By Topic

A High-Performance Feature-Matching Method for Image Registration by Combining Spatial and Similarity Information

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Gong-jian Wen ; Nat. Univ. of Defense Technol., Changsha ; Lv, Jin-jian ; Wen-xian Yu

A crucial problem that involves feature-based image registration algorithms is how to reliably establish the correspondence between the features detected in the sensed image and those detected in the reference image. Generally, most existing methods only use spatial relations or feature similarity, or a simple combination of them, to solve this problem, and all have some limitations. In this paper, a new feature-matching strategy is developed. It is realized by introducing a function whose independent variable is the match matrix, which describes the correspondence of the features, to combine spatial relations and organically feature similarity, and its global maximum is assumed to be reached if the sensed image is completely aligned with the reference image. Thus, the feature correspondence can be estimated by finding the maximum of the function. Two approaches are devised to solve the optimization problem. One is based on the branch-and-bound strategy to yield a global optimal solution, and the other uses an iterative algorithm that combines graduated assignment and variable metric methods to search for a local optimal solution with low computational complexity. The proposed method can work without the limitations of feature type, similarity criterion, and transform model, and its performance is evaluated using a variety of real images. Compared with some existing methods, it is fast and robust, and has the highest accuracy.

Published in:

Geoscience and Remote Sensing, IEEE Transactions on  (Volume:46 ,  Issue: 4 )