Abstract
Palmprint based Identification is gaining popularity due to its traits like user acceptance, reliability and ease of acquisition. The paper presents a recognition method which extorts textural information obtainable from the palmprint, utilizing different filters of wavelet transform. Palmprint center has been computed using the chessboard metric of Distance Transform whereas the structures of best fitting ellipse help resolve the alignment of the palmprint. Region Of Interest of 256×256 pixels is clipped around the center. Next, normalized directional energy components of the decomposed subband outputs are computed for each block. Biorthogonal, Symlet, Discrete Meyer, Coiflet, Daubechies and Mexican hat wavelets are investigated on 500 palmprints acquired from 50 users with 10 samples each for their individual and concatenated combined features vectors. The performance has been analyzed using Euclidean classifier. An Equal Error Rate (EER) of 0.0217 and Genuine Acceptance Rate (GAR) of 97.12% with combined feature vector formed by Bior3.9, Sym8 and Dmeyer wavelets depict better performance over individual wavelet transforms and combination of coiflet, Daubechies and Mexican hat wavelets.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
