Coal micrograph segmentation based On visual clustering

Abstract

In order to distinguish different components of macerals from coal micrograph, a visual clustering algorithm that is inspired from visual psychology is proposed. It mimics the mechanism of the human visual system. There are two procedures: the hierarchical feature extraction mechanism dominated by receptive field functions and the feature integration principle characterized by Gestalt law in psychology. Experimental results show that the proposed algorithm performs well for the coal micrograph segmentation compared with other methods.