A noise-resistant fuzzy Kohonen clustering network algorithm for color image segmentation

Fuzzy Kohonen clustering network(FKCN) is a kind of self-organizing fuzzy neural network, it shows great superiority in processing the ambiguity and uncertainty of image. But FKCN will encounter some difficulties when used for real noisy color images and medical Sublingual vein color images segmentation. To overcome this defect, an improved FKCN algorithm is presented in this paper, which a new measurement of distance, the biologic lateral-inhibition mechanism and an improved cut-set method are used to reduce the effect of noisy pixels.In the end, the improved algorithm will be used for the segmentation of noisy color image and medical Sublingual vein color image. The experiments show that the improved algorithm can segment both noisy color image and medical Sublingual vein color image more effectively and provide more robust segmentation results.