Fast algorithm for multisource image registration based on geometric feature of corners

  • Authors:

  • Shaohua Jiang;Cheng Wang;Xuejun Xu;Wensheng Tang;Hongbo Zhu;Xuesong Chen

  • Affiliations:

  • Digital Engineering and Simulation Center, Huazhong University of Science and Technology, Wuhan, China and Institute of Image Recognition & Computer Vision, Hunan Normal University, Changsha, ...;Digital Engineering and Simulation Center, Huazhong University of Science and Technology, Wuhan, China;Digital Engineering and Simulation Center, Huazhong University of Science and Technology, Wuhan, China;Institute of Image Recognition & Computer Vision, Hunan Normal University, Changsha, China;Digital Engineering and Simulation Center, Huazhong University of Science and Technology, Wuhan, China;Digital Engineering and Simulation Center, Huazhong University of Science and Technology, Wuhan, China

  • Venue:
  • ICIC'10 Proceedings of the 6th international conference on Advanced intelligent computing theories and applications: intelligent computing
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Due to the different imaging characteristics of sensor, there are big differences of multisource images in gray and trend of gray gradient. And the existing algorithms of image registration were time-consuming or low matching. In view of the status quo, a brief review of the SIFT algorithm is firstly given, and the shortcoming of SIFT, in which the matching rate is vulnerable to influence by gray feature, is pointed out. Then a fast algorithm for multisource image registration based on geometric feature of corners was presented. It adopts geometric feature of corners rather than gray feature. So the shortcoming of SIFT can be overcome. The novel algorithm can be used to register multisource images with large differences in gray or with different wavebands, and can increase the speed and raise the matching rate of registration. This section focused on how to select the corners, how to calculate feature vectors, and the feature matching algorithm. Finally, experiments have been done to prove that this algorithm can register images quickly and efficiently.