Color Image Stitching Using Scale Invariant Feature Transform with 2-Dimensional Entropy Segmentation
Mu Zhou, Mingchun Wang, Zengshan Tian · 2015
This paper proposes a novel color image stitching approach by using the two-dimensional (2-D) maximum entropy threshold segmentation based Scale Invariant Feature Transform (SIFT). First of all, we conduct image segmentation based on the gray level of each pixel and the average gray level of its adjacent pixels. Second, we rely on the key points obtained from the extreme points in different scale spaces of SIFT to stitch the color images. The experimental results show that the proposed image stitching approach significantly increases the number of matching points of the images for image stitching.