REVIEW OF EXISTING ALGORITHMS FOR FACE DETECTION AND RECOGNITION
In this paper, we present a review on the most successful existing algorithms or methods for face recognition technology to encourage researchers to embark on this topic. A brief on general information of this topic is also included to compose an overall review. This review is written by investigating past and ongoing studies done by other researchers related to the same subject. Five different algorithms have been preferred based on the most widely used criteria. The algorithms are Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA), skin colour, wavelet and Artificial Neural Network (ANN). Certain parameters have been taken into account for the algorithms’ review. The parameters are size and types of database, illumination tolerance, facial expressions variations and pose variations. However, no specific justification can be claimed as it is only a review paper based on other researches.
Computer vision offers a high demanding applications and outcomes specifically face detection and recognition. This area has always become the researchers’ major focus in image analysis because of its nature as human-face primary identification method. It is very interesting and becomes such a challenge to teach a machine to do this task. Face recognition also is one of the most difficult problems in computer vision area. Face detection and recognition also receives a huge attention in medical field and research communities including biometric, pattern recognition and computer vision communities [1][2][3][4]. The field of biometrics technology utilizes detection and recognition method involving human body parts such as fingerprint, palm, retina (eyes) and face. Biometrics ID method of access is not only authenticates but also verifies the identity of a person, which is corresponding to the authorized access. In terms of reliability and security of access, biometrics does offer a better one rather than the conventional access method which using the password. The password access method only authenticates the user but does not actually “know” the user. Other people can easily steal or hack someone else’s password. When this happens, the person who stole the password may be able to log into the secured system and access other people’s data that is personal and valuable. Biometrics ID method such as physiological method (face, fingerprint, eyes) is more competent and stable than the behavioural method (keystrokes, voice). Physiological method is more stable because the feature such as face is not easily changed unless severe damage occurred to the face. Instead of behavioural method, such as voiceprint that may change easily due certain reasons like health factor, illness stress. Biometrics characteristics are difficult to imitate and therefore it is very hard to forge. This may be the one the reasons of why face recognition is well known for its functionality. The raising of computer capabilities and the market demand for security has also driven the studies of face detection and recognition into a deeper depth.
Free download research paper
CSE PROJECTS