Some of the material in is restricted to members of the community. By logging in, you may be able to gain additional access to certain collections or items. If you have questions about access or logging in, please use the form on the Contact Page.
Image segmentation is one of the most important categories of image processing. The purpose of image segmentation is to divide an original image into homogeneous regions. It can be applied as a pre-processing stage for other image processing methods. There exist several approaches for image segmentation methods for image processing. The watersheds transformation is studied in this thesis as a particular method of a region-based approach to the segmentation of an image. The complete transformation incorporates a pre-processing and post-processing stage that deals with embedded problems such as edge ambiguity and the output of a large number of regions. Multiscale Morphological Gradient (MMG) and Region Adjacency Graph (RAG) are two methods that are pre-processing and post-processing stages, respectively. RAG incorporates dissimilarity criteria to merge adjacent homogeneous regions. In this thesis, the proposed system has been applied to a set of co-aligned images, which include a pair of intensity and range images. It is expected that the hidden edges within the intensity image can be detected by observing range data or vice versa. Also it is expected that the contribution of the range image in region merging can compensate for the dominance of shadows within the intensity image regardless of the original intensity of the object.