RESUMO
The combination of multi-scale transform and the rules which are "high-frequency coefficients combined by selecting the maximum gray value or energy" and "low-pass ones combined by weighting average" is an effective method in dual-band image fusion. However, when these methods are used to fuse multi-band images, sequential weighted average often leads the weakening of the inherent different information of original images, which affects the subsequent target recognition and scene understanding. The problem is more obvious when fusing multi-band images with texture features. In order to describe the scene in a more comprehensive and precise way, a new multi-band texture image fusion method based on embedded multi-scale decomposition and possibility theory is proposed. The method consists of three parts. The original multi-band images are decomposed into their high- and low-frequency components through a multi-scale transform. The high-frequency components are fused per-pixel by extracting the maximum gray value, whereas the last layer of low-frequency components of original multi-band images with the largest standard deviation is blocked through the another multi-scale transform. Based on the specific sizes and positions of these blocks, the remaining two original images are divided. All the blocks from three bands are traversely fused according to the possibility theory, and the low-frequency image is formed by mosaicing these fused blocks. Then, this image is inversely transformed with its high-frequency counterparts to get the final fusion image. This method not only integrates the pixel-level with feature-level fusion methods, but also integrates the space domain with transform domain technologies together, and solves the problem of sawtooth effect on the edge of the target through the different fusion rules with the different sizes of blocks. The validity of the method proposed is proved.
RESUMO
Fusion method of dual color mid-wave infrared images is presented in this paper in order to solve such frequently rising issues as limited contrast ratio improvement and serious marginal area distortion in the fusion of the above two images using multi-scale top-hat decomposition. The detailed procedure is shown as the following: A low-frequency component image and a sequence of support value images of the two subdivision band images of mid-wave infrared are obtained respectively with support value transform. Multi-scale bright and dim information are first extracted from the last layer of low-frequency image using the multi-scale top-hat decomposition method respectively. Then they are fused by selecting the maximum gray of each pixel in two subdivision band images of mid-wave infrared respectively. Following that, the two resulted images are enhanced using the gray-scale normalization and Gaussian filtering and fused with the two low-frequency images to get the low-frequency fusion image. After that, this fusion image is reversely transformed with the support sequence image fused by selecting the maximum gray. The final image is got at last. The result shows that compared with the simple support value transform fusion and the multi-scale top-hat decomposition fusion, the method suggested in this paper successfully increases the contrast ratio by 11.69%, decreases the distortion factor by 63.42%, and increases the local coarseness by 38.12%. All these show that the validity of fusion method proposed has been proved, which indicates that both bright and dim information from low-frequency images can effectively solve the contradiction between improving fused image's contrast ratio and reducing its' distortion after the both are fused and enhanced respectively, and then fused with the two low-frequency images, which provides a new useful method for improving the quality of fused inferred images.
