Modification on distance transform to avoid over-segmentation and under-segmentation

Abstract

Many techniques, both conventional and morphological, have been proposed in the literature for the segmentation of images. Morphological image segmentation methods, particularly those using a watershed algorithm, have found wide applications. The popular method of F. Meyer and S. Beucher (see J. Visual Comm. Image Representation., vol.1, p.21-46, 1990), based on a marker constrained watershed algorithm which uses only the binary image and its distance transform, can lead to over-segmentation or under-segmentation if the image objects are of irregular shape and they are overlapping or touching. Another problem with the Beucher and Meyer method is that the watersheds constructed may not agree/coincide with the actual image object junctions as only the binary image is used and information contained in the gray scale image is not utilised. We present an approach addressing both these problems. Morphological area-opening on the distance transform is used for choosing markers to avoid over-segmentation and under-segmentation. The second problem is addressed by using a gray scale image instead of a distance transform to force the watersheds to coincide with the actual junctions of the image objects. The proposed procedure has been applied to images with almost similar objects and the results of our procedure of segmentation are found to be very efficient and encouraging.