Edge based region growing
Sophie Liu Xiao Fan, Zhihong Man, Rashi Samur · 2004
Quite often, in grey level image segmentation, the objects to be delineated are found in regions of non-uniform illumination. In these cases, using thresholds derived from intensity-based algorithms cannot yield good segmentation performance. Region growing techniques have been shown to perform well under these situations. In this paper, a novel edge based region growing method is presented. Two kinds of seeds (pixels) - hot and cold, are defined near edges (of objects) and both kinds of regions are grown from these seeds simultaneously. In this paper, the approach is not sensitive to the parameters, for example the sizes of different operators and the thresholds in edge detection and edge region detection. This technique produces good segmentation results, even for cases of images with non-uniform illumination.