In Image Classification of Skin Cancer Sufferers: Modification of K-Nearest Neighbor with Histogram of Oriented Gradients Approach

Classification in data mining is one technique in recognizing all types of data. Where data can be in the form of text, numeric, images and others. One of the superior classification techniques is the KNN algorithm. The KNN algorithm is a distance search using Euclidean distance. image data classification using the HOG process is needed to modify the KNN. The purpose of this paper is to classify patients with classifying skin cancer patients using the KNN method where the Histogram of Oriented Gradients (HOG) process is used to assist in extracting data for skin cancer patients, which consists of benign and malignant cancers. However, in this paper, the images included in this article are pictures of skin cancer sufferers, which consist of malignant and benign. The data obtained were 660 datasets of which 630 were used as training data and 30 were used as test data. The training and testing went well, this was shown by getting a MAPE of O.06705477%. So that the classification process can be accepted because it shows a small validity.