In the field of civil engineering, Ground Penetrating Radar (GPR) is the most widely used method of Non-Destructive Testing (NDT). Using supervised learning methods or signal processing methods, it is possible to analyze the sub-surface defects in pavement. In this paper, we propose to use a supervised machine learning method called Support Vector Machines (SVM) to detect the presence of debondings within the pavement. Here, the ground-coupled GPR in quasi mono-static configuration along with SVM is used to detect debondings. The experiments are done on bituminous concrete pavements with various material characteristics. The classification results show the efficiency of the detection process.