Image fusion based on improved contrast in finite discrete shearlet domain

In order to improve the accuracy of multifocus image fusion, combining with good localization and shift invariance of finite discrete shearlet transform(FDST), a new image fusion algorithm based on FDST and improved contrast was proposed. Firstly, the registration multifocus images were decomposed by FDST, and the low frequency subband coefficients and high frequency subband coefficients of different scales and directions were obtained. The fusion principle of low frequency subband coefficients was based on the method of regional average energy matching degree. As for high frequency subband coefficients,the sum of contrast was adopted as the fusion rule, which combined the lowfrequency coefficients with the high frequency coefficients. Finally，low frequency information and high frequency information were reconstructed to image by finite discrete shearlet inverse transform, and both subjective visual evaluation and objective performance assessments of the fusion results were implemented. Simulation results indicate that the proposed algorithm is obviously superior on subjective visual effects. The values of entropy, mutual information quantity and edge similarity increase averagely by 1.4%,3.4% and 0.8%, respectively, compared with other fusion algorithms. It is superior to other fusion algorithms on objective evaluation.