Image segmentation based on Iterative Self-Organizing Data clustering threshold of PCNN

Tn order to solve the problem of PCNN with improper parameter selection and determination of circulation iterations which leads to the image owe-segmentation or over-segmentation, an Iterative Self-organizing Data Clustering (ISODC) model is used in this paper to resolve the problems of the PCNN parameters selection and requiring multiple circulation. By using ISODC clustering search decision-making ability, the best threshold value is obtained. ISODC can solve the dilemma that PCNN needs to determine appropriate model parameters and circulation iterations. ISODC-PCNN makes use of the grey level of the image to cluster, and then uses the improved ISODATA to determine the initial number and the center of clustering which can be used as the optimal threshold value of PCNN. Therefore ISODC-PCNN can automatically segment an image with one time of iteration. Experimental results show that the proposed method improves the segmentation speed and achieves good segmentation results.