This paper is published in Volume-4, Issue-3, 2018
Area
Image Processing
Author
Ramya Yalwarkar
Co-authors
Shivaleela Patil, Shreya Mahajan, Dr. Suvarna Nandyal
Org/Univ
PDA College of Engineering, Gulbarga, Karnataka, India
Pub. Date
15 May, 2018
Paper ID
V4I3-1331
Publisher
Keywords
Face recognition, Face detection, Local binary pattern (LBP), Histogram of orientation (HOG), Support vector machine (SVM).

Citationsacebook

IEEE
Ramya Yalwarkar, Shivaleela Patil, Shreya Mahajan, Dr. Suvarna Nandyal. An efficient approach for attendance management system for occluded face recognition, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Ramya Yalwarkar, Shivaleela Patil, Shreya Mahajan, Dr. Suvarna Nandyal (2018). An efficient approach for attendance management system for occluded face recognition. International Journal of Advance Research, Ideas and Innovations in Technology, 4(3) www.IJARIIT.com.

MLA
Ramya Yalwarkar, Shivaleela Patil, Shreya Mahajan, Dr. Suvarna Nandyal. "An efficient approach for attendance management system for occluded face recognition." International Journal of Advance Research, Ideas and Innovations in Technology 4.3 (2018). www.IJARIIT.com.

Abstract

The face is the identity of a person. The traditional approach for attendance can now be replaced by an effective online attendance management system in a classroom environment. The methods to exploit this physical feature have seen a great change since the advent of image processing techniques. The attendance is taken in every school, colleges, and library. The system aims to deviate from traditional systems and introduce a new approach for taking an attendance using image Processing. This describes the working of an Attendance Management System in a classroom environment. Generally, the students in the classroom will sit in an occluded manner. Hence there are more chances of overlapping of faces. In this method initially, the video clip of classroom is taken and is stored in the database. The video clips along with the occluded region are converted into full frames/images. Then we apply Face detection techniques to detect the faces in frames/images and then features are extracted from the detected face (HOG and LBP algorithm). The system first stores the faces of the students in the database. The detected faces are compared with the faces stored in the database during face recognition (SVM classifier). If the system recognizes faces, the attendance gets marked immediately of recognized faces. Given video is compared with the database, after comparing faces are detected and recognized. Attendance gets marked. The methods proposed till now have no solution for Occlusion in which, the overlapped faces are not detected. But this system has the solution for occlusion in which the overlapped faces are detected. Hence, the attendance gets marked.