A Novel Color Reduction Based Image Segmentation Technique For Detection Of Cancerous Region in Breast Thermograms

Segmentation of an image into its components plays an important role in most of the image processing applications. In this article an important application of image processing in determination of Breast Cancer is studied, and A Novel Image Segmentation Technique is proposed in order to determine Cancer in Breast Thermograms. First, this image is converted from RGB to color space HSV. Then Cancer shape is extracted by ACM algorithm. Finally, the image has segmented using Color Reduction Based algo-rithm. Experimental results on the acquired images show Accuracy of the proposed algorithm on the acquired images is over 90% for healthy pix-els and defected ones

کلیدواژه ها:

Image Segmentation ، Breast Cancer ، Color Space ، Breast Thermograms ، Active Counter Model ، Self Organized Map ، Neural Networks