Constrast based color segmentation with adaptive thresholds

Abstract

In this paper, we propose a color segmentation algorithm based on contrast information and adaptive thresholds. Given a color image, instead of the commonly used achromatic difference and chromatic difference, we use achromatic contrast and chromatic contrast to represent the significance of boundary. To fit for human's visual perception, adaptive thresholds are applied to suppress perceptually faint boundaries. A complete segmentation scheme is proposed and the simulation results demonstrate the superiority of this approach in providing reasonable and reliable color segmentation.