See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/379784132

MACHINE LEARNING APPROACH FOR FACE RECOGNITION BASED

ATTENDANCE SYSTEM

Article in Cailiao Kexue yu Gongyi/Material Science and Technology · February 2024

CITATIONS READS

0 148

1 author:

Kiran Kumar Kommineni

Chalapathi Institute of Technology
27 PUBLICATIONS 272 CITATIONS

SEE PROFILE

All content following this page was uploaded by Kiran Kumar Kommineni on 13 April 2024.

The user has requested enhancement of the downloaded file.

Vol.23 No.02
Feb, 2024 MATERIAL SCIENCE AND TECHNOLOGY

MACHINE LEARNING APPROACH FOR FACE RECOGNITION BASED

ATTENDANCE SYSTEM
1
Dr K.Kiran Kumar, Professor, Department of CSE, Chalapathi Institute of Technology, Guntur.
2
Yarra Sai Naga Lakshmi, B.Tech, Department of CSE, Chalapathi Institute of Technology, Guntur.
3
Mukkarala Mahesh Babu, B.Tech, Department of CSE, Chalapathi Institute of Technology, Guntur.
4
Tammisetti Vamsi, B.Tech, Department of CSE, Chalapathi Institute of Technology, Guntur.
5
Vamaraju Lakshmi Haripriya, B.Tech, Department of CSE, Chalapathi Institute of Technology, Guntur.

Abstract: In this project we have implemented the automated attendance system using Python . We have projected our
ideas to implement “Student Attendance System Based on Facial Recognition”, in which it imbibes large applications. The
application includes face identification, which saves time and eliminates chances of proxy attendance because of the face
authorization. Hence, this system can be implemented in a field where attendance plays an important role. Face is the
representation of one’s identity. Hence, we have proposed an automated student attendance system based on face
recognition. Face recognition system is very useful in life applications especially in security control systems. We are living
in a world where everything is automated and linked online. The internet of things, image processing, and machine
learning are evolving day by day. Many systems have been completely changed due to this evolve to achieve more
accurate results. The attendance system is a typical example of this transition, starting from the traditional signature
on a paper sheet to face recognition. This Project proposes a method of developing a comprehensive embedded
class attendance system using facial recognition with showing whether the face of the person is the student for that
specified class or not. The system is based on the machine learning algorithm which is to be implemented on python
language and using computer/laptop camera for the input image of the students or a normal outer camera can also be used
which has to be connected to the system which is programmed to handle the face recognition by implementing the
Local Binary Patterns algorithm LBPs.The average accuracy of recognition is 100 % for good quality images, 94.12 % of
low-quality images and 95.76 % for Yale face database when two images per person are trained.

1. INTRODUCTION proposes that the system is based on face detection and

The main objective of this project is to develop face recognition algorithms, which is used to automatically
recognition based student attendance system. In order to detects the student face when he/she enters the class and
achieve better performance, the test images and training the system is capable to marks the attendance by
images of this proposed approach are limited to frontal and recognizing him.In this proposed system the student is
upright facial images that consist of a single face only. The requested to stand in front of the camera to detect and
test images and training images have to be captured by recognize the iris, for the system to mark attendance for the
using the same device to ensure no quality difference. In student. Face recognition is crucial in daily life in order to
addition, the students have to register in the database to be identify family, friends or someone we are familiar with.
recognized. The enrolment can be done on the spot through We might not perceive that several steps have actually
the user-friendly interface.In today's networked world, the taken in order to identify human faces. Human intelligence
need to maintain the security of information or physical allows us to receive information and interpret the
property is becoming both increasingly important and information in the recognition process. We receive
increasingly difficult. From time to time we hear about the information through the image projected into our eyes, by
crimes of credit card fraud, computer breakin's by hackers, specifically retina in the form of light. Light is a form of
or security breaches in a company or government building. electromagnetic waves which are radiated from a source
In most of these crimes, the criminals were taking onto an object and projected to human vision. Robinson-
advantage of a fundamental flaw in the conventional access Riegler, G., & Robinson-Riegler, B. (2008) mentioned that
control systems: the systems do not grant access by "who after visual processing done by the human visual system,
we are", but by "what we have", such as ID cards, keys, we actually classify shape, size, contour and the texture of
passwords, PIN numbers, or mother's maiden name. None the object in order to analyse the information. The analysed
of these means are really define us. Recently, technology information will be compared to other representations of
became available to allow verification of "true" individual objects or face that exist in our memory to recognize. In
identity. This technology is based in a field called fact, it is a hard challengeto build an automated system to
"biometrics".The idea of two technologies namely Student have the same capability as a human to recognize faces.
Attendance and Feedback system has been implemented However, we need large memory to recognize different
with a machine learning approach. This system faces, for example, in the Universities, there are a lot of
automatically detects the student performance and students with different race and gender, it is impossible to
maintains the student's records like attendance and their remember every face of the individual without making
feedback on the subjects like Science, English, etc. mistakes. In order to overcome human limitations,
Automated Attendance System using Face Recognition computers with almost limitless memory, high processing
http://materialsciencetech.com/mst/ ISSN: 1005-0299
Material Science and Technology ·66·

