Human concentration is needed in many aspect of human life, such as in cognitive activities and also can be used in a situation when the human concentration should be present and maintained, for example for a driver, where the absence of concentration could lead to a severe accident. In this research, human concentration is recognized by observing the electroencephalography (EEG) signal generated by the human brain. The EEG signal is taken from a non-invasive brain computer interface (BCI) device and processed using frequency based feature extraction and an RBF kernel SVM classifier. Two frequency-based feature extractions are compared, the power spectral density (PSD) from Fast Fourier Transform (FFT) and the energy from Discrete Wavelet Transform (DWT). DWT is better than FFT to be used as the feature extraction, and the accuracy is higher by 18% compared to the system with FFT. SVM with RBF kernel as the classifier, has shown a good performance with 91% accuracy in recognizing human concentration, with the best parameter settings when C=1 and γ = 0,1.