A two-stage multi-focus image fusion framework robust to image mis-registration

Abstract

Multi-focus image fusion technique is to yield a composite image with all objects in focus. However, most of fusion methods do not obtain the satisfactory performance when the focused objects in the source images are not registered. In this paper, a novel classification and probability optimization based multi-focus image fusion method is proposed, which consists of two main steps. First, by the integration of multinomial logistic regression classifier and random walker based optimization in a two-stage framework, we can extract the focused regions of each source image. Then, in order to construct the fused image, the focused regions are combined together. Experimental results show that compared with other advanced fusion methods, the proposed method can obtain competitive performance in terms of subjective and objective evaluations.