Project-based Design of a Biometric Face Recognition System
Ravi P. Ramachandran, Robi Polikar, Kevin D. Dahm, Ying Tang, Sachin S. Shetty, Richard J. Kozick, Robert M. Nickel, Steven H. Chin · 2020
Abstract PROJECT BASED DESIGN OF A BIOMETRIC FACE RECOGNITION SYSTEMBiometrics is the science of recognizing and authenticating people using their physiologicalfeatures. Interest in biometrics has increased significantly after the 9/11 attacks. Border andimmigration control, restricted access to facilities and information systems, cybersecurity, crimeinvestigations and forensic analysis are just a few of the primary application areas of biometricsused by commercial, government and law enforcement agencies. The biometrics market hasgrown from $2.7 billion in 2007 to an expectation of $7.1 billion by 2012 with a compoundannual growth rate of 21.3 percent. There is much research interest in different biometricsystems, notably, face recognition. Face recognition systems have advantages including ease ofuse and implementation, low cost and high user acceptance. In addition, they can be easilyintegrated (no special hardware except for a built-in Web camera) with many devices includingdesktops, laptops, cell phones, wireless access points, iPhones, iPads and PDAs.This paper is about a face recognition project focused on open-ended design that is part of asenior undergraduate course on biometric systems. In implementing a face recognition system,students go through each step, namely, preprocessing, feature extraction, classification (trainingand use in rendering a decision) and performance evaluation. The AT&T database is used toshow students that robustness to mismatched training and testing conditions is a significantpractical issue. The open-ended aspects include researching different robust features,implementing different classifiers and investigating feature and classifier fusion to augmentperformance. The student learning outcomes of the project include: Enhanced application of math skills Enhanced software implementation skills Enhanced interest in biometrics Enhanced ability to read papers and apply algorithms (like robust feature extraction) to achieve a better design thereby providing research experience. Enhanced communication skills Comprehension of the importance of vertical integration in that students realize that their experiences are part of a flow that contributes to a unified knowledge base.The assessment results are very encouraging with respect to the achievement of the learningoutcomes.