Integrating region growing and edge detection

I Abstract-We present a method that combines region growing and edge detection for image segmentation. We start with a split-and-merge algorithm [12] where the parameters have been set up so that an oversegmented image results. Then region boundaries are eliminated or modified on the basis of criteria that integrate contrast with boundary smoothness, variation of the image gradient along the boundary, and a criterion that penalizes for the presence of artifacts reflecting the data structure used during segmentation (quad tree in our case).