Abstarct: One of the most fitting biometric for identifying individuals is finger veins that have unique patterns of finger veins to recognize persons at a high level of accuracy. In this applicable thesis, we study the human recognition via finger vein images. First we extract veins from finger vein images by using entropy baxsed thresholding. The method extracts veins as well, but the images are very noisy. That means in addition to the veins that appeared as dark lines, they have some short and long lines. Then we applied radon transformation to segmented images. The Radon transform is not sensitive to the noise in the images due to its integral nature, so in comparison with other methods is more resistant to noise. This transform does not require the extraction of vein lines accurately, that can help to increase accuracy and speed. In proposed method PCA and CSP have been used for extracting dominant features from finger vein images. That means common spatial patterns (CSP) and principal component analysis (PCA) is applied to the blocks of radon transformation. To improve the classification accuracy, redundant features are eliminated by using genetic algorithms. Finally we used MLP and 1-NN classifier for data classification. We applied proposed method on the Peking University finger vein data set. We consider 75% of data for training and 25% for testing system. Experimental results show that the proposed method has good performance in recognizing individuals and obtained the recognition rate of 100% without any error.