A hybrid feature extraction approach for the detection of melanoma using neural network
In spite of the gargantuan number of patients affected by melanoma every year, its detection at an early stage is still a challenging task. This paper illustrates a method which involves the combination of the existing ABCD (Involving symmetry, border, color, and diameter detection) rule and grey level co-occurrence matrix (GLCM) along with Local Binary Pattern (LBP) for identification of malignant melanoma skin lesion with greater accuracy. Several steps, such as image acquisition technique, pre-processing (RGB to HSV) techniques and segmentation processes are undertaken for the skin feature selection criteria to successfully determine the skin lesion's characteristic properties for classification. Texture features such as contrast, entropy, energy and homogeneity of the affected region is obtained using LBP and GLCM for discriminatory purposes of the two cases (melanoma and non-melanoma). Finally, the back propagation neural network (BPN) is used as the classifier to determine whether the dermoscopic image is benign or malignant.