Attendance System with Face Recognition
Tanya Sinha1, Abhisekh Ghosh2, G. Manju3
1Tanya Sinha*, Computer Science and Engineering, SRMIST Ktr Campus, Tamil Nadu.
2Abhisekh Ghosh, Computer Science and Engineering, SRMIST Ktr Campus, Tamil Nadu.
3G. Manju, Computer Science and Engineering, SRMIST Ktr Campus, Tamil Nadu.
Manuscript received on March 18, 2020. | Revised Manuscript received on April 02, 2020. | Manuscript published on April 30, 2020. | PP: 799-804 | Volume-9 Issue-4, April 2020. | Retrieval Number: D7710049420/2020©BEIESP | DOI: 10.35940/ijeat.D7710.049420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Marking Attendance is the most common way to know the physical presence of an individual. But it is challenging when it comes to manual attendance system, which is followed in most of the places. Calling out each student’s registration number one by one is a tedious task. Day by Day the number of students in schools and universities is increasing hence, making it more difficult in managing and maintaining the attendance records. Automation is the need in every sector to reduce the human effort. Computer vision is a part of automation where computer replicates the human vision system and performs an understanding of useful information from images. It is a boon for many problems, attendance system can also be transformed from manual sheets to face recognition. This paper proposes a framework for developing an attendance system using Face Recognition. This system comprises an Android Application that can be installed on professor’s mobile phone. Through the application, the camera can be unlocked to capture images. Each student’s image is captured and stored for training. OpenCV is used with a machine learning algorithm to search for faces within a single image. Once faces are found it is trained using KNN (K Nearest Neighbor) classifier. New images are compared with pre-existing images stored in the database using the KNN algorithm. Attendance is automatically recorded when the faces are matched, if not either the student is new and it is added in database or it is declared as a false attendance i.e., proxy. In this way accuracy is also maintained, thus making attendance process easier and efficient.
Keywords: Android Application, Database, Face Detection, Face Recognition, Machine learning.