Image Registration Algorithm Based on Super pixel Segmentation and SURF Feature Points

Abstract

In the current image registration technology, feature points detection and matching feature points have lower accuracy. Based on the analysis of SURF feature point detection and information entropy for image registration, an image registration algorithm based on SURF feature points is proposed. Firstly, the image is divided into super-pixels, and the information entropy of each image area is calculated. The redundant points in feature points are eliminated by using the value of information quantity. The problem that the SURF operator distributes densely is improved and the number of feature points is reduced. Experimental results show that the improved algorithm can improve the accuracy of image feature point pairs, and effectively improve the quality of registration.