Face and Hand Gesture Based Attendance System.
Prof. Mitali Ingle1
Assistant Professor,
Computer Science and Engineering
Jhulelal Institute Of Technology
Nagpur, India
m.ingle@jitnagpur.edu.in
Ms. Shradha Jhaade2
Assistant Professor,
Computer Science and Engineering
Jhulelal Institute Of Technology
Nagpur, India
Lokesh Nandurkar5
Computer Science and Engineering
Jhulelal Institute Of Technology
Nagpur, India
lokeshnandurkar8@gmail.com
Vaishnavi Agrawal3
Computer Science and Engineering
Jhulelal Institute Of Technology
Nagpur, India
pcagrawal75@gmail.com
Yuvraj Pawar6
Computer Science and Engineering
Jhulelal Institute Of Technology
Nagpur, India
yp954128@gmail.com
Mayur Ugale4
Computer Science and Engineering
Jhulelal Institute Of Technology
Nagpur, India
mayurugale113@gmail.com
Chirag Milmile7
Computer Science and Engineering
Jhulelal Institute Of Technology
Nagpur, India
milmilechirag9@gmail.com
Abstract— A This research explores the application of facial recognition and hand gesture detection to automate attendance marking efficiently and accurately. The system addresses the research question: How can facial recognition and hand gesture detection be effectively utilized to automate attendance marking, ensuring accuracy and efficiency?
The methodology involves capturing facial data using OpenCV and training a K-Nearest Neighbors (KNN) model for face recognition. During attendance marking, the system detects faces and verifies raised hands using MediaPipe to prevent unauthorized entries. Attendance records are stored in CSV format, and a report generation module processes these records to create PDF attendance reports.
Key findings indicate that the system successfully automates attendance with minimal manual intervention. Face recognition using KNN provides reliable identification, while gesture detection enhances security. The structured data storage ensures easy retrieval and report generation.
In conclusion, this system offers a cost-effective and efficient alternative to traditional attendance methods, reducing manual errors and enhancing accuracy. Future improvements could include integrating deep learning models for better recognition and cloud-based storage for real-time access, making it even more robust for educational and corporate use.
Keywords: Automated Attendance System, Facial Recognition, Hand Gesture Detection, Machine Learning, K-Nearest Neighbors (KNN), MediaPipe, Computer Vision, Biometric Authentication, Attendance Tracking, Artificial Intelligence.
