Abstract
This study addresses the need for efficient, automated attendance systems through the design of a facial recognition application. Manual attendance systems are slow, error-prone and the retrieval of old records can be tedious. Universally assessable technological developments such as facial recognition software can easily solve these problems. However, the vast amount of computational resources required for its implementation has posed a limitation to its wide adoption. This study presents a two-step approach to resolve these challenges. By leveraging a faster, less-powerful model, as the first step, the workload of facial recognition can be distributed to save time and computational cost. A more powerful machine learning model is applied as the second step, deployed for tasks that are too complex for the first model to handle. The two-step authentication process will also reduce the occurrences of false negatives. Face_recognition, a python library is used for detection and encoding of face images read using python’s opencv library from an IP webcam. A flask application demonstrates this facial recognition functionality. The database connection and communication are accomplished using flask_sqlalchemy. A graphical user interface (web application) is used to interact with users on a high level, showing saved images of logged personnel and their times of entry. The system has a maximum accuracy of 98.78% and precision of 98.82% from tests. This shows its potential for application on a wider scale, with some added improvements such as cloud deployment and larger datasets.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call