Security system using biometric technology: Design and implementation of voice recognition system (VRS)

• Main Authors: A. Rashid, Rozeha, Mahalin, Nur Hija, Sarijari, Mohd. Adib, Abdul Aziz, Ahmad Aizuddin
• Format: Conference or Workshop Item
• Language: English
• Published: 2008
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utm.my/id/eprint/7698/1/Rashid_Rozeha_A_2008_Security_System_Using__Boimetric_Technology.pdf; http://eprints.utm.my/id/eprint/7698/; http://dx.doi.org/10.1109/ICCCE.2008.4580735

Biometric technology is fast gaining popularity as means of security measures to reduce cases of fraud and theft due to its use of physical characteristics and traits for the identification of individuals. The earliest methods of biometric identification included fingerprint and handwriting while more recent ones include iris/eye scan, face scan, voice print, and hand print. Biometric voice recognition and identification technology focuses on training the system to recognize an individual's unique voice characteristics (i.e., their voice print). The technology lends itself well to a variety of uses and applications, including security access control for cell phones (to eliminate cell phone fraud), ATM manufacturers (to eliminate pin # fraud) and automobile manufacturers (to dramatically reduce theft and carjacking). In this paper, we present an implementation of a security system based on voice identification as the access control key. Verification algorithm is developed using MATLAB (SIMULINK) function blocks which is capable of authenticating a person's identity by his or her voice pattern. A voice match will produce logic '1' while a mismatch, logic '0'. A microcontroller circuit controlling access to a door is built to test the reliability of this voice controlled security system. It is found out that the developed voice recognition software has successfully activated the door opening mechanism using a voice command that ONLY works for the authenticated individual. The system is proven to be able to provide medium-security access control and also has an adjustable security level setting to account for the variations in one's voice each time a voice identification occurs.