Abstract—The ever-increasing volume in the collection of image data in various fields of science, medicine, security and other fields has brought the necessity to extract knowledge. Face classification/recognition is one of the challenging problems of computer vision. This paper presents details development of a real time face recognition system (FRS) aimed to operate in less constrained environment. Firstly, it is reviewed the well-known techniques used in face recognition then the details of every step in recognition process and explains the ideas, which leaded to these techniques. Being widely used in pattern recognition tasks, neural networks have also been applied in face recognition. In this study, we developed a face recognition system based on Step Error Tolerance Back-propagation Neural Network (SET-BPN) . SET-BPNs supply flexibility and straightforward design by reducing error in each step of learning which make the system easily and rapidly operable along with the successful classification results. In order to analyze the system in practice we ran several tests using real data. Empirical results show that proposed approach greatly improves recognition speed in feature matching step. From the experiment it is found that the system correctly recognizes 91% of the faces, using less then one second of test samples from each face image.
Index Terms—Recognition, Back-propagation Neural Network, Step Error, Feature Extraction
Sarawat Anam and M. A Rahman are with the Department of Computer Science & Engineering in Rajshahi University of Engineering & Technology, Rajshahi-6204, Bangladesh. (e-mail: firstname.lastname@example.org, email@example.com).
Md. Shohidul Islam and M. A Kashem are with the Department of Computer Science & Engineering in Dhaka University of Engineering & Technology, Gazipur-1700, Bangladesh (e-mail: firstname.lastname@example.org or duet.ac.bd, email@example.com).
Cite: Sarawat Anam, Md. Shohidul Islam, S. M. A Kashem, M. A Rahman, "Real Time Face Recognition Using Step Error Tolerance BPN," International Journal of Engineering and Technology vol. 1, no. 1, pp. 92-96, 2009.