A Improved Infrared and Visible Images Matching Based on SURF

Abstract

Images matching is the basis of image registration. For their difference, a improved SURF(speeded up robust features) algorithm was proposed for the infrared and visible images matching. Firstly, edges were extracted from the images to improve the similarity of infrared and visible images. Then SURF algorithm was used to detect interest points, and the dimension of the point descriptor was 64. Finally, found the matching points by Euclidean distance. Experimental results show that some invalid data points were eliminated.

Registration of infrared and visible images based on the correlation of the edges

“…7 show two groups of original images. Compared to reference [5], the simulation results of the first group using algorithm in this paper are as follows： Fig. 6 shows the output of registration with algorithm in this paper.…”

“…By extracting the points from the edges of both images and using a criterion combined the shape, grayscale and gradient angles together to determine the corresponding points in two images. LI D M [5] proposed an algorithm combined an improved SURF and Canny edge detection algorithm to register infrared and visible image. Considering the correlation of the edges in infrared and visible images, this paper applies the wavelet transform modulus maximum algorithm to edge detection and uses SURF algorithm to detect feature points on edges.…”