Improved bidirectional image registration based on Radon-SIFT

OPT OpenIR > 空间光学技术研究室

	Improved bidirectional image registration based on Radon-SIFT
	Bu, Fan; Qiu, Yuehong; Liu, Jinxia; Yan, Xingtao
作者部门	空间光学技术研究室
	2012
发表期刊	Journal of Computational Information Systems
ISSN	15539105
卷号	8 期号:12 页码:4997-5004
产权排序	1
摘要	Aiming at the problems of large calculation, high complexity and long time-consuming in Scale Invariant Feature Transform (SIFT) feature matching algorithm, this paper proposes a novel bidirectional Radon-SIFT matching algorithm. Based on Radon transform, we make 36 beelines on different directions in local keypoints region. Along these 36 directions, we calculate Radon transform integral values which can be chosen as keypoints vector descriptors. 36-dimensional Radon-SIFT descriptors outweigh the standard 128-dimensional ones both in accuracy and efficiency. The other contribution of this paper is bidirectional matching algorithm. This improved algorithm introduces matching uniqueness constraint to further reduce matching error. To demonstrate the effectiveness and robustness of the proposed algorithm, we apply it to natural images. Experimental results show greater accuracy and faster matching.
收录类别	EI
语种	英语
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/20267
专题	空间光学技术研究室
推荐引用方式 GB/T 7714	Bu, Fan,Qiu, Yuehong,Liu, Jinxia,et al. Improved bidirectional image registration based on Radon-SIFT[J]. Journal of Computational Information Systems,2012,8(12):4997-5004.
APA	Bu, Fan,Qiu, Yuehong,Liu, Jinxia,&Yan, Xingtao.(2012).Improved bidirectional image registration based on Radon-SIFT.Journal of Computational Information Systems,8(12),4997-5004.
MLA	Bu, Fan,et al."Improved bidirectional image registration based on Radon-SIFT".Journal of Computational Information Systems 8.12(2012):4997-5004.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Improved bidirection（870KB）			限制开放	CC BY-NC-SA	请求全文