Palmprint identification via GLCM of Contourlet transform

From different methods for personal identification, biometric features are most concerned. One of robust biometrics for personal identification is palmprint. Feature extraction from palm area is important issue and can determine complexity and efficiency of identification system. In this paper, at first Contourlet transform of region of interest (ROI) calculated. Then, gray-level co-occurrence matrix (GLCM) of contourlet sub-bands are calculated to create feature vector. Linear discriminant analysis (LDA) is used to reduce the dimensionality of feature vector. Support vector machine (SVM) classifies the features to perform personal identification. In order to evaluate the performance of proposed algorithm, Hong Kong Polytechnic University (PolyU) palmprint database is used. Experimental results on 200 different persons demonstrate that proposed method has better efficiency in comparison with recently proposed algorithms for palmprint identification.