An All Approach for Multi-Focus Image Fusion Using Neural Network

'Image Fusion' is the Information from multiple images which are combined to generate the new image, the generated image is more suitable for humans and machines for further image-processing tasks like image segmentation, edge detection, stereo matching, enhancement, extraction and recognition. Novel feature-level multi-focus image fusion technique is proposed in this paper, which fuses multi-focus images using classification. In this technique, Multi-focus images of ten pairs are divided into blocks and the most favourable block size for each image is found in an adaptive manner. The resultant block feature vectors are fed to feed towards neural network. The neural networks are trained in such a way that, the trained neural networks are used to fuse any pair of multi-focus images. The Proposed and Implemented technique used in this paper is more efficient and useful;to highlight the efficiency we have performed broad experimentation on this technique.