Artificial Bee Colony Algorithm based Multifocus Image Fusion in NSCT Domain

Taking full use of the features of NonsubSampled Contourlet Transform(NSCT) in directionality, anisotropism and translational invariance, this paper proposes an Artificial Bee Colony(ABC) algorithm based method on image fusion which may provides with an optimal over-all property. First, this method selects several objective evaluation standards of image fusion and constructs an index to compute the over-all property of fused image. Second, after the original image is decomposed by NSCT, we obtain the coefficients of low-frequency and high-frequency in NSCT domain. And then, according to the features of NSCT and regional energies, we introduce the swarm intelligence of ABC to determine the proportion of high frequency coefficients, i.e. the optimal weights. Finally, we use the high-frequency coefficients fused by the optimal weights and the average of low-frequency coefficients to reconstruct the best fused image. Experimental results show that the method is superior to several fusion methods like principal component analysis, pyramid decomposition method and wavelet transform based method.