CASIA OpenIR  > 精密感知与控制研究中心  > 精密感知与控制
A total variation based nonrigid image registration by combining parametric and non-parametric transformation models
Hu, Wenrui; Xie, Yuan; Li, Lin; Zhang, Wensheng
Source PublicationNEUROCOMPUTING
2014-11-20
Volume144Pages:222-237
SubtypeArticle
AbstractTo overcome the conflict between the global robustness and the local accuracy of dense nonrigid image registration, we propose a union registration approach by combining parametric and non-parametric transformation models. On one hand, to guarantee the robustness, we constrain the displacement field phi using a mapping difference metric between the B-spline parametric space psi and the non-parametric transformation space (Phi. On the other hand, to correct the densely and highly localized geometrical distortions, we introduce a total variation (TV) regularization term for the displacement field phi. Accounting for the effect of spatially varying intensity distortions, the residual complexity (RC) is used as the similarity metric. Moreover, to solve the proposed union nonrigid registration, which is a composite convex optimization problem by the smooth l(2) term and the non-smooth l(2) term (TV), we design a two-stage algorithm using split Bregman iteration. Experiments with both synthetic and real images from different domains illustrate that this approach can capture the local details of transformation accurately and effectively while being robust to the spatially varying intensity distortions. (C) 2014 Elsevier B.V. All rights reserved.
KeywordNonrigid Registration Free-form Deformation Non-parametric Transformation Total Variation Split Bregman Iteration
WOS HeadingsScience & Technology ; Technology
WOS KeywordFREE-FORM DEFORMATIONS ; OPTICAL-FLOW ; ALGORITHMS
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000341677800022
Citation statistics
Cited Times:5[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/8069
Collection精密感知与控制研究中心_精密感知与控制
AffiliationChinese Acad Sci, Inst Automat, State Key Lab Intelligent Control & Management Co, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Hu, Wenrui,Xie, Yuan,Li, Lin,et al. A total variation based nonrigid image registration by combining parametric and non-parametric transformation models[J]. NEUROCOMPUTING,2014,144:222-237.
APA Hu, Wenrui,Xie, Yuan,Li, Lin,&Zhang, Wensheng.(2014).A total variation based nonrigid image registration by combining parametric and non-parametric transformation models.NEUROCOMPUTING,144,222-237.
MLA Hu, Wenrui,et al."A total variation based nonrigid image registration by combining parametric and non-parametric transformation models".NEUROCOMPUTING 144(2014):222-237.
Files in This Item: Download All
File Name/Size DocType Version Access License
A total variation ba(20168KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Hu, Wenrui]'s Articles
[Xie, Yuan]'s Articles
[Li, Lin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Hu, Wenrui]'s Articles
[Xie, Yuan]'s Articles
[Li, Lin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Hu, Wenrui]'s Articles
[Xie, Yuan]'s Articles
[Li, Lin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: A total variation based nonrigid image registration by combining parametric and non-parametric transformation models.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.