Multi-level Thresholding Algorithm for Color Image Segmentation

In this paper, we present an effective multilevel threshold selection method of color image segmentation based on minimum class variance thresholding (MCVT) and OTSU method. The input RGB color image is segmented into regions and proceeds to the region merge using JND (Just Noticeable Difference) of human visual property. The result shows that with simple yet very effective JND merge criteria, the proposed algorithm is capable of generating region representations. After analyzing these two results, Otsu method is better than MCVT method.