Research Of Multi Focus Image Fusion Algorithm Based On PCNN Model

Due to the limited focus area of the optical lens and the digital imaging device,it is difficult to get clear image for all objects in the same scene.In life,people often want to take a full focus of the photos,in order to get a clear image,multi-focus image fusion technology has been widely used in the field of computer vision.In general,multi-focus image fusion may be from three levels:pixel-level,feature-level and decision level.In this paper,two kinds of effective image fusion algorithms based on pixel level are proposed.Aiming at the problem that the image fusion algorithm will often ignore the local pixel correlation,we present an intelligent fusion method using Laplace pyramid(LP)and pulse coupled neural network(PCNN).First,using Laplace pyramid to do multi-scale decomposition of the image,and the decomposition images are processed by PCNN to obtain the neuron firing frequency graph which describes the feature clustering.Then he paper calculates local sum of modified Laplacian(SML)for every pixel's ignition frequency map,and takes local SML as a measure of the quality of the pixels for the source image fusion.Finally,the fused image is obtained by inverse Laplace pyramid transform.The experimental results show that the method has a good effect on the extraction of the main energy and detail information of the image.The traditional pulse-coupled neural networks often cannot achieve optimum efficiency in image fusion because of parameter-setting problems of the PCNN model.To overcome the problem of PCNN parameter-setting,a novel technique that uses PCNN model parameters of multi-objective particle swarm optimization(PSO)is presented.The method consists of three steps.First,the PCNN model parameters are optimized using multi-objective PSO,and the optimal PCNN model is obtained.Then,the paper uses dual-tree complex wavelet transform(DTCWT)for multi-scale decomposition of source images.High-frequency image components are processed by the optimal PCNN model while low-frequency image components are fused by SML.Finally,the fused image is reconstructed based on inverse DTCWT.Experimental results indicate that proposed method has good results both in subjective and objective indexes.