Facial Recognition: Issues, Techniques and Applications

A facial recognition system is an approach for automatically identifying or verifying a person from a still digital image or a video frame of a video source. The basic fundamental principle in the science of facial biometrics is that the dimensions, proportions and physical attributes of a person's face are unique. Face recognition has recently received significant attention, especially during the past several years. It has become more obvious due to the availability of feasible technologies and a requirement in wide range of law and commercial implementation areas. An accurate automatic personal identification is critical in a wide range of application domains such as image processing, pattern recognition, neural networks, computer vision, computer graphics, and psychology with specific cases in national ID card, electronic commerce, and access to restricted areas like banks, embassies, military sites, airports and law enforcement premises. The advantage of face recognition is that it does not require physical contact with an image capture device and does not either require any advanced hardware. Facial recognition is thus considered as a serious alternative in the development of biometric or multi-biometric systems. Biometric facial recognition systems measure and analyze the overall structure, shape and proportions of the face to create a unique template for comparison with the database of facial images; used for verification and identification. The image captured is compared with the template previously recorded. Even after attaining a certain level of maturity, their success is limited by practical conditions imposed by real applications like in an outdoor environment with changes in illumination and other scenarios. This paper provides a survey of still based face recognition research offering some insights into the studies of machine recognition of faces, potentially applicable to the design of face recognition systems.