Mahidol University Logo
Faculty of ICT, Mahidol University
 

Admissions

Printable Version

 

HUMAN FACE RECOGNITION SYSTEM

 

TITLE HUMAN FACE RECOGNITION SYSTEM
AUTHOR CHITTRAPOL INKUNA
DEGREE MASTER OF SCIENCE PROGRAMME IN COMPUTER SCIENCE
FACULTY FACULTY OF SCIENCE
ADVISOR CHOMTIP PORNPANOMCHAI
CO-ADVISOR SUKANYA PHONGSUPHAP
 
ABSTRACT
This research proposed a Human Face Recognition System. Images of staff of the Office of Information Technology at the Revenue Department (RD) of Thailand, were used to develop a system to control access and departure of officers at the IT office building. The system uses a technique of image processing consisting of 3 major processes: 1) preprocessing or preparation of images of the RD staff of 100 officers (10 images each, with 8 for system training and 2 for system testing). In addition, images of 20 people not working in the RD were also prepared ( 1 image each, for system testing); 2) Feature Extraction from images of eyes, ears, noses and mouths, used for a calculation of 20 Euclidean Distances between each organ; and 3) Face Recognition using a Neural Network. Based on the experimental results from reading image a total of 200 images of face staff, with 2 images of each of 100 staff, and another 20 images of people not used for system training, it was found that the system was able to extract 100% face features to calculate the Euclidean Distances. For face recognition, the findings revealed that the average accuracy rate was 96.00% (192 recognized of 200 images) for face images of those used for system training. The average accuracy rate was 100% (20 images recognized) for face images of those not included in the system training.
KEYWORD FACE EXTRACTION / EXTRACT FEATURE / EUCLIDEAN DISTANCE / FACE RECOGNITION / NEURAL NETWORK

 

Go to Top

 

ICT Building, Mahidol University, 999 Phuttamonthon 4 Road, Salaya, Nakhonpathom 73170 Tel. +66 02 441-0909 Fax. +66 02 849-6099
Mahidol University Computing Center, The Faculty of ICT, Mahidol University , Rama 6 Road, Rajathevi, Bangkok 10400 Tel. +66 02 354-4333 Fax. +66 02 354-7333