speed and power are used in face recognition systems. The face recognition problem. Many studies on face recognition
human face is a unique representation of individual were then conducted continuously until today (Ashley
identity. Thus, face recognition is defined as a biometric DuVal, 2012).
method in which identification of an individual is
performed by comparing real-time capture image with 2. LITERATURE SURVEY
stored images in the database of that person (Margaret
Rouse, 2012). To maintain the attendance record with 1)Stress and anxiety detection using facial cues from
day-to-day activities is a challenging task. The videos. AUTHORS:G. Giannakakis, D. Manousos, F.
conventional method of calling name of each student is Chiarugi
time consuming and there is always a chance of proxy This study develops a framework for the detection and
attendance. The following system is based on face analysis of stress/anxiety emotional states through video-
recognition to maintain the attendance record of students. recorded facial cues. A thorough experimental protocol
The daily attendance of students is recorded subject wise was established to induce systematic variability in affective
which is stored already by the administrator. As the time states (neutral, relaxed and stressed/anxious) through a
for corresponding subject arrives the system automatically variety of external and internal stressors. The analysis was
starts taking snaps and then apply face detection and focused mainly on non-voluntary and semi-voluntary facial
recognition technique to the given image and the recognize cues in order to estimate the emotion representation more
students are marked as present and their attendance update objectively. Features under investigation included eye-
with corresponding time and subject id. We have used related events, mouth activity, head motion parameters and
deep learning techniques to develop this system, heart rate estimated through camera-based photo
histogram of oriented gradient method is used to plethysmography. A feature selection procedure was
detect faces in images and deep learning method is used employed to select the most robust features followed by
to compute and compare feature facial of students to classification schemes discriminating between
recognize them. Our system is capable to identify multiple stress/anxiety and neutral states with reference to a relaxed
faces in real time. The main objective of this project is to state in each experimental phase. In addition, a ranking
develop face recognition based automated student transformation was proposed utilizing self reports in order
attendance system. In order to achieve better performance, to investigate the correlation of facial parameters with a
the test images and training images of this proposed participant perceived amount of stress/anxiety. The results
approach are limited to frontal and upright facial images indicated that, specific facial cues, derived from eye
that consist of a single face only. The test images and activity, mouth activity, head movements and camera based
training images have to be captured by using the same heart activity achieve good accuracy and are suitable as
device to ensure no quality difference. In addition, the discriminative indicators of stress and anxiety.
students have to register in the database to be recognized. 2) Attendance System Based on Facial Recognition
The enrolment can be done on the spot through the user- Automated Attendance System Based on Facial
friendly interface.Nowadays, face recognition system is Recognition AUTHORS: S R Dhanush
prevalent due to its simplicity and awesome performance. In this project we have implemented the automated
For instance, airport protection systems and FBI use face attendance system using python . We have projected our
recognition for criminal investigations by tracking ideas to implement “Automated Attendance System Based
suspects, missing children and drug activities (Robert Silk, on Facial Recognition”, in which it imbibes large
2017). Apart from that, Facebook which is a popular social applications. The application includes face identification,
networking website implement face recognition to allow which saves time and eliminates chances of proxy
the users to tag their friends in the photo for entertainment attendance because of the face authorization. Hence, this
purposes (Sidney Fussell, 2018). Furthermore, Intel system can be implemented in a field where attendance
Company allows the users to use face recognition to get plays an important role. I am also adding the link to the
access to their online account (Reichert, C., 2017). Apple code I used for the project since a lot of students have
allows the users to unlock their mobile phone, iPhone X by asked me the codes so far.
using face recognition (deAgonia, M., 2017). The work on 3) Reconstruction of Human Faces from Its Eigenfaces
face recognition began in 1960. Woody Bledsoe, Helen AUTHORS:Subhajit Bhattacharyya
Chan Wolf and Charles Bisson had introduced a system Eigenface or Principal Components Analysis (PCA)
which required the administrator to locate eyes, ears, nose methods have demonstrated their success in face
and mouth from images. The distance and ratios between recognition, detection and tracking. In this paper we have
the located features and the common reference points are used this concept to reconstruct or represent a face as a
then calculated and compared. The studies are further linear combination of a set of basis images. The basis
enhanced by Goldstein, Harmon, and Lesk in 1970 by images are nothing but the eigenfaces. The idea is similar
using other features such as hair colour and lip thickness to to represent a signal in the form of a linear combination of
automate the recognition. In 1988, Kirby and Sirovich first complex sinusoids called the Fourier Series. The main
suggested principle component analysis (PCA) to solve
Material Science and Technology ·67·

