Face recognition

• Main Author: Chia, Min Wen.
• Other Authors: Chua Chin Seng
• Format: Final Year Project
• Language: English
• Published: 2010
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Biometrics
• Online Access: http://hdl.handle.net/10356/40140
• Institution: Nanyang Technological University

This is a report for the Final Year Project held in the year of study of the 4-year Electrical and Electronic Engineering course in Nanyang Technological University (NTU), starting on 2nd January 2010. Over the years, the face has been a major interest for researchers as it plays an important role in security systems and biometric purposes and it has been an important in our daily lifestyle. The importance of face recognition technology has aroused much interest in researchers to develop a reliable face recognition face system. The objective of this project is to create an accurate face recognition system for a set of face database. The method that the author will be using is the Principal Component Analysis (PCA), which is one of the earliest approaches to face recognition. The project was divided into two major parts. In the first part, Principal Component Analysis (PCA) was used to evaluate face images from different subjects and each set of images consists of different variations such as different frontal expressions and etc. Two test cases namely, the overall successful rate to identify and the rejection capability was also developed by the author to determine the threshold value (ranging from 3000 to 5000) to be used for the recognizer that achieve the best result. The best threshold value was found to be 3000 and 3250; both thresholds provides the best results for both of the test cases. For the second portion, a face recognition system, (GUI) is developed in the second part of the project to facilitate the recognition process. Further results of the analysis will be explained in detailed subsequent pages