Issuu

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 09 Issue: 05 | May 2022

p-ISSN: 2395-0072

www.irjet.net

ATTENDANCE MANAGEMENT VIA FACIAL RECOGNITION Aditya Sengar1, Mrityunjay Mishra2, Naveen Kumar Yadav3, Vikas Malviya4 Under the guidance of

Gagandeep Singh : Assistant Professor LOVELY PROFESSIONAL UNIVERSITY ---------------------------------------------------------------------***---------------------------------------------------------------------

PCA, Eigenfaces, image processing, and a micro-controller. The system works with facial picture data, and a suitable method that works with the systems’ orientation is required. A. Patil and colleagues introduced a face identification approach for attendance marking based on Haar cascades and the Viola-Jones algorithm. The system of artificial neural networks was proposed , which is both secure and simple. PCA was used to extract facial data, as well as training and testing. In which neural networks are achieved, the system operates in several orientations. M. Kalyani.K and Veera-Muthu proposed a 3D face recognition method for the system for managing attendance, each student’s attendance was recorded in the monthly timeframe. There is an urgent need for a new algorithm that can improve the identification of oriented faces. The PCA algorithm was used to create an effective attendance management system that attained a precision of up-to 83 percent, but the system’s performance was disturbed by minute changes in lighting conditions. The author introduced an eigenface technique along with PCA algorithm for marking facial recognition attendance systems, and they mentioned comparisons of various facial recognition algorithms. Overall, keeping a record of attendance was a good idea.

Abstract - Bio-metric authentication is being widely

used and it is replacing traditional systems with its main features being fast and reliable. There are different methods for biometric security such as systems based on fingerprint scanners, facial recognition, iris scanner, and voice recognition. Fingerprint scanner is extensively used in most the places for purpose of authentication but their major drawback can be hygiene. Facial recognition is emerging as a popular technology in this era. There has been a significant advancement in the field of facial recognition for the purpose of biometric security. It is really challenging to remember different passwords for various accounts, but in the system which uses facial recognition we don’t have to remember the passwords, we become the password. Facial recognition is majorly used in fields of defense, security, smartphones, and banking, but this system can be further developed to be incorporated into our day-to-day life for attendance marking in schools and offices and also by law enforcement to identify criminals or lawbreakers. Our project is the integration of web development, machine learning, and database with a user-friendly interface with the help of this system many organizations such as schools, and corporate office can change their conventional method of attendance management.

3. SYSTEM FEATURES

Key Words : PYTHON; FACE RECOGNITION; IMAGE PROCESSING; DJANGO; OPENCV; HOG+SVM

System features are highly divided into 3 modules.

1. INTRODUCTION This project attendance management system uses facial recognition for marking attendance, time of entrance, time of departure, and maintaining attendance records of students. This is an efficient replacement for the traditional attendance system that is done manually. it covers areas of computer vision (face detection, alignment, and recognition), machine learning, and web application development to implement various functionalities namely student registration, creation of dataset, training of ml model on the dataset, and view attendance reports, etc. This project can be extremely useful for maintaining attendance records in schools and various organizations.



Registration and Access Module This module works closely with related tasks For the registration of any new user in the organization, Login to the system, and managing user profile information. Using features provided by this module manager may register new users in the system and the controller/user can access both the system through their credentials.



Manage attendance information This module primarily addresses issues concerning the student’s attendance. Students can use it to record their presence, time of entrance, and time of departure in the system. Admin can view each student’s report generated by the system, and students can view their attendance report, With some filters, like filter by date and by student name.



Manage Student Records This module includes features of the user profile. By using this module admin can add a photo of the newly registered student during registration. Admin can also command the system explicitly to train the model and the system will make necessary calculations and will generate some data

2. EXISTING SYSTEM Over the last few years, a variety of attendance management systems based on facial recognition have been deployed in various organizations to enhance the performance of employees and students. J. Joseph and K Zacharia suggested a Matlab-based system that included

Impact Factor value: 7.529

ISO 9001:2008 Certified Journal

Page 1201

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 09 Issue: 05 | May 2022

p-ISSN: 2395-0072

www.irjet.net

which will be used internally to identify each student uniquely.

Input: Student’s username Output: Dataset created successfully

3.1.Manage Attendance and Login

Training the system

Student registration New Registrations can be made by the admin. Input: Student information (username and password) Output: Success message is displayed "user successfully registered".

Input: Username of student Output: The system will train a machine learning model with the available datasets created in the above process.

