2014/09/27 by Shervin Minaee, Minaee, Shervin, AmirAli Abdolrashidi +1
Chemistry · Computer Science · #Biometric Identification and Security #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Spectroscopy and Chemometric Analyses
paper · pdf · doi:10.48550/arxiv.1409.7818
openalex publication_date 2014/09/27 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28
Biometric-based identification has drawn a lot of attention in the recent\nyears. Among all biometrics, palmprint is known to possess a rich set of\nfeatures. In this paper we have proposed to use DCT-based features in parallel\nwith wavelet-based ones for palmprint identification. PCA is applied to the\nfeatures to reduce their dimensionality and the majority voting algorithm is\nused to perform classification. The features introduced here result in a\nnear-perfectly accurate identification. This method is tested on a well-known\nmultispectral palmprint database and an accuracy rate of 99.97-100 % is\nachieved, outperforming all previous methods in similar conditions.\n