Image Segmentation via Fischer-Burmeister Total Variation and Thresholding

作     者：TingtingWu Yichen Zhao Zhihui Mao Li Shi Zhi Li Yonghua Zeng 

作者机构：School of ScienceNanjing University of Posts and TelecommunicationsNanjingJiangsu 210023China The Department of Computer Science and TechnologyShanghai Key Laboratory of Multidimensional Information ProcessingEast China Normal UniversityShanghai 200241China College of Field EngineeringPLA Army Engineering UniversityNanjingJianhsu 210007China 

出 版 物：《Advances in Applied Mathematics and Mechanics》 (应用数学与力学进展（英文）)

年 卷 期：2022年第14卷第4期

页      面：960-988页

核心收录：

学科分类：07[理学] 0701[理学-数学] 070101[理学-基础数学] 

基　　金：supported by the Natural Science Foundation of China(Grant Nos.61971234,11501301,and 62001167) the“1311 Talent Plan”of NUPT,the“QingLan”Project for Colleges and Universities of Jiangsu Province,East China Normal University through startup funding,and Technology Innovation Training Program(Grant No.SZDG2019030) 

主　　题：Image segmentation Fischer-Burmeister total variation difference of convex algorithm sPADMM K-means method. 

摘      要：Image segmentation is a significant problem in image *** this paper,we propose a new two-stage scheme for segmentation based on the Fischer-Burmeister total variation(FBTV).The first stage of our method is to calculate a smooth solution from the FBTV Mumford-Shah ***,we design a new difference of convex algorithm(DCA)with the semi-proximal alternating direction method of multipliers(sPADMM)*** the second stage,we make use of the smooth solution and the K-means method to obtain the segmentation *** simulate images more accurately,a useful operator is introduced,which enables the proposed model to segment not only the noisy or blurry images but the images with missing pixels *** demonstrate the proposed method produces more preferable results comparing with some state-of-the-art methods,especially on the images with missing pixels.