Image Set Compression Based on Undirected Weighted Graph

With the development of imaging capturing technology, a huge number of pictures have been created. Most of the pictures are of high resolution and large size. Traditional compression schemes like JPEG compress pictures individually. Since many pictures may be taken in the same or similar scene, they can be compressed as an image set to improve the compression ratio. This paper proposes an image set compression scheme based on the undirected weighted graph. We first down sample the Y-component of all images in the image set and use correlation coefficient as the parameter of edge weight function to construct an undirected weighted graph. Then we calculate the Minimum Spanning Tree (MST) of the graph using Kruskal’s algorithm and rearrange the images based on the depth of the leaf vertex and Breadth First Search (BFS). At last, the rearranged images are coded by the latest video coding technique High Efficiency Video Coding (HEVC). Experimental results show that our method performs better than both JPEG and JPEG2000.