Ground Penetrating Radar (GPR) senses dielectric discontinuities below the surface. Thus, it can detect low-metal and non-metal land mines. However, it detects not only landmines but also all objects under the ground and therefore, false alarm rates of GPR are very high. Powerful feature based algorithms are required to reduce false alarm rates and to distinguish land mine from clutter that causes false alarms. In this paper, Histograms of Dominant Orientations (HDO) feature extraction method is implemented for landmine detection problem. HDO method is compared with Histograms of Oriented Gradients (HOG) method which is the state-of-the-art feature extraction method for landmine detection. Receiver Operating Characteristic (ROC) curves are calculated for comparison of methods and it is shown that the HDO outperforms HOG.