Title :
A New Image Registration Algorithm Based on Mutual Information of Gradient and Improved PSO
Author :
Laiming Xu ; Jun Liu
Author_Institution :
Coll. of Inf. Eng., Nanchang Hangkong Univ., Nanchang, China
Abstract :
Because of the larger difference between the two images to be registered, such as exposure degree or noise pollution, the common registration algorithm that based on mutual information of original gray, is easy to fall into local extreme value, thus the registration accuracy is unsatisfactory. In this case, a new method of image registration algorithm that based on mutual information of gradient and improved PSO is developed in this paper. The experiment result shows the method works well, and comparing with traditional registration algorithm, the registration accuracy is significantly improved while the efficiency is also guaranteed.
Keywords :
gradient methods; image registration; particle swarm optimisation; exposure degree; image registration algorithm; improved PSO; local extreme value; mutual gradient information; noise pollution; original gray; Accuracy; Biomedical imaging; Image registration; Mutual information; Noise; Optimization; Pollution measurement; image registration; mutual information of gradient; optimization algorithm;
Conference_Titel :
Intelligent System Design and Engineering Application (ISDEA), 2012 Second International Conference on
Conference_Location :
Sanya, Hainan
Print_ISBN :
978-1-4577-2120-5
DOI :
10.1109/ISdea.2012.389