Method for fusing multi-focus images based on wavelet transform and neighborhood characteristics

The invention relates to a method for fusing multi-focus images based on wavelet transform and neighborhood characteristics, The method comprises the following steps of: firstly, performing multi-scale decomposition on the images by utilizing wavelet transform to acquire low-frequency and high-frequency information of images in different resolution ratios and directions; secondly, processing the low-frequency and the high-frequency information by adopting different fusion rules according to the characteristics of the low-frequency and the high-frequency information, wherein low-frequency subimages are processed by a neighborhood normalization gradient weighted average-based fusion method, so the defect that marginal information is ignored in the conventional low-frequency component fusion method is overcome, and high-frequency subimages are processed by a neighborhood standard deviation weighted average-based fusion method so as to retain detail information of the images furthest; and finally, performing wavelet reconfiguration to obtain the fused images. The method eliminates the phenomenon that marginal distortion exists in the conventional fusion algorithm, improves the quality and definition of the fused images, and can be applied to various military or civil multi-focus image fusion systems.