Multi‐focus image fusion algorithm based on multilevel morphological component analysis and support vector machine

Abstract

In this study, a novel algorithm is proposed for multi-focus image fusion based on multilevel morphological decomposition and classifier. The attractive feature of the algorithm is that it decomposes images into several layers with different morphological components, which makes it preserve more detail information of source images. In the algorithm, source images are first decomposed by the multilevel morphological component analysis. Then, feature vectors are extracted from nature layers, and they are classified by a trained two-class support vector machine. Then, consistency verification is employed to verify the decision matrix sets. Finally, coefficients are fused based on the decision matrix sets. Experimental results demonstrate the superiority of the proposed method in terms of subjective and objective evaluation.