Open AccessAn Efficient Dorsal Hand Vein Recognition Security System Using Arduino And Gsm Technology
Author(s) -
N. Rajalakshmi,
Ramsankar. M.P,
P. Manimegalai
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.f1290.0986s319
Subject(s) - biometrics , computer science , gsm , arduino , word error rate , filter (signal processing) , artificial intelligence , pattern recognition (psychology) , computer vision , embedded system , computer network
With the onset of maximum power, modest figuring and more prominent unpredictability, biometric verification has turned out to be conceivable at each scale in light of its more secure nature and furthermore easy to use conduct. Compare to other biometrics, vein biometric is a decent verification characteristic among others. The dorsal hand vein recognition is an emerging biometric procedure which is utilized for verification purposes in many applications. In this work preprocessing is done by median filter and region of interest such as veins separated from the muscles and bones through adaptive Kmeans clustering algorithm.The proposed method extracts the dorsal hand vein pattern features by using LBP and Repeated Line Tracking algorithm.Finally recognition and authentication is done using Artificial Neural Network. Arduino and GSM technology is used in this work to set security preference for the particular user.In order to validate the proposed work , a total of 480 images of dorsal hand veins is involved in this work. In a comparison with four existingverification algorithms, the proposed method achieves thehighest accuracy with lowest error rate.