Circular histogram thresholding for color image segmentation

Abstract

A circular histogram thresholding for color image segmentation is proposed. A circular hue histogram is first constructed based on a UCS (I,H,S) color space. The histogram is automatically smoothed by a scale-space filter, then transformed into traditional histogram form, and finally recursively thresholded based on the maximum principle of variance. Three comparisons of performance are reported: (i) the proposed thresholding on the circular histogram with that on a traditional histogram; (ii) the proposed thresholding with clustering; and (iii) thresholding based on a UCS hue attribute with that based on a non-UCS hue attribute. Benefits of the proposed approach are confirmed in experiments.