You are on page 1of 5


Group Members 1. Ashtekar Mahadev C. 2. Narute Ratnagouri B. 3. Unde Mayur A.

ABSTRACT: Abstract: This paper describes a Class attendance system. It uses Face Recognition as the parameter for marking the Attendance of students. If the student is present an SMS is sent to the parent. Authentication is a significant issue in system control in computer based communication. Human face recognition is an important branch of biometric verification and has been widely used in many applications, such as video monitor system, human-computer interaction, and door control system and network security. Our system will be use for Students Attendance System which will integrate with the face recognition technology using Principal Component Analysis (PCA) algorithm.

Our project deals with face recognition for college libraries or anywhere like crowdie areas, these areas are 1) FOR COLLEGE LIBRARY. We can use this system for colleges that is we can recognize all the database of students those are allotted in college so that it will easier to find all the data of students. 2) FOR OUTSIDE THE CLASSROOMS. We can also use this system for attendance purpose. 3) FOR COLLEGE ENTRY GATES.

INTRODUCTION Three main tasks of face recognition may be named: document control Access control and database retrieval. The term document control means the verification of a human by comparison his/her actual camera image with a document photo. Access control is the most investigated task in the field. Such systems compare the portrait of a tested person with photos of people who have access permissions to joint used object. The last task arises when it is necessary to determine name and other information about a person just based on his/her one casual photo. Because of great difference between the tasks there is not a universal approach or algorithm for face recognition. We tested several methods for mentioned above tasks: geometric approach, elastic matching and neuron nets. Summary of our experiments are described below. Attendance is the most basic job in every institution or organization. Manual methods have been used since a long time. Integrating Face Recognition for attendance system is an innovative technique

Block Diagram:-


Face recognition by PCA Micro Controller




Face Recognition Implementation Methodology PCA is an ideal method for recognizing statistical patterns in data. The underlying concept of face recognition with PCA is used in this approach. PCA is a useful statistical technique that has found application in fields such as face recognition and image compression, and is a common technique for Finding patterns in data of high dimension Controller role is send the attendance to parents of the student via gsm when face get recognized if not buzzer get activate

We are presenting our experimental study of face recognition approaches, Which may be applied in identification systems, document control and access control? An original algorithm of pupil detection oriented for low-contrast image was described. The proposed face similarity meter was found to perform satisfactorily in adverse conditions of exposure, illumination and contrast variations, and face pose. We achieved the recognition accuracy of 98.5%, 92.5% and 94 % for the presented approaches, correspondingly. It may be improved by utilization any additional features. Cruising the warping space more efficiently, e.g. using a corresponded faces rotation and gesture geometric model, and may speed up the execution time. ADVANTAGES

Less time delays Quick response time Fully automate system

At Tollbooth. Security Guard Cabins/security areas such bank locker ,atm. Replacement for thumb detection. (Attendance system)

Physical access control (smart doors).

REFERENCE 1 ) N. Otsu, A threshold selection method from the gray-level histograms // IEEE Trans. on Syst., Man, Cybern.-1979.- Vol. SMC-9.- P. 62-67. 2) R. Brunelli and T. Poggio, Face recognition: features versus templates // IEEE Trans. on PAMI.-1993. - Vol. 15.- P.1042-1052. 3) The 6-th International Conference on Pattern Recognition and Image Analysis October 21-26, 2002, Velikiy Novgorod, Russia, pp. 707-711 THREE APPROACHES FOR FACE RECOGNITION V.V. Starovoitov1, D.I Samal1, D.V. Briliuk1