Classification of Skin Diseases Types using Naïve Bayes Classifier based on Local Binary Pattern Features
Happy Septiana Kusumastuti Aji Putri, Christy Atika Sari, De Rosal Ignatius Moses Setiadi, Eko Hari Rachmawanto · 2020 International Seminar on Application for Technology of Information and Communication (iSemantic) · 2020
This study aims to analyze the Naïve Bayes classifier (NBC) method and feature extraction of Local Binary Pattern (LBP) for the classification of skin diseases. NBC was chosen because it is reliable for small datasets. Whereas LBP is suitable for feature extraction because every skin disease has a distinctive texture. The combination of these two algorithms is proven to produce good accuracy in small datasets. Based on four experiments with a total of images used are 225, 180, 135 and 90 images on nine types of skin diseases, with a composition of 80% for training data and 20% for testing data resulted in an accuracy of 82.20%, 91.67%, 85.18%, and 94.44%. The best accuracy obtained with the total image used is 90, this proves that the Naïve Bayes classifier has good performance for classifying images in small datasets and with a small number of datasets can save time to do the training process.