Automated Attendance System : Recognition System Based on Facial Features

Sammanfattning: Consider a situation where you need to identify each and every person in a room and categorize each of the persons as present or absent. To mark the presence of hundreds of people in a room takes a lot of time, which means you can eventually be left out with less time to explain the main aim of that meeting, class, or some other things. In such cases, either we may need a lot of time for a meeting or we may need more people to accomplish the tasks. In the present world, time is considered equivalent to money. If you lose your time you will lose your money. Many education institutions and offices see this as a very important consideration to maintain their busy schedule.  In this study, we came to know that many institutions and offices are facing the same issue, so as engineers we decided to take this as a challenge and try to find a solution to it. Our main objective of this project is to make a working model, which helps in marking the attendances of the person automatically and saves precious time. We can say that human effort is simply replaced by our end product which helps the person to spend more time efficiently.  To replace the human effort with an easy and cost-efficient system that has accurate results, we are using a Raspberry Pi 4 Model B as a microcontroller and along with it, we are using a Raspberry Pi camera module to capture the image of the person. To control and give the commands to the microcontroller, we are using MATLAB as a programming language that interprets the commands given by the user.   Using this Raspberry Pi system with a camera module attached to the Raspberry Pi, We can capture the image of the person who comes in front of the camera. Once the person images are captured, the microcontroller starts running the program which can predict the face of a person from the pre-trained database that we have previously stored in the system. Once the prediction is done, the face of the person is automatically marked as present in an excel sheet under the predicted name.  We are concluding that by using the automated attendance system one can avoid the manual marking of persons and save time. For further future works, one can use a good resolution camera module to capture the images clearly and can use the python coding method to access face recognition. We can also develop a mobile application, that can access the camera present in the smartphone which can be used to capture the images and mark the attendances automatically.