Login page Input: Username and password Output: If username and password are verified, the user will be directed to the dashboard Exception: If entered username and password are invalid then the system will redirect the user to the login page, and an error message is displayed.

4.1.Data Acquisition

3.2.Administer Attendance Info

Images are captured using the webcam of the laptop using the OpenCV module.

4. METHEDOLOGY

User Creation The user is created with a specific username and password. Image Capture

Marking your presence-in

Dataset Creation

Input: With the use of an integrated webcam or external webcam system will scan the student's face. Output: Registered students will be identified and system will mark students’ time of entrance to the database. A success message will be transmitted to the user.

Dataset is created to train the model. For better accuracy, 25 images of the student are captured. The captured image is stored in a folder with names specific to the respected student.

Mark your presence-out

4.2.Facial Recognition

Input: With the use of an integrated webcam or external webcam system will scan the student's face. Output: Registered students will be identified and the system will mark the student’s time of entrance to the database. A success message will be transmitted to the user. View my attendance report Students may often need to see their attendance record throughout. the month or year. Using this feature students can see their attendance record to the date. Input: User selection

Face Detection and Feature Extraction

Output: Statistical analytics of the particular student who is currently logged into the system will be displayed.

This feature is for the admin for monitoring the availability of each student to the date. i.e., how many students are present today out of total students etc. can be monitored. Input: user selection

Facial recognition is a significant aspect wherein the image captured by the camera is fed into the system, a facial recognition algorithm is used to recognize the unique faces in the input dataset, several computer vision algorithms are being used to identify faces in an image, and the location of facial landmarks is also determined. To identify different faces within a given image, we have used the HOG feature extraction algorithm.

Output: Attendance record of each student including how many students are present today along with the graph.

Face Alignment

View student’s attendance report

There are 68 distinct points on the person’s face or 68 landmarks. This step’s primary aim is to discover facial landmarks and placement of faces in the image without distorting the image.

3.3.Manage Student’s Details Adding images This feature can only be accessed by the admin, Admin can capture images of students via webcam while the registration process and create a folder with username as the folder name in face_recognition_data.

Impact Factor value: 7.529

Encoding of the Face After detecting faces in an input dataset of faces, the Extraction of uniquely identifying features from the face is an important step. Essentially, whenever we get face

ISO 9001:2008 Certified Journal

Page 1202

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 09 Issue: 05 | May 2022

p-ISSN: 2395-0072

www.irjet.net

Admin

localization, the 128 specific facial features were extracted from each image from the input dataset, and all these 128d facial features are saved in a 23 data file for face recognition. Face recognition The final stage of the face detection and recognition procedure. We used one of the most effective learning techniques, deep metric learning, being highly accurate and competent in producing real-value featureovectors. This system validates the faces by building the 128-d embedding for each one. The Euclidean distance between the face in the image and all faces in the dataset is computed using an internally compare-faces function. If the current image matches the 70 percent threshold in the entire dataset, it will proceed to attendance marking.

Admin can perform following tasks:-

4.3.Marking Attendance

   

The system will recognize the user uniquely and will mark the student’s time of departure in the database. Success Message will be received by the user. The attendance record of each student including the number of students present today out of the total along with the graph will be displayed.

Admin can register new students Add photos of students Train the model using dataset View attendance reports of all students

5. RESULTS

Training Dataset

Home Page

Smart Attendance Management System is effective and efficient. On the home page, the user can mark his attendance with options to mark the arrival and departure time. The system works flawlessly after the registration process of a student is completed by the admin.

The system will train the machine learning model on the available dataset of images of students. After training, the system will be capable of identifying students distinctively.

Marking Attendance in

If the username and password are correct, the user will be taken to the system’s dashboard. If the username and password en?tered are invalid, the user will be routed to the login page with an error notice.

The system will uniquely identify the user and will mark his/her arrival time in the database. A success message will be received by the user.

Marking Attendance out The system will uniquely identify the user and will mark his/her departure time in the database. A success message will be received by the user.

Impact Factor value: 7.529

ISO 9001:2008 Certified Journal

Page 1203

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 09 Issue: 05 | May 2022

p-ISSN: 2395-0072

www.irjet.net

View Attendance report

Statistical analytics of the particular employee who is currently logged into the system will be displayed.

[3]

Selvi, K. Senthamil, P. Chitrakala, and A. Antony Jenitha. "Face recognition based attendance marking system." Corresponding Author: S. Rajkumar*, Email: rajkumarsrajkumar@ gamil. com (2014).

