Research on improved level set image segmentation method

Author:

Zhang Mei,Meng Dan,Liu Lingling,Wen JinghuaORCID

Abstract

Aiming at the shortcomings of the traditional level set model which only has good robustness to the weak boundary and strong noise of the original target image, this paper proposes an improved algorithm based on the no-weight initialization level set model, introducing bilateral filters and using implicit surface level sets to extract and segment the original target image object more accurately, clearly and intuitively in the evolution process. The experimental simulation results show that, compared with the traditional non-reinitialized level set model segmentation method, the improved method can more accurately extract the edge contours of the target image object, and has better edge contour extraction effect, and the original target noise reduction effect of the improved model is better than that of the model before the improvement. The original target image object edge contour takes less time to extract than the conventional non-reinitialized level set model before the improvement.

Funder

department of science and technology of Guizhou province

Science and Technology Program of the Guizhou Provincial Science and Technology Agency

Guizhou Key Laboratory of Big Data Statistical Analysis

Publisher

Public Library of Science (PLoS)

Subject

Multidisciplinary

Reference25 articles.

1. Cai Qing. Research on image segmentation and target tracking algorithm based on level set theory[D]. xi’an: Northwestern Polytechnic University, 2019.

2. Ma Chao. Research on 3D segmentation of medical magnetic resonance image body data [D]. Harbin: Harbin Institute of Technology, 2019.

3. Wu Di. Research on typical target detection methods for optical remote sensing images [D]. Harbin: Harbin Institute of Technology, 2019.

4. Mahalanobis distance based on fuzzy clustering algorithm for image segmentation;X. Zhao;Digital Signal Processing,2015

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