Non-subsampled shearlet transform-based image fusion using modified weighted saliency and local difference

Abstract

Existing image fusion methods can not efficiently capture significant edges, texture and fine details of the source images due to inefficient fusion framework. In addition, for objective evaluation of fusion algorithms, not much attention is given to simultaneously measure both texture and structural information of the source images which are preserved in the fused image. To address these issues, non-subsampled shearlet transform (NSST) is used to decompose pre-registered source images into low- and high-frequency components. These low- and high-frequency coefficients are fused by using our proposed modified weighted salience and local difference fusion rules, respectively. To enrich edge information in the fused image, Canny edge detector with scale multiplication is employed. Moreover, a metric QTS is proposed to jointly measure both texture and structural information present in the fused image. The proposed metric is formulated on the basis of local standard deviation filtering, local information entropy, and local difference filtering. Both subjective and objective results validate the proposed fusion framework and the metric QTS.