الفهرس 
Chapter 1: IntroductionOnly 14 pages are availabe for public view
 |  | from | 130 |  |  |
| | | from | 130 | | |
Abstract
Over the past few decades, face recognition has become a rapidly growing
research topic due to the increasing demands in many applications of our daily life
such as airport surveillance, personal identification in law enforcement, surveillance
systems, information safety, securing financial transactions, and computer security.
The objective of this thesis is to develop a face recognition system capable of
recognizing persons with a high recognition capability, low processing time, and
under different illumination conditions, and different facial expressions. The thesis
presents a study for the performance of the face recognition system using two
techniques; the Principal Component Analysis (PCA), and the Zernike Moments
(ZM). The performance of the recognition system is evaluated according to several
aspects including the recognition rate, and the processing time.
Face recognition systems that use visual images are sensitive to variations in
the lighting conditions and facial expressions. The performance of these systems may
be degraded under poor illumination conditions or for subjects of various skin colors.
Several solutions have been proposed to overcome these limitations. One of these
solutions is to work in the Infrared (IR) spectrum.
IR images have been suggested as an alternative source of information for
detection and recognition of faces, when there is little or no control over lighting
conditions. This arises from the fact that these images are formed due to thermal
emissions from skin, which is an intrinsic property because these emissions depend
on the distribution of blood vessels under the skin. On the other hand IR face
recognition systems still have limitations with temperature variations and recognition
of persons wearing eye glasses.
In this thesis we will fuse IR images with visible images to enhance the
performance of face recognition systems. Images are fused using the wavelet
transform. Simulation results show that the fusion of visible and thermal face images
enhance the performance of face recognition systems. The thesis also presents an
application of cepstral analysis for face recognition. A cpestrum-based face
recognition system is introduced and tested for various types of degradation.