Image Enhancement Using Non-Linear Root-Signal and Guided Filtering Approach

In this paper, a new method of image enhancement using image fusion algorithm is proposed which is based on deriving multiple root-signals from the given input image and enhancing each of them individually. In order to obtain a single enhanced image, these multiple enhanced images are fused. The overall system for the proposed methodology turns out to be a nonlinear system. The various enhanced images using root-signal approach are further passed through the guided filter for the improvement of the quality of the enhancement results. The proposed approach has been evaluated on number of images and results are compared with existing enhancement methods such as histogram equalization (HE) and adaptive histogram equalization (AHE). The efficacy of the proposed approach is evaluated using several quality metrics and it is observed that, compared to some of the existing techniques, it improves the quality of the enhanced images.