Skip to Main Content
This paper presents an effective algorithm of palmprint feature extraction. This algorithm is constructed on the basis of Gabor filter and moment invariant (MI). The process of implementing the algorithm is as follows: first, we perform wavelet transform of the original region of interest (ROI) of the palmprint image to get the approximation image (AIROI). Later, we exploit the Gabor filter to capture the texture information of the AIROI, and then compute each pixelpsilas magnitude of the transformed image to produce a Gabor Magnitude Picture (GMP). We compute the MIs of the GMP and use the MIs as features of palmprint identification. Our experiment on an open database downloaded from PolyU Biometrics Research Center obtains very high right recognition rate.
Date of Conference: 21-24 Sept. 2008