A total variation based nonrigid image registration by combining parametric and non-parametric transformation models

CORC > 自动化研究所 > 中国科学院自动化研究所 > 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
刊名	NEUROCOMPUTING
	2014-11-20
卷号	144 页码:222-237
关键词	Nonrigid registration Free-form deformation Non-parametric transformation Total variation Split Bregman iteration
英文摘要	To 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.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Computer Science, Artificial Intelligence
研究领域[WOS]	Computer Science
关键词[WOS]	FREE-FORM DEFORMATIONS ; OPTICAL-FLOW ; ALGORITHMS
收录类别	SCI
语种	英语
WOS记录号	WOS:000341677800022
公开日期	2015-09-22
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/8069]
专题	精密感知与控制研究中心_精密感知与控制
作者单位	Chinese Acad Sci, Inst Automat, State Key Lab Intelligent Control & Management Co, Beijing 100190, Peoples R China
推荐引用方式 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.