Improving image segmentation using edge information

We report methods for image segmentation that combine region growing and edge detection. Existing schemes that use region-based processing provide unambiguous segmentation, but they often divide regions that are not clearly separated, while merging regions across a break in an otherwise strong edge. Edge-based schemes are subject to noise and global variation in the picture (e.g. illumination), but do reliably identify strong boundaries. Our combined algorithm begins by using region growing to produce an over-segmented image. This phase is fast (order N, where N is the number of pels in the image). We then modify the over-segmented output of the region growing using edge criteria such as edge strength, edge smoothness, edge straightness and edge continuity. Two techniques - line-segment subtraction and line-segment addition - have been investigated. In the subtraction technique, the weakest edge (based on a weighted combination of the criteria) is removed at each step. In addition technique, the strongest edge is used to seed a multi-segment line that grows out from it at both ends. At every junction, the adjoining edge that has the highest edge strength is appended. We have also investigated a form of look-ahead, where the growing of lines depends on the strength of the adjoining edge and those to which it is linked. The overall procedure for both techniques, current results and the areas for improvement and expansion have been discussed in the full paper.