Skin lesion detection in dermoscopy images using wavelet transform and morphology operations

Dermoscopy is one of the major imaging modalities used in the diagnosis of skin lesions such as melanoma and other pigmented lesions. Due to the difficulty and subjectivity of human interpretation, computerized analysis of dermoscopy images has become an important research area. One of the most important steps in dermoscopy image analysis is the automated detection of lesion borders. In this paper we propose a novel approach for border detection of lesions in dermoscopy images. First, the color input image is converted into a gray-level image. Then, the wavelet coefficients of gray-level image are calculated. The wavelet coefficients are modified using gradient of each wavelet band and a nonlinear function. The enhanced image is obtained from the inverse wavelet transform of modified coefficients. Morphology operators are used to segment the image, and finally the lesion is detected by an automated algorithm. The results show that the proposed method has a low percentage border error in a vast majority of skin lesions compared recent methods.