DocumentCode :
3778713
Title :
Image matching via higher order structures
Author :
Zhen Zhang;Yanning Zhang;Jinqiu Sun;Li Sun
Author_Institution :
School of Computer Science and Technology, Northwestern Polytechnical University, Xi´an, Shaanxi, China, 710129
fYear :
2015
Firstpage :
105
Lastpage :
108
Abstract :
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.
Keywords :
"Image matching","Belief propagation","Linear programming","Robustness","Transform coding","Image coding","Image resolution"
Publisher :
ieee
Conference_Titel :
Orange Technologies (ICOT), 2015 International Conference on
Type :
conf
DOI :
10.1109/ICOT.2015.7498509
Filename :
7498509
Link To Document :
بازگشت