Fast Rotation-Free Feature-Based Image Registration Using Improved N-SIFT and GMM-Based Parallel Optimization

doi:10.1109/TBME.2015.2465855

CORC > 自动化研究所 > 中国科学院自动化研究所 > 中国科学院分子影像重点实验室

	Fast Rotation-Free Feature-Based Image Registration Using Improved N-SIFT and GMM-Based Parallel Optimization
	Yu, Dongdong1 ; Yang, Feng 2; Yang, Caiyun1 ; Leng, Chengcai 3; Cao, Jian 4,5; Wang, Yining 4,5; Tian, Jie1
刊名	IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
	2016-08-01
卷号	63 期号:8 页码:1653-1664
关键词	Accelerated Nsift Medical Imaging Parallel OptimizatiOn Based On Gaussian Mixture Model Rigid Image Registration Rotation-free
DOI	10.1109/TBME.2015.2465855
文献子类	Article
英文摘要	Image registration is a key problem in a variety of applications, such as computer vision, medical image processing, pattern recognition, etc., while the application of registration is limited by time consumption and the accuracy in the case of large pose differences. Aimed at these two kinds of problems, we propose a fast rotation-free feature-based rigid registration method based on our proposed accelerated-NSIFT and GMM registration based parallel optimization (PO-GMMREG). Our method is accelerated by using the GPU/CUDA programming and preserving only the location information without constructing the descriptor of each interest point, while its robustness to missing correspondences and outliers is improved by converting the interest point matching to Gaussian mixture model alignment. The accuracy in the case of large pose differences is settled by our proposed PO-GMMREG algorithm by constructing a set of initial transformations. Experimental results demonstrate that our proposed algorithm can fast rigidly register 3-D medical images and is reliable for aligning 3-D scans even when they exhibit a poor initialization.
WOS关键词	ALGORITHM ; ACCURACY
WOS研究方向	Engineering
语种	英语
WOS记录号	WOS:000380325000010
资助机构	National Basic Research Program of China (973 Program)(2011CB707700) ; National Natural Science Foundation of China(81227901 ; Chinese Academy of Sciences(2013Y1GB0005) ; National High Technology Research and Development Program of China (863 Program)(2012AA021105) ; Guangdong Province-Chinese Academy of Sciences(2010A090100032 ; NSFC-NIH(81261120414) ; Beijing Natural Science Foundation(4132080) ; Fundamental Research Funds for the Central Universities(2013JBZ014) ; National Basic Research Program of China(61301002) ; State Key Laboratory of Management and Control for Complex Systems(20140101) ; 61231004 ; 2012B090400039) ; 61363049)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/12171]
专题	自动化研究所_中国科学院分子影像重点实验室
通讯作者	Tian, Jie
作者单位	1.Chinese Acad Sci, Key Lab Mol Imaging, Inst Automat, Beijing 100190, Peoples R China 2.Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing, Peoples R China 3.Nanchang Hangkong Univ, Sch Math & Informat Sci, Nanchang, Peoples R China 4.Chinese Acad Med Sci, Peking Union Med Coll Hosp, Dept Radiol, Beijing, Peoples R China 5.Peking Union Med Coll, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Yu, Dongdong,Yang, Feng,Yang, Caiyun,et al. Fast Rotation-Free Feature-Based Image Registration Using Improved N-SIFT and GMM-Based Parallel Optimization[J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING,2016,63(8):1653-1664.
APA	Yu, Dongdong.,Yang, Feng.,Yang, Caiyun.,Leng, Chengcai.,Cao, Jian.,...&Tian, Jie.(2016).Fast Rotation-Free Feature-Based Image Registration Using Improved N-SIFT and GMM-Based Parallel Optimization.IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING,63(8),1653-1664.
MLA	Yu, Dongdong,et al."Fast Rotation-Free Feature-Based Image Registration Using Improved N-SIFT and GMM-Based Parallel Optimization".IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 63.8(2016):1653-1664.