IMAGE AND VISION COMPUTING, cilt.24, ss.483-497, 2006 (SCI-Expanded)
The potential of hand shape and hand texture-based biometry is investigated and algorithms are developed. Feature extraction stage is preceded by meticulous registration of the deformable shape of the hand. Alternative features addressing hand shape and hand texture are compared. Independent component analysis features prove to be the best performing in the identification and verification tasks. It is shown that hand biometric devices can be built that perform reliably for a population of at least 1000. (C) 2006 Elsevier B.V. All rights reserved.