Nowadays, skin cancer is one of the unrestrictive spreading diseases. Melanoma skin cancer has the maximum fatality rate in contrast with other variety of cancers. Detection of Melanoma in the initial stages can improve survival rate to a greater extent. The fundamental scrutiny of melanoma is very crucial to take relevant medication. Hence, there is a requirement for automatic skin cancer recognition procedure with high efficiency. The complications of melanoma detection can be handled by the use of excellent Digital image processing algorithms, which are extremely beneficial to clinicians during the disease diagnosis process. The de-noising of an image is a complicated pre-processing task, to preserve minute details in the acquired images which occupy the images during image acquisition in digital image processing applications. The use of a proper de-noising filter allows for the preservation of tiny details in the image, which is beneficial for feature extraction. Especially in the domain of dermoscopic image processing, the better de-noising technique is necessary to maintain the fine details in the image. In general the dermoscopy images are not clear due to improper resolution adjustments and light focusing during image acquisition. Most of the dermoscopic images are diminished by Gaussian type of noise. In this present work, three different types of noise have been added to the acquired image and de-noised by the use of linear filters. The performances of various de-noising filters are evaluated with variables such as Mean-Square-Error (MSE), and Peak-Signal-to-Noise Ratio (PSNR).

Dermoscopic, Image De-Noising, MSE, PSNR