Examination of Skin Cancer Images using Wavelet De-noising

Abstract

The objective of this paper is de-noising of melanoma images using wavelets because, dermatoscopy images are corrupted by noise, which leads to fault diagnosis. Hence de-noising is essential in melanoma skin cancer image to remove the salt and pepper noise(impulse noise) by preserving the melanoma image original information. The wavelet thresholding techniques are used in this paper to de-noise the melanoma image and improved the quality of an image. Wavelet de-noising algorithm has been developed employing soft and hard thresholding techniques. It works on Daubechies, Symlet, biorthogonal wavelets at decomposition level5. Image objective performance metrics like peak signal to noise ratio, mean square error and statistical performance metrics like mean, median, standard deviation, L1 norm, L2 norm are observed and analyzed for melanoma images