基于SIFT和SURF的医学图像特征匹配
研究

doi:10.3969/j.issn.1674-1633.2016.04.008

摘要
图/表
参考文献
相关文章 (1)

全文: PDF (2995 KB) HTML (39 KB)
输出: BibTeX | EndNote (RIS)

摘要本文采用基于特征点的匹配算法完成对实验医学图像的匹配，从特征点数量、特征提取时间和匹配准确性等方面比较尺度不变特征变换（SIFT）和快速鲁棒特征（SURF）算法，然后采用K最近邻算法（KNN）去除误匹配，统计分析不同阈值的随机抽样一致算法（RANSAC）和最小中值方差估计算法（LMEDS）与配准结果的相关性。本研究建立了基于特征点的医学图像配准算法程序实验平台，实现了多算法融合的医学图像特征匹配，对进一步探讨和改进医学图像配准提供了研究基础。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	鹿煜炜
	胡峻

关键词 ： SIFT, SURF, 图像匹配, K最近邻算法

Abstract：The paper adopted the matching algorithm based on characteristic points to accomplish image matching in experimental medicine. The two algorithms: scale-invariant feature transform (SIFT) and speeded up robust features (SURF) were compared in aspects of characteristic points, characteristic extraction time and matching veracity. Then the K-nearest neighbor (KNN) algorithm was used to eliminate mismatching points. The paper also carried on statistical analysis of the results of random sample consensus (RANSAC) and least median of squres (LMEDS) as well as the correlation between matching veracity and algorithms. This research established a medical image matching platform based on characteristic points in order to provide a research basis for the further research and improvement of medical image matching.

Key words： scale-invariant feature transform speeded up robust features image matching K-nearest neighbor algorithm

收稿日期: 2015-11-11

TN911.23

基金资助:安徽省级质量工程项目（2015sjjd008、2015jyxm191）

通讯作者: 胡峻 E-mail: 70602345@qq.com

作者简介:

引用本文:

鹿煜炜，胡峻. 基于SIFT和SURF的医学图像特征匹配研究[J]. 中国医疗设备, 2016, 31(4): 40-44.
LU Yu-wei, HU Jun. Research on Medical Image Matching Based on SIFT and SURF Features. China Medical Devices, 2016, 31(4): 40-44.

链接本文:

http://cs.china-cmd.org/zgylsb/CN/10.3969/j.issn.1674-1633.2016.04.008 或 http://cs.china-cmd.org/zgylsb/CN/Y2016/V31/I4/40

[1]	Harris C,Stephens M.A combined corner and edge detector[A].
[1]	Harris C,Stephens M.A combined corner and edge detector[A].
[1]	Harris C,Stephens M.A combined corner and edge detector[A].
	Proceding of the Fourth Alvey Vision Conference[C].Manchester,
	Proceding of the Fourth Alvey Vision Conference[C].Manchester,
	UK,1988:147-151.
	Carnegie Mellon University Technical Report CMU-CS-91-132,
	Carnegie Mellon University Technical Report CMU-CS-91-132,
	1991.
	1991.
	1991.
[3]	Smith SM,Brady JM.SUSAN:A new approach to low level image
[3]	Smith SM,Brady JM.SUSAN:A new approach to low level image
	UK,1988:147-151.
	Carnegie Mellon University Technical Report CMU-CS-91-132,
	Proceding of the Fourth Alvey Vision Conference[C].Manchester,
[2]	Tomasi C,Kanade T.Detection and Tracking of Point Features[R].
[3]	Smith SM,Brady JM.SUSAN:A new approach to low level image
	Processing[J].Int J Comput Vis,1997,23(1):45-78.
	Processing[J].Int J Comput Vis,1997,23(1):45-78.
	Processing[J].Int J Comput Vis,1997,23(1):45-78.
[4]	Lowe DG.Object recognition from local scale-invariant features[A].
[4]	Lowe DG.Object recognition from local scale-invariant features[A].
[4]	Lowe DG.Object recognition from local scale-invariant features[A].
	International Conference on Computer Vision[C].Corfu,Greece,
	International Conference on Computer Vision[C].Corfu,Greece,
19	99:1150-1157.
19	99:1150-1157.
	UK,1988:147-151.
[2]	Tomasi C,Kanade T.Detection and Tracking of Point Features[R].
[2]	Tomasi C,Kanade T.Detection and Tracking of Point Features[R].
	International Conference on Computer Vision[C].Corfu,Greece,
19	99:1150-1157.