a novel system for identifying skin cancer through the application of machine learning techniques is introduced. The method intends to make it easier to detect skin cancer early, which is essential for efficient treatment and prevention. The image of skin cancer is obtained from Kaggle and is pre-processed using a variety of methods. The image is then processed using a variety of image-processing techniques, including edge-detection, image sharpening, and enhancement. The HOG feature methodology is used to extract some image characteristics. The classifier receives these features as input. Support vector machine (SVM), Random Forest, and K Nearest Neighbor are used for categorization. The Random Forest algorithm among them provides more accuracy. It categorizes the type of image that is displayed as benign or malignant.
DATASET
https://www.kaggle.com/datasets/fanconic/skin-cancer-malignant-vs-benign