30 October 2009 A novel feature matching algorithm based on shape-context between optical and infrared image
Author Affiliations +
Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 74953C (2009) https://doi.org/10.1117/12.832973
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China
Abstract
Different-source image matching is still a difficult problem in computer vision. In this paper, we propose a novel algorithm based on edge information, shape context descriptor and graph matching to make a good performance in the different-source image matching field, especially optical and infrared image. First, as the edge information is a relatively stable in these two kinds of images, we detect the feature point based on the edge information which can reflect the construction information. Then shape context descriptor, which is rotation invariant, scale invariant and translation invariant, is adapted to describe the feature point. Finally, the graph matching algorithm is used for the image matching to eliminate the false matching point. From experimental results, our algorithm is efficient in different-source image matching.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zenglu Wan, Zheng Li, Jianliang Weng, Hongxia Gao, "A novel feature matching algorithm based on shape-context between optical and infrared image", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74953C (30 October 2009); doi: 10.1117/12.832973; https://doi.org/10.1117/12.832973
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT


Back to Top