Contactless Attendance System
Now attendance does not require you to share bacteria.
Created on 28th March 2021
•
Contactless Attendance System
Now attendance does not require you to share bacteria.
The problem Contactless Attendance System solves
Owing to the current (COVID) situation it is essential to have a system, which has minimum contact, for attendance. Biometric attendance possesses the risk of spreading bacteria among its users. So in the pursuit of a solution, we came up with an idea of taking attendance with the help of a camera sensor. The current systems were capable of processing only one user's request at a time, which was very inefficient. Hence the inspiration came from the pursuit of a solution for no contact attendance system.
Our team RTE has comeup with a solution for this. we have created a contactless attendance system which allows the user to mark himself for entry exit without actually being in contact with the device physically.
Challenges we ran into
There were many challenges that we encountered while building the project like retrieving the face images from the camera and sending them to the server for processing, recognizing multiple faces in the same image. Initially, we were sending every captured image to the server for detection, but it was too costly by bandwidth, processing and it generated an alternative log for check-in check-out consequently until the user does not leave the frame. So we found a solution by using Google Vision API which will look for a face in the image and if there is a face available then and then only the image is sent to the server. So this was a game-changing optimation. The library we have used to Recognize Face is face-recognition which is used to Recognize faces from Python. It is built using dlib’s state-of-the-art face recognition built with deep learning. The model has an accuracy of 99.38% on the Labeled Faces in the Wild benchmark.
Technologies used