A Real-time Face Recognition System Using Multiple Mean Faces and I Dual Mode Fishefwaces

segmentation. Second, for face recogmtion,' we have enhanced the recognition performance by enabling the This research features an automatic face detection and system to not only work under normal lighting condition recognition system. The purpose of the system is for but also operate in a particularly tuned way when there are access control to a building or an office. The main feature severe illumination changes. of the system is face detection and face recognition robust In the following section, we give a brief overview of to illumination changes. A novel template matching the entire system. Section 3 and 4 describe face detection techmque using multiple mean faces (MMF) of various and face recognition parts of the system respe7tively. We sizes, luminance, and rotations is employed to achieve report the experimental results on the recognition robust face detection. The system is also capable of performance of the system in section 5. operating in two different modes for face recognition: 1 under normal illumination condition and under severe 2. SYSTEM OVERVIEW , illumination changes. , The system can operate with a normal PC icamera of 300,000 pixel resolution and the illumination condition for normal operation is interior lighting brighter than 60 lux. It