[4]

Joseph, Jomon, and K. P. Zacharia. "Automatic attendance management system using face recognition." International Journal of Science and Research (IJSR) 2.11 (2013): 327- 330.

[5]

Patil, Ajinkya, and Mrudang Shukla. "Implementation of classroom attendance system based on face recognition in class." International Journal of Advances in Engineering Technology 7.3 (2014): 974.

[6]

Kanti, Jyotshana, and Shubha Sharm. "Automated Attendance using Face Recognition based on PCA with Artificial Neural Network." International journal of science and research IJSR(2012).

[7]

MuthuKalyani, K., and A. VeeraMuthu. "Smart application for AMS using face recognition." Computer Science Engineering 3.5 (2013): 13.

[8]

Deshmukh, Badal J., and Sudhir M. Kharad. "Efficient Attendance Management: A Face Recognition Approach." (2014).

[9]

Wagh, Priyanka, et al. "Attendance system based on face recognition using eigen face and PCA algorithms." 2015 International Conference on Green Computing and Internet of Things (ICGCIoT). IEEE, 2015.

About us

Description about the project, details of team members, and contact form to reach out.

[10] Bhattacharya, Shubhobrata, et al. "Smart Attendance

Monitoring System (SAMS): A Face Recognition Based Attendance System for Classroom Environment." 2018 IEEE 18th Inter?national Conference on Advanced Learning Technologies (ICALT). IEEE, 2018.

3. CONCLUSIONS Attendance via facial recognition is a great replacement for the traditional Attendance marking system (manual). Concepts of facial recognition for marking attendance of students and making the system more efficient. The system can detect faces effectively with different positions and performs efficiently. The system has some limitations sometimes it fails to recognize faces from long distances, and it is less optimized with a low configuration system, but this can be resolved by the use of devices with high computing power. In-short facial recognition is the future of biometric security.

[11] Samet,

Refik, and Muhammed Tanriverdi. "Face recognition-based mobile automatic classroom atten?dance management system." 2017 International Conference on Cyberworlds (CW). IEEE, 2017.

[12] Li,

Xiang-Yu, and Zhen-Xian Lin. "Face recognition based on HOG and fast PCA algorithm." The Euro-China Conference on Intelligent Data Analysis and Applications. Springer, Cham, 2017.

REFERENCES [1]

[2]

[13] Arsenovic,

Marko, et al. "FaceTime—Deep learning based face recognition attendance system." 2017 IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY). IEEE, 2017.

Kar, Nirmalya, et al. "Study of implementing automated attendance system using face recognition technique." International Journal of computer and communication engineering 1.2 (2012): 100.

[14] Rekha, N., and M. Z. Kurian. "Face detection in real time

based on HOG." International Journal of Advanced Research in Computer Engineering Technology (IJARCET) 3.4 (2014): 1345-1352.

RoshanTharanga, J. G., et al. "Smart attendance using real time face recognition (smart-fr)." Department of Electronic and Computer Engineering, Sri Lanka Institute of Information Technology (SLIIT), Malabe, Sri Lanka (2013)

Impact Factor value: 7.529

[15] Kwolek, Bogdan. "Face detection using convolutional

neural networks and Gabor filters." International

ISO 9001:2008 Certified Journal

Page 1204

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 09 Issue: 05 | May 2022

p-ISSN: 2395-0072

www.irjet.net

Conference on Artificial Neural Networks. Springer, Berlin, Heidelberg, 2005. [16] Ashwini, C., et al. "An Efficient Attendance System Using

Local Binary Pattern and Local Directional Pattern." Journal of Network Communications and Emerging Technologies (JNCET) www. jncet. org 8.4 (2018). [17] Karnalim,

Oscar, et al. "Face-face at classroom environment: Dataset and exploration." 2018 Eighth International Confer?ence on Image Processing Theory, Tools and Applications (IPTA). IEEE, 2018.

[18] Mian,

Ajmal. "Realtime face detection and tracking using a single pan, tilt, zoom camera." 2008 23rd International Con?ference Image and Vision Computing New Zealand. IEEE, 2008.

[19] Mehta,

Preeti, and Pankaj Tomar. "An Efficient Attendance Management Sytem based on Face Recognition using Matlab and Raspberry Pi 2." International Journal of Engineering Technology Science and Research IJETSR 3.5 (2016): 71-78.

Impact Factor value: 7.529

ISO 9001:2008 Certified Journal

Page 1205