A multi-focus image fusion algorithm using modified adaptive PCNN model

Image fusion is the technology that combines more than one images into an image, to lay the foundation for further image processing tasks. The paper proposed a novel image fusion framework based on improved adaptive PCNN. PCNN is evolved from mammal's visual cortex neuron model, and characterized by its pulse synchronization and acquisition of the neurons. It has been proved that it is very suitable for the field of image processing, and it has been successfully applied in the field of image fusion. The two source images were input into two parallel PCNN networks, and the gray value of the image was used as the external stimuli of PCNN; At the same time, an improved Sum-modified-laplacian was selected as the image focus evaluation fuction, and linking strength of the corresponding neuron of the PCNN was calculated. The ignition map could be obtained after PCNN ignition, and the clearer part of the images were selected to generate the fused image by comparing the ignition map. In the end, the fused image was generated by pixel by pixel window-based consistency verification, and the final fusion result was obtained. Experimental results show that the proposed method is superior to the traditional image fusion methods in terms of subjective and objective evaluation criteria.