Mohammad Reza Khezri - Payame Noor University (PNU)Tehran, Iran
Seyed Mosarreza Mosavisadr - Technical and Vocational University (TVU)Tehran, Iran

This paper proposed a new biometric system based on the texture of hand knuckles. The texture pattern produced by finger knuckle bending is highly unique andmakes the surface a distinctive biometric identifier. In this approach, we used Contourlet and wavelet transforms to extract features from finger knuckle surfaces. Then we usedAGV to select the best features. Finally we examined three famous classifier to select the one with the best results. Theexperimental results confirmed the 97.66% recognition rate for the proposed system

biometrics; FKP; contourlet; wavelet; AGV