The Algorithm Research Of Image Fusion Based On Wavelet And Contourlet Transforms

As one of the important aspects of the multi-sensor information fusion,the image fusion technique is how to use different images from different sensors, through some algorithm, to obtain a more accurate and abundant new image, then we can gain more exact,complete and reliable description and decision-making. It has been widely used in many fields such as military application, computer vision, remote sensing, robot engineering, medical imaging, etc.The image fusion algorithm has three fusion levels: pixel-level, feature-level and decision-level. Pixel-level fusion which is the base of feature-level and decision-level is the elementary level, and is the main contents of this thesis. This dissertation mainly discusses the multi-resolution image fusion algorithms in pixel-level.The main contributions of this dissertation are summarized as follows:1. In order to solve the problem of directional finiteness in wavelet transform, and reduce the redundancy of Laplacian pyramid decomposing in contourlet transform. A regional gradient selection mean image fusion algorithm is proposed with the wavelet-based contourlet transform(WBCT). This algorithm employs weighted mean rule to low frequence, calculates the regional gradient and employs selection average rule to high frequence. Evaluation of the experimental results according to objective criteria including spatial frequence, cross entropy and deviation, it is demonstrated that fusion algorithm based on WBCT is better than the one based on wavelet transform, contourlet transform with the same fusion rule.2. Because the preview of optical lens is limited,it is difficult to get a image that all its scenery is clear in actual camera. A multifocus image fusion algorithm based on WBCT is proposed in this dissertation. The source images are first decomposed by WBCT. Then the clarity measure of each pixel is calculated according to the decomposition coefficients. Fused image is obtained by reconstructing all the clearest pixels in the source images. Experiments show that the proposed algorithm works well in multifocus image fusion.