Robust template matching algorithm with multi-feature using best-buddies similarity

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 光电信息技术研究室

	Robust template matching algorithm with multi-feature using best-buddies similarity
	Jiang SP(江苏蓬)1,2,3,4,5; Xiang W(向伟)1,2,4,5; Liu YP(刘云鹏)1,2,4,5
	2019
会议日期	August 28-30, 2019
会议地点	Shenyang, China
关键词	Template Matching Best-Buddies Similarity HOG Feature Confidence Map
页码	1-6
英文摘要	In order to solve the problem of matching failure of BBS (Best-Buddies Similarity) algorithm when the target image has a partial occlusion, cluttered background, imbalance illumination, and nonrigid deformation. A multi-feature template matching algorithm based on the BBS algorithm is proposed in this paper. On the basis of the location features and appearance features, we add HOG (Histogram of Oriented Gradients) features to make full use of the color, position and structural contour of the target image to match. In addition, we also perform mean filtering on the confidence map. The experimental results show that the AUC (Area Under Curve) score of the proposed algorithm is 0.6119, which is 6.38% higher than the BBS algorithm. Moreover, our algorithm has stronger robustness and higher matching accuracy.
源文献作者	Chinese Society for Optical Engineering
产权排序	1
会议录	Second Target Recognition and Artificial Intelligence Summit Forum
会议录出版者	SPIE
会议录出版地	Bellingham, USA
语种	英语
ISSN号	0277-786X
ISBN号	978-1-5106-3631-6
WOS记录号	WOS:000546230500067
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/26417]
专题	沈阳自动化研究所_光电信息技术研究室
通讯作者	Jiang SP(江苏蓬)
作者单位	1.Key Lab of Image Understanding and Computer Vision, Shenyang, China 2.Key Laboratory of Opto-Electronic Information Processing, CAS, Shenyang, China 3.University of Chinese Academy of Sciences, Beijing, China 4.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China 5.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
推荐引用方式 GB/T 7714	Jiang SP,Xiang W,Liu YP. Robust template matching algorithm with multi-feature using best-buddies similarity[C]. 见:. Shenyang, China. August 28-30, 2019.