Research And Application Of Non-subsampled Shearlet Transform In Image Fusion

Image fusion is a technique to combine information from multiple images of the same scene. Multiple source images from various sensors can provide either redundant or complementary information. It is possible to utilize the complementary and redundant information to improve the signal-to-noise ratio (SNR) and obtain a composite image with more detailed and texture information. With the use of multiple sensors.the fused image contains a more complete and accurate description of the scene than any of the individual source images. Shearlet transform and non-subsampled Shearlet transform are applied to image fusion in order to work on new image fusion algorithms in this dissertation.First of all, the multi-focus image fusion algorithm based on Non-subsampled Shearlet transform(NSST) and Fractional Fourier Transform(FRFT) is studied in this dissertation. According to the imaging characteristics of multi-focus images and the advantages of two transform, the fusion rule of weighting by regional sum-modified-Lap lac ian value is applied to fuse the tow frequency coefficients and the fusion rule of choosing max in combine decomposition is applied to fuse the high frequency coefficients of Shearlet domain. Experimental results demonstrate that the proposed fusion algorithm can both obtain good visual effect and highly objective evaluation criteria.Secondly, the multi-focus image fusion algorithm based on Non-sample Shearlet transform and guided filtering is studied in this dissertation. A image fusion framework based on guided filtering is proposed, and the role of guided filtering in image fusion is discussed. Experiments results show that this algorithm can fuse the multi-focus better and obtain the highly objective evaluation criteria.Finally, the application on infrared and visible image fusion and medical image fusion algorithm based on non-subsampled Shearlet transform is studied in the dissertation. The regional segmentation algorithm is applied to the process of image fusion, which is regarded as objective evaluation criteria. Experimental results show that visual effect and objective evaluation index of the fused image by the proposed algorithm have been improved.