Using of Hand Geometry in Biometric Security Systems

Abstract

In this paper, biometric security system for access control based on hand geometry is presented. Biometric technologies are becoming the foundation of an extensive array of highly secure identification and personal verification solutions. Experiments show that the physical dimensions of a human hand contain information that is capable to verify the identity of an individual. The database created for our system consists of 408 hand images from 24 people of young ages and different sex. Different pattern recognition techniques have been tested to be used for verification. Achieved experimental results FAR=0,1812% and FRR=14,583% show the possibilities of using this system in environment with medium security level with full acceptance from all users.

Keywords

• Biometric security
• hand geometry recognition
• Gaussian mixture model
• expectation-maximization algorithm