Fractional derivative filter for image contrast enhancement with order prediction

Fractional derivative based techniques have been proposed for preprocessing of digital images. Although these techniques address the texture enhancement and other issues to a certain extent, none of them have proposed a method of determining the fractional order adaptively. In this paper, we propose a Grunwald-Letnikov derivative based fractional derivative mask for image contrast enhancement. The proposed mask is multidirectional thus enhancing the image in several directions in one pass. The regularisation based prediction network learns from the training set of images and determines the fractional order based on the statistics of the image at hand. Also the blur reduction is achieved in a controlled fashion as the fractional order is predicted according to the desired blur improvement. Experimental results with the comparative blur metric show the effectiveness of the proposed novel filter on a wide range of images.