Skip to Main Content
The luminance components of the input color images are firstly processed with nonsubsampled Contourlet transform (NSCT). The decision map is attained by fusing the high frequency coefficients through the scheme of Synthesis Image Absolute Value Select Maximum (SI-AVSM). Then the decision map is verified by consistency verification and is used to select the R, G, B components simultaneously. Experience results show that the proposed algorithm avoids color distortion caused by fusion algorithms in RGB space model. The fused image, which not only retains the important information existing in the input color images, but also improves the detail expression, are more adaptive to vision of human beings.