Classification of Colposcopy Data Using GLCM-SVM on Cervical Cancer
Muhammad Ikhsan Thohir, Ahmad Zoebad Foeady, Dian Candra Rini Novitasari, Ahmad Zaenal Arifin, Bunga Yuwa Phiadelvira, Ahmad Hanif Asyhar · 2020
cervical cancer is the second deadliest disease for women. To reduce the number of deaths caused by this disease, it is necessary that there is prevention by early detection of cancer. The method used to identify the presence of cervical cancer is to make visual observations that produce image data. However, a visual observation also has weaknesses, so it needs to be done computer-based observation to facilitate early detection. In this study, the computer-based observation method used is preprocessing, followed by a feature extraction process using the Gray Level Co-occurrence Matrix (GLCM) and Support Vector Machine (SVM) as a classification method. The best SVM classification results are using the polynomial kernel and GLCM feature extraction with an angle of 450. The accuracy rate obtained is 90%.