Total Variation Constrained Non-Negative Matrix Factorization for Medical Image Registration
Chengcai Leng; Hai Zhang; Guorong Cai; Zhen Chen; Anup Basu
刊名IEEE/CAA Journal of Automatica Sinica
2021
卷号8期号:5页码:1025-1037
关键词Data clustering dimension reduction image registration non-negative matrix factorization (NMF) total variation (TV)
ISSN号2329-9266
DOI10.1109/JAS.2021.1003979
英文摘要This paper presents a novel medical image registration algorithm named total variation constrained graph-regularization for non-negative matrix factorization (TV-GNMF). The method utilizes non-negative matrix factorization by total variation constraint and graph regularization. The main contributions of our work are the following. First, total variation is incorporated into NMF to control the diffusion speed. The purpose is to denoise in smooth regions and preserve features or details of the data in edge regions by using a diffusion coefficient based on gradient information. Second, we add graph regularization into NMF to reveal intrinsic geometry and structure information of features to enhance the discrimination power. Third, the multiplicative update rules and proof of convergence of the TV-GNMF algorithm are given. Experiments conducted on datasets show that the proposed TV-GNMF method outperforms other state-of-the-art algorithms.
WOS记录号WOS:000638401600007
内容类型期刊论文
源URL[http://ir.ia.ac.cn/handle/173211/43964]  
专题自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式
GB/T 7714
Chengcai Leng,Hai Zhang,Guorong Cai,et al. Total Variation Constrained Non-Negative Matrix Factorization for Medical Image Registration[J]. IEEE/CAA Journal of Automatica Sinica,2021,8(5):1025-1037.
APA Chengcai Leng,Hai Zhang,Guorong Cai,Zhen Chen,&Anup Basu.(2021).Total Variation Constrained Non-Negative Matrix Factorization for Medical Image Registration.IEEE/CAA Journal of Automatica Sinica,8(5),1025-1037.
MLA Chengcai Leng,et al."Total Variation Constrained Non-Negative Matrix Factorization for Medical Image Registration".IEEE/CAA Journal of Automatica Sinica 8.5(2021):1025-1037.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace