Melanoma detection using HSV with SVM classifier and de-duplication technique to increase efficiency

Abstract

Around one third of all recorded cancers account worldwide for skin cancer, according to the World Health Organization. Every year in the USA there are over 5 million non-melanoma, although about 13,000 cases of melanoma are reported in the UK and Australia. Over the last few decades, occurrences of skin cancer have also risen by 119%, from 1990 to 91270, from 27,600 in 2018. Melanoma has risen 119 million in nations such as the United Kingdom. Not only has the ozone layer reduced ultraviolet radiation safety but the misuse of the atmosphere and heat and tanning [2] has explained this trend. The medical fraternity has spent enormous time and energy on sensitizing people by awareness initiatives. Human skin cancer is the most dangerous variety, with its effects growing rapidly. Early detection of melanoma in dermoscopic photos is extremely important as they are useful for early diagnosis and treatment of ailment. Computer-aided diagnostic tools may promote the detection of cancer early for dermatologists. In this method pre-processing shall take place by applying a list of filters for removing hair, spots and assorted noises from pictures and the methodology of photographs painting shall then be used to fill unspecified areas. In this paper system uses PH2 dataset for evaluation. Also proposed de-duplication method will help in image preprocessing time which will also help in detection of melanoma. KNN, Naïve Bayes and SVM classifier are used for training and testing purpose also SVM shows the highest accuracy of classifier with de-duplication techniques.