International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 04 | Apr 2023
p-ISSN: 2395-0072
www.irjet.net
MTCNN BASED AUTOMATIC ATTENDANCE SYSTEM USING FACE RECOGNITION Prathap J1, Yashaswini H N2, Varsha S3, Mohammed Ibrahim Shariff4, Dr.Honnaraju B5, Ambika K B6, 1,2,3,4 UG Student, Department of Computer Science and Engineering ,Maharaja Institute Of Technology
Mysore,Karnataka,India.
5,6 Assistant Professor, Department of Computer Science and Engineering ,Maharaja Institute Of Technology
Mysore, Karnataka, India. ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Maintaining the attendance register amidst
features is an innate ability that all humans possess, and our system leverages this feature to identify faces.
daily events can be challenging, as the current practice of calling out each student's name is time-consuming and susceptible to fraud or proxy. To address this issue, a new approach based on facial recognition has been developed to secure students' attendance records. The attendance records are organized by subject and already stored by the administrator. The proposed method captures snapshots at the designated subject-specific times, performs face detection and recognition on the images, and identifies the recognized students as present, updating their attendance records with the appropriate subject ID and timestamp. The objective of this study is to suggest an automated attendance system using facial recognition technology, utilizing the MTCNN(Multi-task Cascaded Convolutional Neural Networks) method for face detection and the CNN method for facial image recognition. Additionally, Face Net and SVM are used for feature extraction and classification, respectively.
Implementing facial recognition for attendance tracking is a smart strategy for managing attendance. Compared to other methods, facial recognition is a more accurate and faster method, reducing the possibility of attendance fraud or proxy. Facial recognition also provides a non-invasive means of identification where the person being identified does not have to take any active measures to verify their identity. To achieve this, we use the MTCNN technique for face detection and feature extraction, followed by face recognition. The proposed approach involves five stages, including data preparation for training, using MTCNN for face detection from the data, embedding each face using the Face Net Keras model, classifying feature vectors using SVM, and finally conducting face recognition.
2. LITERATURE REVIEW 2.1 Automated Attendance Management System Based on Face Recognition Algorithms
Key Words: Attendance, Face Recognition, MTCNN, CNN, Face Net.
This study presents a proposed automated attendance management system that utilizes face detection and recognition algorithms to automatically identify students as they enter the classroom and mark their attendance accordingly. The paper provides a detailed description of the system's architecture and the algorithms employed at each stage. Additionally, different real-time scenarios are considered to assess the performance of various face recognition systems, while also proposing techniques to address potential security threats like spoofing. By replacing traditional attendance tracking methods, this system saves time and enhances student monitoring capabilities.
1.INTRODUCTION The traditional manual method of calling out student names is a time-intensive process, whereas the RFID card system assigns a unique card to each student, which holds their identity information, but it poses a risk of card misplacement or unauthorized use, resulting in inaccurate attendance records. Furthermore, other biometric techniques such as fingerprint, iris, or voice recognition have their limitations and are not entirely accurate. For organizations to effectively manage attendance records, they require a robust and dependable system. Our proposed solution is to automate the attendance system by utilizing face recognition technology. Given that the face is a crucial aspect of human interactions, carrying essential information about an individual, we have developed a real-time system that can recognize frontal faces of students from images captured within the classroom, streamlining the attendance process. The ability to recognize individuals from their facial
© 2023, IRJET
|
Impact Factor value: 8.226
2.2 FaceTime-Deep Learning Recognition Attendance System
Based
Face
This paper provides a detailed description of the entire process involved in developing a face recognition model. The model utilizes advanced techniques, including CNN cascade for face detection and CNN for generating face embeddings,
|
ISO 9001:2008 Certified Journal
|
Page 1827