A human face is a complex object with features that can vary over time. However, we humans have a natural ability to recognize
faces and identify persons in a glance. Of course, our natural recognition ability extends beyond face recognition, where
we are equally able to quickly recognize patterns, sounds or smells. Unfortunately, this natural ability does not exist in
machines, thus the need to simulate recognition artificially in our attempts to create intelligent autonomous machines.
Face recognition by machines can be invaluable and has various important applications in real life, such as, electronic and
physical access control, national defense and international security. While the world is in war against terrorism, the list
of wanted persons is getting larger, however, in most cases there is a database containing their face images with various
different features such as: with and without eyeglasses or bearded and clean shaven...etc. These different face images of
persons (wanted or not) can be used as database in the development of face recognition systems.
Current face recognition methods rely on either: detecting local facial features and using them for face recognition or on
globally analyzing a face as a whole. This chapter reviews known existing face recognition methods and presents two case studies
of recently developed intelligent face recognition systems that use global and local pattern averaging for facial data encoding
prior to training a neural network using the averaged patterns.