Biometric Attendance system using Face Recognition
From Dayananda Sagar University
“Biometrics is certainly the most secure form of authentication, It is hardest to imitate and duplicate”
A Quick Introduction:
In this model, we are using the biometric-based attendance system to mark the attendance of the students automatically by detecting and recognizing their faces. The face detection and recognition system is developed using python along with the OpenCV package. This system contains three modules which are detection, training and recognition. The model we are using is cascade classifiers which is basically used to train the images. This method helps reducing complexity of the system.
The facial recognition system is a real-time and contact-less attendance tracking software exceptionally relevant in the current pandemic situation.
So the main purpose of this project is to build a biometric face recognition-based attendance monitoring system for the universities to enhance and upgrade the current attendance system into more efficient as compared to before as well as saving lives as well as time.
ALGORITHM:
LBPH Algorithm:- Local Binary Pattern Histogram
It is one of the simplest algorithms for face recognition. The local features of the images can be characterized by this algorithm. Using this algorithm, considerable results can be obtained. Open CV library is used to implement LBPH algorithm.
The Steps involved to achieve this are:
1. Creating dataset
2. Face Acquisition
3. Face Extraction
The images are saved in gray scale after being recorded by a camera. The LBPH recognizer is employed to coach these faces because the coaching sets the resolution and therefore the recognized face resolutions are completely different.
OpenCV Based Approach:
Open CV (Open Source Computer Vision Library) is an open source computer vision software library for the purpose of machine learning. Open CV was developed to serve the purpose of computer vision applications and to stimulate the usage of machine perception in the commercially viable products.
This model integrates a camera that captures an input image, an algorithm for detecting faces from an input image, encoding and identifying the face, marking the attendance in a spreadsheet. The training database is created by training the system with the faces of the authorized students. The cropped images are then stored as a database with respective labels. The features are extracted using LBPH algorithm. The database of all the students in the university is stored and when the face of the individual students matches with one of the faces stored in the database then the attendance is recorded with components Id, Name, Date and Time to the server.
Breakdown:
This can be explained in 4 major parts namely Registration, Face Detection, Training image, Face Recognition.
REGISTRATION:
Initially our dataset does not contain any data. To get the data the user has to register and take the image from the camera by entering the necessary details. By then all the data is stored in the data set and thus, the dataset is ready to train the images.
FACE DETECTION:
Once the registration part is done. The user will take the image and save the profile with the specified password. When the user takes the image the face is detected using the LBPH recognizer where the LBPH algorithm comes into consideration. The data will be stored in a csv file automatically.
TRAINING THE IMAGE:
Now to train the image, cascade classifiers have been used here as haar cascade classifiers are the best approach for training the image. OpenCV also helps in training the particular model that has been proposed. The images taken are multiple as it takes from all the angles till the time the camera has been closed so that the face can be easily recognized in any of the face recognition. In this way the model has been trained and saved for the best recognition.
FACE RECOGNITION:
This will be the final major step as the trained images are recognized in this step. when the camera is pop up, automatically the image is recognized from the trained dataset. After this the data is stored in csv file wherein, new separate files are created every 24 hours.
CONCLUSION:
Face recognition provide passive identification that is a person which is to be identified does not to need to take any action for its identity
Face recognition technologies have been associated generally with very costly top secure applications. Certain applications of face recognition technology are now cost effective, reliable and highly accurate.
This is the most productive OpenCV face recognition method accessible for Attendance Management. The system has been implemented using the LBPH algorithm. LBPH excels other algorithms by a confidence factor of 2–5 and has least noise interference. The implementation of the Smart Attendance System portrays the existence of an agreement between the appropriate recognition rate and the threshold value. Therefore LBPH is the most authentic and competent face recognition algorithm found in OpenCV for the identification of the students in an educational institute and marking their attendance adequately by averting proxies.
