Segmentation using Six Sigma Threshold on Spectral Bands of Malignant Melanoma

This paper presents a method for analyzing the variations of the RGB spectrum of lesion skin images using the novel segmentation process based on Six Sigma concept. This analysis further contemplates on the incidence and propagation of cancer. It is based on the underlying principles of Dr. W.A. Shewhart’s Control Charts, which focuses on the fact that the variability does exist in all repetitive processes. The heterogeneous color variation within the skin is considered as an assignable cause and is due to the secretion of excess melanin. These variations possess greater magnitude as compared to the chance causes due to the color variations found in normal skins. The power of control chart that lies in its ability to separate out this assignable cause, which is one of inherent mnemonics of Malignant Melanoma, is exhibited. The proposed Six Sigma based segmentation identifies the normal skin region from the regions of lesions, besides its fuzzy border. Results show that the method produces a robust segmentation of regions of high color contrast.