An Image Fusion Approach Based on Segmentation Region Using Ant Colony Optimization

An Image fusion method based on segmentation region is proposed in this paper. First, the source images are decomposed by wavelet to get the approximate and detailed subimages,and the segmentation for these sub images are used to get the regions of each level, these regions are used to guide fusion process.A new image segmentation algorithm based on Markov Random Field (MRF) and Ant Colony Optimization (ACO) is presented.Information positive feedback and heuristic search, the characters of ACS, were applied for the image segmentations with MRF model.The activity level and match degree measure of the wave-let coefficients of source images are carried out in these regions, and the maxi-mum value rule and the weighted average rule are respectively used to combine the coefficients of detailed sub-images and approximate sub-image. At last, the combinations Coefficients are inversely transformed by wavelet to get the final fusion image. The experimental results show that the fusion effect is better.