Melanoma Identification with Content based Image Classification using Bit Plane Features

Augmented episodes of melanoma, a curable skin cancer variety of antagonistic nature, have stimulated the advancements in designing systems for computer aided diagnosis of the disease. Clinical diagnosis includes primary vetting of the symptoms followed by a biopsy and necessary medical examinations. However, computer based classification of the clinical images of dermoscopy have the potential to diminish the exertion of the dermatologist by offering a computer aided opinion independent of medical know-how. Assorted methods are proposed in recent times including the deep learning techniques for computer based melanoma recognition. But, most of the techniques have enhanced computational overhead which has added to the computational complexity of the entire system. In this work, the authors have attempted to design light-weight feature extraction techniques from high level bit planes of dermoscopic images by ignoring the noisy slices of bit planes for robust feature extraction. The proposed method of feature extraction is tested with three different classifiers for specificity and sensitivity outputs of the dermoscopic images. The results of classification have outclassed the performance of state-of-the-art feature extraction techniques.