Study of Dempster-Shafer theory for image segmentation applications

This paper addresses a new knowledge model using the Dempster-Shafer's theory of evidence for image segmentation and fusion. The salient aspects of the proposed method are at two levels. Firstly, mass distributions in Dempster-Shafer theory are directly derived from image histograms. Secondly, the fusion process does not start from one single frame of discernment, as it was done in most of the previously reported works, but does start from first defining two independent frames of discernment associated with the two images to be fused, and then combining them for forming a new frame of discernment. The strategy used to define mass distributions in the combined framework is discussed in detail. The proposed fusion method is illustrated in the context of image segmentation. The obtained results show the robustness of the method. (C) 2002 Elsevier Science B.V. All rights reserved.