advantage is that the number of eigenfaces required is less absent

than the number of face images in the database. Selection The objective of this project is to develop face recognition
of number of eigefaces is important here. Here we based automated student attendance system. Expected
investigate what is the number of minimum eigenface that achievements in order to fulfill the objectives are:
is required for faithful production of a face image. • To detect the face segment from the video
ArunKatara et al. (2017) mentioned disadvantages of RFID frame.
(Radio Frequency Identification) card system, fingerprint • To extract the useful features from the face
system and iris recognition system. RFID card system is detected.
implemented due to its simplicity. However, the user tends • To classify the features in order to recognize
to help their friends to check in as long as they have their the face detected.
friend’s ID card. The fingerprint system is indeed effective • To record the attendance of the identified
but not efficient because it takes time for the verification student.
process so the user has to line up and perform the SYSTEM ARCHITECTURE
verification one by one. However for face recognition, the
human face is always exposed and contain less information
compared to iris. Iris recognition system which contains
more detail might invade the privacy of the user. Voice
recognition is available, but it is less accurate compared to
other methods. Hence, face recognition system is suggested
to be implemented in the student attendance system.
3. EXISTING SYSTEM
To develop an attendance system using face recognition.
Concept In a classroom with large number of students, it is
a very tedious and time-consuming task to take the
attendance manually. Therefore, we can implement an
effective system which will mark the attendance of
students automatically by recognizing their faces. The
process of this face recognition system is divided into
various steps, but the important steps are detection of
face and recognition of face. Firstly, to mark the
attendance of students, the image of students’ faces will be 
required. This image can be snapped from the camera Fig 1: System Architecture
device, which will be placed in the classroom at a
suitable location from where the whole classroom can be
5. MODULES
covered. This image will act as input to the system. For the
effective face detection, the image needs to be MODULES:
enhanced by using some image processing techniques
like grayscale conversion of image and histogram  Admin
equalization. To identify the students sitting on the last  Face Detection And Recognition
rows neatly, the histogram equalization of image needs to
be done. Hence, there is a need to develop a real  OPENCV
time operating student attendance system which means Admin:
the identification process must be done within defined Admin can login with his credentials. Once he login he can
time constraints to prevent omission. The extracted activate the Students data. The activated students only
features from facial images which represent the identity allow the attends in our applications. The admin can set the
of the students have to be consistent towards a change training and testing data for the project dynamically to the
in background, illumination, pose and expression. code. The admin can view all users detected results in hid
4. PROPOSED SYSTEM frame. By clickingan hyperlink in the screen he can detect
The proposed System is to capture the face of each the emotions of the images. . The dataset in the excel
student and to store it in the database for their attendance. format. By authorized persons we can increase the dataset
The face of the student needs to be captured in such a size according the imaginary values.
manner that all the feature of the students' face needs are FACE DETECTION AND RECOGNITION:
recorded and analyzed to the existing record. The main Dataset contains grid view of already stored dataset
working principle of the project is that, the video captured consisting numerous properties, by Property Extraction
data is converted into image to detect and recognize it. newly designed dataset appears which contains only
Further the recognized image of the student is provided numerical input variables as a result of Principal
with attendance, else the system marks the database as Component Analysis feature selection transforming A
Material Science and Technology ·68·

