Image contrast enhancement based on laplacian-of-gaussian filter combined with morphological reconstruction

Abstract

In the paper, a method of contrast enhancement is presented. It combines linear and non-linear techniques. A non-linear approach based on morphological reconstruction is applied to select essential regions on the of Laplacian-of-Gaussian (LoG) of the input. The morphologically modified result of LoG is next added to the initial image. Thanks to the morphological processing, only the meaningful region boundaries are used to enhance the image contrast. The usage of morphological processing allows for selecting more precisely the image regions that are subject to contrast enhancement. The method performs well on textured images, allowing for adjusting the level of visible details in the output image while increasing the sharpness of meaningful image regions. A couple of examples illustrates the performance of the proposed method.