Optimization of SIFT algorithm for fast-image feature extraction in line-scanning ophthalmoscope

doi:10.1016/j.ijleo.2017.09.075

CORC > 光电技术研究所 > 中国科学院光电技术研究所 > 自适应光学技术研究室（八室）

	Optimization of SIFT algorithm for fast-image feature extraction in line-scanning ophthalmoscope
	He, Yi 1,2; Deng, Guohua 4; Wang, Yuanyuan 1,2,3; Wei, Ling 1,2; Yang, Jinsheng 1,2; Li, Xiqi 1,2; Zhang, Yudong 1,2
刊名	OPTIK
	2018
卷号	152 页码:21-28
关键词	Confocal microscopy Retina scanning Medical and biological imaging Feature extraction Image matching SIFT
ISSN号	0030-4026
DOI	10.1016/j.ijleo.2017.09.075
文献子类	J
英文摘要	The Scale Invariant Feature Transform (SIFT) algorithm is utilized broadly in image registration to improve image qualities. However, the algorithm's complexity reduces its efficiency in biology study and usually requires real-time. In this article, we present an improved SIFT technique in software architecture for matching sequences of images taken from a line-scanning ophthalmoscope (LSO). The method generates the Gaussian Scale-space pyramid in frequency domain to complete the SIFT feature detector more quickly. A novel SIFT descriptor invariable with rotation and illumination is then created to reduce calculation time, implementing the original SIFT method, our improved SIFT method, and the graphic processing unit (GPU) version of our improved SIFT method. The experiments have shown that the improved SIFT is almost 2-3 times faster than the original while maintaining more robust performance, and the GPU implementation of the improved SIFT is 20 times faster than central processing unit (CPU) implementation and achieves acceleration at real-time as expected. Although tested on an LSO system, the improved SIFT method does not rely on the acquisition setup. As a result, this method can be applied to other imaging instruments, e.g., adaptive optics to increase their resolution in agreement. (C) 2017 Elsevier GmbH. All rights reserved.
WOS关键词	MOTION CORRECTION ; HIGH-SPEED ; REGISTRATION
语种	英语
WOS记录号	WOS:000418624500004
内容类型	期刊论文
源URL	[http://ir.ioe.ac.cn/handle/181551/9350]
专题	光电技术研究所_自适应光学技术研究室（八室）
作者单位	1.The Key Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu; 610209, China; 2.Institute of Optics and Electronic, Chinese Academy of Sciences, Chengdu; 610209, China; 3.School of Optometry and Ophthalmology and Eye Hospital, Wenzhou Medical College, Wenzhou; 325035, China; 4.Department of Ophthalmology, The Third People's Hospital of Changzhou, Jiangsu, China
推荐引用方式 GB/T 7714	He, Yi,Deng, Guohua,Wang, Yuanyuan,et al. Optimization of SIFT algorithm for fast-image feature extraction in line-scanning ophthalmoscope[J]. OPTIK,2018,152:21-28.
APA	He, Yi.,Deng, Guohua.,Wang, Yuanyuan.,Wei, Ling.,Yang, Jinsheng.,...&Zhang, Yudong.(2018).Optimization of SIFT algorithm for fast-image feature extraction in line-scanning ophthalmoscope.OPTIK,152,21-28.
MLA	He, Yi,et al."Optimization of SIFT algorithm for fast-image feature extraction in line-scanning ophthalmoscope".OPTIK 152(2018):21-28.