A CNN Based Attendance Management System Using Face Recognition

In the present era of digital advancements, face recognition technology is utilized across various industries. It serves as a popular biometric solution for ensuring detection and recognition. Despite having relatively lower accuracy compared to other biometric methods such as iris or fingerprint re...

Full description

Saved in:
Bibliographic Details
Published in2023 4th International Conference on Smart Electronics and Communication (ICOSEC) pp. 880 - 884
Main Authors Kushwaha, Kishan, Rahul, Sakala, Eliyaz, Shaik, Reddy, Chaitanya, K, Amarendra, Rao, TK Rama Krishna
Format Conference Proceeding
LanguageEnglish
Published IEEE 20.09.2023
Subjects
Attendance system
CNN encodings
Face detection
Face recognition
Industries
Machine learning
Streaming media
Support vector machines
Training
Online AccessGet full text

Cover

More Information
Summary:In the present era of digital advancements, face recognition technology is utilized across various industries. It serves as a popular biometric solution for ensuring detection and recognition. Despite having relatively lower accuracy compared to other biometric methods such as iris or fingerprint recognition, face recognition remains widely adopted due to its non-intrusive and touchless nature. Moreover, it offers a valuable application in streamlining attendance management within educational institutions, colleges, and offices by eliminating the time-consuming manual processes that often result in proxy attendance. The solution is designed to develop a class attendance system that makes use of facial recognition technologies. The system consists of four main steps: creating a database, using face detection technology to identify individuals in the vicinity, comparing the facial features of the detected individuals with those in the database, and updating attendance records based on the recognition results. This will allow the system to keep track of which individuals were present at the given location and time. Images of the class are taken to establish the database. In this paper we have used CNN encodings to measure the face images and we used SVM classifier also. The system is designed to detect and recognize faces in real-time from classroom's live streaming video. At the end of the session, the attendance information is automatically sent via mail to the respective faculty member.
DOI:10.1109/ICOSEC58147.2023.10276353