Melanoma is the deadliest form of skin cancer and is on rise. Prescreening of suspicious moles and lesions for malignancy is of great importance. Detection can be done through images captured by standard cameras, which are preferable due to low cost and availability. Analysis of these images is usually challenging due to existence of disturbing factors such as illumination variations, light reflections from skin surface, less detailed information and presence of skin artifacts. One important stage in diagnosis of melanoma is segmentation of lesion region from normal skin. In this thesis, firstly a method for accurate extraction of lesion region is proposed that is based on deep learning approaches. The input image, after being preprocessed to reduce noisy artifacts, is applied to a deep convolutional neural network (CNN). The CNN combines local and global contextual information and outputs a label for each pixel, producing a segmentation mask that shows the lesion region. This mask will be further refined by some post processing operations. The experimental results show that our proposed method can outperform the existing state-of-the-art algorithms in terms of segmentation accuracy. In addition, in this thesis we propose an efficient system for prescreening of pigmented skin lesions for malignancy using general-purpose digital cameras. The proposed method enhances the lesion’s border using guided filtering and extracts a broad set of dermatologically important features. A set of fifteen features is formed which cover different color and shape characteristics of melanoma visible in skin images. The first 5 features are extracted using Fuzzy C-means clustering based on color variations and color spatial distributions of pigmented skin. The next 5 features consider colors and intensity of the colors and finally the last 5 features assess the shape of the lesion. These discriminative features allow dir=ltr align=left Keywords: Medical image processing, image segmentation, deep learning, feature extraction
