In this work, to develop an accurate segmentation and classification of skin lesions, have
presented a fuzzy clustering and deep neural network (DNN) in segmentation and classification
of skin lesions. The proposed effective segmentation and classification procedure is described
as; initially input image is taken from the dermoscopy images database. In the pre-processing
stage, the input dermoscopy image undergoes Gaussian filter and morphological operations.
Then fuzzy clustering is applied to the pre-processed images for the segmentation of lesion
regions. Subsequently, effective features such as texture features are extracted from the
segmented output images. Finally, the proposed DNN classifier classifies the skin lesion
images into normal or abnormal images based on the extracted features. The results were
analyzed to demonstrate the performance of the proposed segmentation and classification
technique with the existing techniques.