Research on multi focus image fusion technology based on four branch tree decomposition and RPCA

Abstract

The purpose of multi-focus image fusion is integrating the partially focused images into one single All-in-focus image, which is focused everywhere. A new quadtree decomposition and robust principal component analysis(RPCA) algorithm for space domain multi-focus image fusion are proposed. Fristly, according to the proposed decomposition strategy, the source images are decomposed into blocks with optimal sizes in a quadtree structure. Meanwhile, robust principal component analysis algorithm is used to detect the focus region, and the result of the detecting would be regarded as the condition for stop decomposition. Finally, the focused regions could be well extracted from the source images and reconstructed to produce one fully focused image. The algorithm proposed in this paper take full advantages of the quadtree and RPCA. Experimental results show that the proposed method can not only obtain good visual effect, but also improve its objective evaluation criteria.