Abstract
In this paper we propose a novel image contrast enhancement method using collaborative learning. Block-based histogram equalization methods such as contrast limited adaptive histogram equalization (CLAHE) and exact histogram equalization consider only a local window or neighboring windows for contrast enhancement. Inspired by the collaborative learning of individuals in a knowledge-creating community, we propose using random spatial sampling on the image to create multiple individuals, followed by normalization of the entire image according to the perspectives of these individuals. Our method not only increases the range of intensities for the entire image, but also enhances details of relatively homogeneous regions. Experiments demonstrate very good results.