Dorsal hand vein authentication system using artificial neural network

<span>Biometric feature authentication technology had been developed and implemented for the security access system. However, known biometric features such as fingerprint, face iris pattern failed to provide ideal security. Dorsal hand vein is beneath skin which makes it not easily be duplicated forged. It was expected used in achieve an accuracy with uniqueness of its characteristics. In this paper, 240 images 80 users were obtained from Bosphorus Hand Vein Database. The then pre-processed by cropping ROI, mean filtering, CLAHE enhancing histogram equalizing. ROI segmented implementing binarization. local binary (LBP) extracted ROI. sent artificial neural network (ANN) classification images. training result shows that LBP ANN can recognize dorsal quite well 99.86% accuracy. utilized MATLAB GUI program testing 100 (80 trained 20 untrained users) results revealed 100% their matching result.</span>