A Systematic Review of PCA and Its Different Form for Face Recognition
Reecha Sharma, Manjeet Singh Patterh · 2014
Face recognition is an important part of our daily life. Face recognition is used either for verification (one-to-one matching) or for identification (one-to-many). Mainly face recognition consists of two categories feature based and appearance based. Feature-based method first process the input image to identify and measure distinctive facial features such as the eyes, mouth, nose, etc., as well as other fiducial marks and then compute the geometric relationships among those facial points, thus reducing the input facial image to a vector of geometric features. Appearance based method used holistic features of 2D image attempt to identify faces using global representations, i.e., descriptions based on the entire image rather than on local features of the face. In this paper holistic method is discussed using Principle Component Analysis. This paper presents a systematic review of different forms of Principle Component Analysis (PCA) for face recognition. Based on the brief review of different forms of PCA, comparison table of recognition rate for ORL and FERET database are prepared. Face is an important biometric trait used in many applications such as General identity verification, Criminal justice system, Image database investigation, Smart card etc. The human ability to recognize faces is awesome. A human can recognize thousands of faces learned throughout the lifetime and identify familiar faces at a glance even after years of separation. This skill is quite robust, despite large changes in the visual stimulus due to viewing conditions, expression, aging, and distractions such as glasses, beards or changes in hair style. Developing a computational model for face recognition is difficult. Over the last few decades, a lot of researchers have been working in this area. Principal component analysis (PCA) is holistic method. Holistic method tries to identify face using global representation. It describes the entire face rather than on local features such as eyes, nose, lip etc of the face. One of the simplest and most effective PCA approaches used in face recognition systems is the eigenface approach. This approach transforms faces into a small set of essential characteristics.