Speed up Robust Features (SURF) with Principal Component Analysis-Support Vector Machine (PCA-SVM) for benign and malignant classifications

Abstract

A novel Computer Aided Diagnosis (CADx) component is proposed for breast cancer classifications. Four major phases were conducted in this research. The first phase is pre-processing, this is followed by features extraction phase by using the Speed Up Robust Features (SURF). The next phase is features selection by using the Principal Component Analysis (PCA). The final phase is the classification phase to classify the cancer. Three different classifiers; Support Vector Machine (SVM), Linear Discriminant Analysis (LDA) and Decision Tree (DT) were compared in this research. Results obtained shows that the PCA-SVM performs the highest accuracy with 92.9% accurate compared to other classifiers.

Keywords: breast cancer; CADx; SURF; PCA; SVM