in dealing with the images with the fuzzy characteristics. Boundary pixels which have higher uncertainties can be correctly classified with maximum probability. The superpixel has homogeneous pixels. Meanwhile, the paper also uses the surrounding neighborhood pixels to constrain the spatial information, which effectively alleviates the negative effects of noise. The paper tests on the images from Berkeley database and brain MR images from the Brain web. In addition, this paper proposes a comprehensive criterion to measure the weights of two kinds of criterions in choosing superpixel methods for color images. An evaluation criterion for medical image data sets employs the internal entropy of superpixels which is inspired by the concept of entropy in the information theory. The experimental results show that this method has superiorities than traditional methods both on natural images and medical images.

Funder

National Natural Science Foundation of China

Publisher

Hindawi Limited

Subject

Applied Mathematics,General Immunology and Microbiology,General Biochemistry, Genetics and Molecular Biology,Modeling and Simulation,General Medicine

Reference28 articles.

1. Learning a classification model for segmentation;X. Ren;IEEE International Conference on Computer Vision,2003

2. Improving an object detector and extracting regions using superpixels;G. Shu;IEEE Conference on Computer Vision and PatternRecognition,2013

3. A review of segmentation method for MR image;L. Yi;Proceedings of the International Conference on Image Analysis and Signal Processing,2010

4. Segmentation and tracking of coronary artery using graph-cut in CT angiographic;M. Li;International Conference on Biomedical Engineering and Informatics,2009

5. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3