A hybrid learning scheme towards authenticating hand-geometry using multi-modal features

<span lang="EN-US">Usage of hand geometry towards biometric-based authentication mechanism has been commercially practiced since last decade. However, there is a rising security problem being surfaced owing to the fluctuating features hand-geometry during mechanism. Review existing research techniques exhibits usage singular hand-geometric along with sophisticated learning schemes where accuracy accomplished at higher cost computational effort. Hence, proposed study introduces simplified analytical method which considers multi-modal extracted from could further improve upon robust recognition system. For this purpose, system implementing hybrid scheme using convolution neural network and Siamese algorithm former used for feature extraction latter person on basis authenticated geometry. The main results show that offers 12.2% improvement in compared models exhibiting simpler amendment by inclusion multi-modalities, can be significantly without burden.</span>