facial recognition system[1] is a technology capable of

matching a human face from a digital image or a video
frame against a database of faces. Such a system is
typically employed to authenticate users through ID
verification services, and works by pinpointing and
measuring facial features from a given image
OPENCV:
Opencv is the huge open-source library for the computer
vision, machine learning, and image processing and now it
plays a major role in real-time operation which is very
important in today’s systems. By using it, one can process
images and videos to identify objects, faces, or even Fig 6.3 Capture the student face
handwriting of a human. When it integrated with various In above screen shows the capturing the student face for
libraries, such as NumPy, python is capable of processing
taking the attendance.
the Opencv array structure for analysis. To Identify image
pattern and its various features we use vector space and
perform mathematical operations on these features, from
the original image, lots of pieces of information that are
present in the original image can be obtained. Like in the
above image there are two faces available and the person(I)
in the images wearing a bracelet, watch, etc so by the help
of Opencv we can get all these types of information from
the original image. It’s the basic introduction to Opencv we
can continue the Applications and all the things in our
upcoming articles.
6. RESULTS
6.1 Output Screens
Fig 6.4 Attendance Report
In abovsssssse screen shows the attendance report for the
students.
7. CONCLUSION
A face recognition based automated student attendance
system is thoroughly described. The proposed approach
provides a method to identify the individuals by comparing
their input image obtained from recording video frame with
respect to train image. This proposed approach able to
detect and localize face from an input facial image, which
Fig6.1 run the manage.py server file is obtained from the recording video frame. Besides, The
goal of the project was to build a facial recognition system
In the above screen is the to run the manage.py server file
for student’s attendance. Concepts of facial recognition is
in the command prompt. heavily discussed in this thesis. Similarly, web
development with Django is also discussed, followed by
examples of implementation and explanations. The result
of the project was a successful prototype of a facial
recognition system where the admin can create a teacher
account and add students and their information to the
database. Teachers then can log in to the system and take
attendance of the student. The student’s face is detected by
a camera and attendance is recorded in the database.
Teachers and admin could see the attendance report of the
students. Overall, the project was successful in its can be
implemented in Django to create a web application. Once
Fig 6.2 Attendance sheet implemented, it can be used to take attendance of students
In above screen shows the attendance sheet for the student. and keep track of their attendance records. This project has
the potential for further development in the future by
adding more features for students and teachers. More
 Material Science and Technology ·69·

features such as assignments, results, and grades could be

added.
FUTURE ENHANCEMENT
Automated Attendance System has been envisioned for the
purpose of reducing the drawbacks in the traditional
(manual) system. This attendance system demonstrates the
use of image processing techniques in classroom. This
system can not only merely help in the attendance system,
but also improve the goodwill of an institution.
8. REFERENCES
[1] Michael Dobson, Douglas Ahlers, Bernie DiDario,
<Attendance Tracking System", United States Patent
Application Publication, Pub. No.: US 2006/0035205
A1, Feb.16, 2006.
[2] NaveedKhan Balcoh, M. HaroonYousaf, Waqar
Ahmad and M. IramBaig, <Algorithm for Efficient
Attendance Management: Face Recognition based
approach=, IJCSI International Journal of Computer
Science Issues, Vol. 9, Issue 4, No 1, pp.146-150, July
2012.
[3] O. Shoewu and O.A. Idowu, <Development of
Attendance Management System using Biometrics ", The
Pacific Journal of Science and Technology, Vol. 13,
Number1, pp.300- 307, May 2012 (Spring).
[4] DamirDemirovic, Emir Skejic , Amira Serfovic,
<Performance of some images processing algorithms in
TensorFlow=, computer vision and pattern recognition, pp,
799- 778, 2018.
[5] http://www.openCV.org
[6] Hapani, Smit, et al. "Automated Attendance
System Using Image Processing." 2018 Fourth
International Conference on Computing Communication
Control and Automation (ICCUBEA). IEEE, 2018.
[7] S. Bahrampour, N. Ramakrishnan, L. Schott. And
M. Shah, M. Comparative Study of Caffe, Neon,
Theano, and Torch for Deep Learning<. CoRR,
abs/1511.06435. 2015.
[8] I. K. Park, N. Singhal, M. H. Lee, S. Cho and C.
Kim, "Design and Performance Evaluation of Image
Processing Algorithms on GPUs," in IEEE Transactions on
Parallel and Distributed Systems, vol. 22, no. 1, pp. 91-
104, Jan. 2011.
[9] K. K. Kumar, S. G. B. Kumar, S. G. R. Rao and S. S. J.
Sydulu, "Safe and high secured ranked keyword searchover
an outsourced cloud data," 2017 International Conference
on Inventive Computing and Informatics (ICICI),
Coimbatore, India, 2017, pp. 20-25, doi:
10.1109/ICICI.2017.8365348.
[10] K. K. . Kommineni and A. . Prasad, “A Review on
Privacy and Security Improvement Mechanisms in
MANETs”, Int J Intell Syst Appl Eng, vol. 12, no. 2, pp.
90–99, Dec. 2023.
[11] Kiran Kumar Kommineni, Ratna Babu Pilli, K.
Tejaswi, P. Venkata Siva, Attention-based Bayesian
inferential imagery captioning maker, Materials Today:
Proceedings, 2023, , ISSN 2214-7853,
https://doi.org/10.1016/j.matpr.2023.05.231.

View publication stats