Face recognition using subspaces techniques

Abstract

With many applications in various domains, Face Recognition technology has received a great deal of attention over the decades in the field of image analysis and computer vision. It has been studied by scientists from different areas of psychophysical sciences and those from different areas of computer science. Psychologists and neuro-scientists mainly deal with the human perception part of the topic where as engineers studying on machine recognition of human faces deal with the computational aspects of Face Recognition. Face Recognition is an important and natural human ability of a human being. However developing a computer algorithm to do the same thing is one of the toughest tasks in computer vision. Research over the past several years enables similar recognitions automatically. Various face recognition techniques are represented through various classifications such as, Image-based face recognition and Video-based recognition, Appearance-based and Model-based, 2D and 3D face recognition methods. This paper gives a review of different face recognition techniques available as of today. The focus is on subspace techniques, investigating the use of image pre-processing applied as a preliminary step in order to reduce error rates. The Principle Component Analysis, Linear Discriminant Analysis and their modified methods of face recognition are implemented under subspace techniques, computing False Acceptance Rates (FAR)and False Rejection Rates (FRR) on a standard test set of images that pose typical difficulties for recognition. By applying a range of image processing techniques it is demonstrated that the performance is highly dependent on the type of pre-processing steps used and that Equal Error Rates (EER) of the Eigenface and Fisherface methods can be reduced using the method proposed in this paper.