Real time attendance system using facial recognition:
Our Automated Attendance System employs facial recognition technology for streamlined tracking, achieving 85% accuracy. Utilizing a Tkinter UI, it automates enrollment, model training, and real-time attendance capture. Data is managed in MongoDB and CSV backends, ensuring efficient storage and retrieval. With features like multi-threaded model training and real-time face detection, it offers a robust solution for educational institutions.
About Our project introduces an innovative Automated Attendance System leveraging facial recognition technology to streamline traditional attendance tracking methods. Developed as a fourth-year project, this system aims to eradicate manual efforts associated with attendance monitoring, achieving an impressive accuracy rate of approximately 85%. The system, tailored initially for English and Hindi lectures, exhibits scalability to accommodate additional subjects seamlessly. Operated through a user-friendly Tkinter interface, the system automates processes from student enrollment to attendance capture, utilizing Keras Sequential layers and a Softmax function for model training. Data management is facilitated through MongoDB and CSV backends, ensuring efficient storage and retrieval of attendance records. By eliminating manual tasks and providing real-time attendance tracking, our system offers a sophisticated solution to enhance administrative efficiency within educational institutions.
Features Implements advance neural network method. A framework based application for deployment purpose. High scalability. Less time complexity. A specific scope of Chatbot response model, using json data format.
Requirements Operating System: Requires a 64-bit OS (Windows 10 or Ubuntu) for compatibility with deep learning frameworks. Development Environment: Python 3.6 or later is necessary for coding the sign language detection system. Deep Learning Frameworks: TensorFlow for model training, MediaPipe for hand gesture recognition. Image Processing Libraries: OpenCV is essential for efficient image processing and real-time hand gesture recognition. Version Control: Implementation of Git for collaborative development and effective code management. IDE: Use of VSCode as the Integrated Development Environment for coding, debugging, and version control integration. Additional Dependencies: Includes scikit-learn, TensorFlow (versions 2.4.1), TensorFlow GPU, OpenCV, and Mediapipe for deep learning tasks.
Output
Output1 - Graphical user Interface
Output2 - Collecting images and training model
Detection Accuracy: 85% Note: These metrics can be customized based on your actual performance evaluations.
Results and Impact This project presents a sophisticated automated attendance systemleveraging facial recognition technology, designed to alleviate the manual workloadassociated with traditional attendancetracking methods. Achieving an impressiveoverall accuracy of approximately85%, albeit sensitive to lighting conditions, thesystem offers a seamless solutionforeducational institutions. Throughauserfriendly Tkinter interface, it enableseffortless enrollment of students intoMongoDB and CSV databases, streamliningthe administrative process fromdatageneration to attendance capture. Byintegrating Keras Sequential layers withaSoftmax function at the output layer, themodel ensures robust training, pavingtheway for reliable attendance management across English and Hindi lectures.
This project serves as a foundation for future developments in assistive technologies and contributes to creating a more inclusive and accessible digital environment.
Articles published / References Joseph, J. and Zacharia, K.P. (2013). "Automatic attendance management system using face recognition." International Journal of Science and Research, vol. 2, no. 11, pp. 327-330. Mohamed, B.K. and Rahul, C. (2012). "Fingerprint attendance system for classroom needs." Proceedings of the Annual IEEE India Conference (INDICON), pp. 433-438. Sawhney, S., Kacker, K., Jain, S., Singh, S.N., and Garg, R. (2019). "Real-time smart attendance system using face recognition techniques." Proceedings of the 9th International Conference on Cloud Computing, Data Science & Engineering, pp. 522-525. Aljasim, M. and Kashef, R. (2022). "E2DR: a deep learning ensemble-based driver distraction detection with recommendations model." Sensors, vol. 22, no. 5, pp. 1858.