Manual classroom attendance is a very time consuming and inconvenient task that is often required for classes at any level of education. By reducing the time taken for conducting such attendance, this will increase the available time for teaching the course contents. Therefore, automating classroom attendance will benefit both the educator and the student since it does not require user input and is much faster.
This work researches and builds an efficient solution for automating classroom attendance using Face Recognition. The system initially captures 100 pictures of each student’s face and labels them with the student’s name, after which the same images are used to train the face recognition algorithm. Prior to each lecture, the student stands in front of the camera so that an image of their face can be captured and recognized by the system. After recognition process is complete (i.e. the algorithm assigns a name to each captured face), their names, date and timestamp will be recorded in an excel sheet and be sent as an email attachment. Additionally, a face detection algorithm is used to locate the face for each image inserted in the system. The existing model was executed on a PC but was originally developed to run on the Raspberry PI.
After this system was fully functional, alternate algorithms were implemented and their efficiency was tested using a local dataset. The results were then saved and evaluated via a spreadsheet. Testing the algorithms on frontal face pictures resulted in 100% identification accuracy for each algorithm, while when they were tested on different face poses all the algorithms obtained 99% identification accuracy. The ideal algorithm for this type of system would be the one with the highest speed since reducing the time taken is essential for lectures to always start on time.
![](https://ictprojects.mt/wp-content/uploads/2022/07/BarbaraCristina_300301L_image1.png)
![](https://ictprojects.mt/wp-content/uploads/2022/07/BarbaraCristina_300301L_image2-1024x264.jpg)
Student: Cristina Barbara
Course: B.Sc. IT (Hons.) Software Development
Supervisor: Prof. John Abela