Color Image Segmentation using Optimal Separators of a Histogram

J. Delon, A. Desolneux (France), J.L. Lisani, and A.B. Petro (Spain)


Image manipulation, color, segmentation, histogram thresholding, gestalt theory.


In this paper, a new method for the segmentation of color images is presented. This method searches the optimal se parators in a histogram, according to the Helmholtz prin ciple and the Gestalt theory. The algorithm is parameter free and it uses recursivity to locate all the modes in the histogram. Its main advantage is that it is able to obtain just the optimal modes, avoiding the problems of over segmentation and under-segmentation. The algorithm is a pplied on the hue, saturation and intensity histograms of the image. As a result, an optimal and accurately seg mented image is obtained. In contrast to previous state of-the-art methods, the suggested approach uses only the image's color histogram to perform segmentation without using spatial information.

Important Links:

Go Back