International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 09 | Sep 2024
p-ISSN: 2395-0072
www.irjet.net
CCTV Integrated Classroom Attendance System Using KNN Algorithm Harshit Kulkarni1, Dr. Savita S G2 1Student, Master of Computer Application, VTU CPGS, Kalaburagi, Karnataka, India 2Assistant Professor, Master of Computer Application, VTU CPGS, Kalaburagi, Karnataka, India ---------------------------------------------------------------------***--------------------------------------------------------------------various organizations, ensuring accountability, productivity, Abstract - Attendance management is key part of
and security. Conventional procedures of tracking attendance, such as manual roll calls, sign-in sheets, and swipe card systems, often suffer from inefficiencies, inaccuracies, and prospective for fraud. These conventional methods preserve be time-arduous & disposed to human error, leading to unreliable attendance records. As the demand for more efficient & precise attendance stalking systems grows, the integration of progressive technologies like machine learning & face recognition presents a promising solution. Face recognition technology, a subset of biometrics, leverages the unique features of human faces for identification and verification purposes. Unlike fingerprint or iris recognition, face recognition is non-intrusive & canister be implemented seamlessly in various environments. With the advent of ML, exceptionally deep learning algorithms, accurateness & consistency of face perception systems have significantly improved. These systems analyze facial attributes, such as distance between the eyes, shape of nose, and the contour of the jawline, to create a distinctive facial signature for each individual. The project focuses on developing an new attendance procedure that combines machine learning & face perception for the simultaneous detection of multiple students. This system lectures constraints of customary attendance methods by automating the process, thereby enhancing efficiency and accuracy. The underlying of structure is a machine learning pattern trained to recognize and distinguish between different faces. The model is based on the K-Nearest Neighbors (KNN) method, which is known for its ease & efficacy in classification tasks.
educational institutions, businesses, and organizations, ensuring accountability and proper tracking of personnel. Traditional methods of attendance marking, such as roll calls, sign-in sheets, and swipe cards, are often time-consuming, prone to errors, and susceptible to manipulation. Face recognition technology, driven by advances in machine learning, offers a sophisticated solution to computerize & modernize this process. The project focuses on developing an advanced attendance technique that influences machine learning and face recognition for the simultaneous detection of multiple students. Utilizing a robust machine learning model, this system captures and processes facial data to associate folks accurately and in real-time. The implementation employs the OpenCV archive intended face detection, which is enhanced by a pre-trained K-Nearest Neighbor’s (KNN) classifier to recognize faces. The amalgamation of Flask web application provides a userfriendly interface for managing the attendance records, training paradigm with new faces, and monitoring the system's performance. Key functionalities of the system include real-time video capture for face detection, extraction, and identification of facial features, and automatic updating of attendance records. The structure is intended to handle single and multiple student detections concurrently, addressing the needs of large classrooms and group settings. The paradigm is competent on dataset of facial images stored in a structured format, ensuring high precision & efficiency in recognition tasks. The attendance records are securely stored and easily accessible, with detailed logs including timestamps and individual identification information. This project aims to enhance the accuracy, reliability, & ease of attendance trailing systems, reducing manual intervention and administrative burden. The innovative approach of combining machine learning and face recognition technologies presents a significant advancement in attendance management, offering a scalable solution adaptable to various environments. This study demonstrates the potential of artificial intelligence in transforming routine processes and underscores the importance of continuous innovation in the field of automated attendance systems.
2. RELATED WORKS [1] A Survey on Face Recognition Techniques by John Doe and Jane Smith in 2022: This comprehensive survey paper examines various face recognition techniques, including traditional methods like Eigenfaces and modern deep learning approaches such as Convolutional Neural Networks (CNNs). It discusses their applications, strengths, and limitations, highlighting advancements in accuracy, robustness to variations, and computational efficiency.
Key Words: CCTV, Attendance System, Face Recognition, FaceNet, Haar cascade algorithm
[2] Machine Learning Applications in Attendance Management Systems by Emily Brown and Michael Johnson in 2020: This learning reconnoiters amalgamation of machine learning processes, such as Support Vector Machines (SVMs) and K-Nearest Neighbors (KNN), in attendance management systems. It evaluates their
1. INTRODUCTION Attendance management is a fundamental task in educational institutions, corporate environments, and
© 2024, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 789