You are in:Home/Publications/Real-Time Dorsal Hand Recognition based on Smartphone‏

Ass. Lect. Mohammed Ibrahim Sayed Mohammed :: Publications:

Real-Time Dorsal Hand Recognition based on Smartphone‏
Authors: Mohamed I. Sayed; Mohamed Taha; Hala H. Zayed
Year: 2021
Keywords: Biometric system , dorsal hand , features extraction , features matching , near-infrared , veins recognition , smartphone
Journal: IEEE Access
Volume: 9
Issue: Not Available
Pages: 151118 - 151128
Publisher: IEEE
Local/International: International
Paper Link:
Full paper Not Available
Supplementary materials Not Available

The integration of biometric recognition with smartphones is necessary to increase security, especially in financial transactions such as online payments. Vein recognition of the dorsal hand is superior to other methods such as palm, finger, and wrist, as it has a wide area to be captured and does not have any wrinkles. Most current systems that depend on dorsal hand vein recognition do not work in real-time and have poor results. In this paper, a dorsal hand recognition system working in real-time is proposed to achieve good results with a high frame rate. A contactless device consists of a universal serial bus (USB)camera and infrared LEDs and is connected to a smartphone used to collect our dataset. The dataset contained 2200 images collected from both hands of 100 individuals. The captured images were processed with light algorithms to improve the real-time performance and increase the frame rate. The feature detection and extraction algorithm is oriented FAST and rotated BRIEF (ORB) with K-nearest neighbors (K-NN) matching to match features. Another benchmark, called the Poznan University of Technology (PUT) dataset, is used to measure the efficiency of the proposed system. The results obtained from experimental testing showed that the proposed system had a low equal error rate (EER) of 4.33% and a high frame rate of 29 frames per second.

Google ScholarAcdemia.eduResearch GateLinkedinFacebookTwitterGoogle PlusYoutubeWordpressInstagramMendeleyZoteroEvernoteORCIDScopus