Research On Key Techniques For Multi-scale Decomposition Based Pixel Level Image Fusion

Image fusion is an important part of image processing,and can make use of multi-sensor image information of the same scene,to output a fused image that is more suitable for human visual perception or for further image processing and analysis.It can obviously improve the shortage of single sensor,the clarity of the result image and the content of the package,thus helps obtain the information of the target or scene more accurately,more reliability and more comprehensively.Image fusion can be performed at three different levels,i.e.,pixel level,feature level,and decision level.Compared with others,pixel-level image fusion directly combines the original information in the source images,which aims at synthesizing a fused image that is more informative for visual perception and computer processing.Due to this advantage,pixel-level image fusion has shown notable achievements in photography,medical imaging,and video surveillance applications.In this paper,we make studies about the problems of multi-scale decomposition methods in the pixel-level image fusion,and put forward the improved method.The main innovations include the following aspects:1.We propose a novel multi-focus image fusion technique,which is developed by using the nonsubsampled contourlet transform(NSCT)and a proposed fuzzy logic based adaptive pulse-coupled neural network(PCNN)model.In our method,sum modified-Laplacian(SML)is calculated as the motivation for PCNN neurons in NSCT domain.Since the linking strength plays an important role in PCNN,we propose an adaptively fuzzy way to determine it by computing each coefficient's importance relative to the surrounding coefficients.Combined with human visual perception characteristics,the fuzzy membership value is employed to automatically achieve the degree of importance of each coefficient,which is utilized as the linking strength in PCNN model.Experimental results on simulated and real multi-focus images show that the proposed technique has a superior performance to series of exist fusion methods.2.We presents a novel multimodal medical image fusion method that adopts a multiscale geometric analysis of the NSCT with type-2 fuzzy logic techniques.First,the NSCT is performed on pre-registered source images to obtain their high-and low-frequency subbands.Next,an effective type-2 fuzzy logic based fused rule is proposed for fusion of the high-frequency subbands.In the presented fusion approach,the local type-2 fuzzy entropy is introduced to automatically select high-frequency coefficients.However,for the low-frequency subbands,they were fused by a local energy(LE)algorithm based on the corresponding image's local features.Finally,the fused image was constructed by the inverse NSCT with all composite subbands.Both subjective and objective evaluations show better contrast,accuracy,and versatility in the proposed approach compared with state-of-the-art methods.Besides,an effective color medical image fusion scheme is also given in the paper that can inhibit color distortion to a large extent and can produce an improved visual effect.3.We propose a novel multisensor image fusion method based on multiple visual features measurement with gradient domain guided filtering.Firstly,a Gaussian smoothing filter is employed to decompose each source image into two components: approximate component formed by homogeneous regions and detail component with sharp edges.Secondly,an effective decision map construction model is presented by measuring three key visual features of the input sensor image: contrast saliency,sharpness and structure saliency.Third,a gradient domain guided filtering based decision map optimization technique is proposed to make full use of spatial consistency and generate weight maps.Finally,the resultant image is fused with the weight maps and then is experimentally verified through multifocus image,multimodal medical image and infrared-visible image fusion.The experimental results demonstrate that the proposed method can achieve better performance than state-of-the-art methods in terms of subjective visual effect and objective evaluation.