Comparison of GLCM and First Order Feature Extraction Methods for Classification of Mammogram Images

Breast cancer is one of the main causes death in women and ranks first cases Indonesia. Therefore, an early detection prevention breast necessary, which through mammography procedures. A machine learning classifier such as Support Vector Machines (SVM) could be used aid to doctors radiologist diagnosing from mammogram images. The aim this paper compare two feature extraction methods SVM, namely Gray Level Co-Occurrence Matrix (GLCM) order with kernels for each method, Gaussian Polynomial. Classification using SVM method carried out by testing several parameters value C, gamma, degree varying pixel spacing values ​​in GLCM, usually previous studies only default spacing. dataset consists 500 images containing 250 benign malignant images, respectively. This study expected find best highest accuracy between these texture extractions able distinguish classes correctly. result achieved that both Polynomial kernel yields performance 89%.