TY - GEN
T1 - Image matching via higher order structures
AU - Zhang, Zhen
AU - Zhang, Yanning
AU - Sun, Jinqiu
AU - Sun, Li
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2016/6/22
Y1 - 2016/6/22
N2 - Image matching is an important and fundamental problem in computer vision. When human matches two objects in images, not only local feature, (i.e. colour similarity and etc.), but also higher order structures (i.e. shape similarity and etc.) are used. In this paper, a novel higher order score function for image matching is proposed, and then the score function are optimised via efficient belief propagation algorithm. Experiments show that the proposed image matching method are robust to noise, JPEG compression and etc. The proposed algorithm also handles large scale problems that previous algorithms fails to handle.
AB - Image matching is an important and fundamental problem in computer vision. When human matches two objects in images, not only local feature, (i.e. colour similarity and etc.), but also higher order structures (i.e. shape similarity and etc.) are used. In this paper, a novel higher order score function for image matching is proposed, and then the score function are optimised via efficient belief propagation algorithm. Experiments show that the proposed image matching method are robust to noise, JPEG compression and etc. The proposed algorithm also handles large scale problems that previous algorithms fails to handle.
UR - http://www.scopus.com/inward/record.url?scp=84980317599&partnerID=8YFLogxK
U2 - 10.1109/ICOT.2015.7498509
DO - 10.1109/ICOT.2015.7498509
M3 - 会议稿件
AN - SCOPUS:84980317599
T3 - Proceedings of 2015 International Conference on Orange Technologies, ICOT 2015
SP - 105
EP - 108
BT - Proceedings of 2015 International Conference on Orange Technologies, ICOT 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd International Conference on Orange Technologies, ICOT 2015
Y2 - 19 December 2015 through 22 December 2015
ER -