Image segmentation using multi-scan Constraint Satisfaction Neural Network

A novel image segmentation method based on Constraint Satisfaction Neural Network (CSNN) and applied to color images is presented. The new method uses CSNN based relaxation but with a modified scanning scheme of the image. The pixels are scanned with graduated sparse intervals but with wide neighborhoods in the first level of the algorithm. The intervals between pixels are reduced as well as neighborhood of pixels. This method contributes to the formation more regular segments rapidly and consistently. A cluster validity index to determine the number of segments is also added to complete the proposed method into a fully automatic unsupervised segmentation scheme.