VEL TECH HIGH

Dr. RANGARAJAN Dr. SAKUNTHALA ENGINEERING COLLEGE

TECH An Autonomous Institution

Department of Computer Science and Engineering

Face Recognition Attendance System Based on Real-Time Video Processing

MINI PROJECT REVIEW

ROUNAKDEEP (VH12403)
SINGH SARAN M S
SUKESH S T (VH12409) SUPERVISOR : PAVITHRA
II YEAR, COMPUTER SCIENCE AND
(VH12426) ASST. PROFESSOR CSE
ENGINEERING
OBJECTIV
E:
Develop a user-friendly interface for teachers and students to
streamline the attendance recording process .
ABSTRA
CT : introduces a pioneering Face Recognition Attendance System, capitalizing on
This research
real-time video processing techniques to revolutionize traditional attendance tracking. The
system seamlessly integrates advanced facial recognition algorithms with computer vision
and machine learning technologies, ensuring accurate identification of different faces. The
system captures video feeds from dedicated devices, utilizing real-time face detection
algorithms to locate and extract facial features. Deep learning-based facial recognition
models then match these features with a pre-registered database, facilitating real-time
identification. Continuous learning mechanisms enable the system to enhance recognition
accuracy over time through feedback loops and retraining with new data. With applications
across among different fields the proposed Face Recognition Attendance System
streamlines processes, reduces manual errors, and enhances security, marking a significant
advancement in attendance management. The research findings underscore the system's
effectiveness to redefine conventional attendance tracking methodologies.
INTRODUCTIO
With: the advent of the era of big data in the world and the commercial value of face
N
recognition technology, the prospects for face recognition technology are very bright and
have great market demand. This project aims to design a face recognition attendance system
based on real-time video processing. This project mainly sets directions to consider the
problems: the accuracy rate of the face recognition system in the actual check-in, the stability
of the face recognition attendance system with real-time video processing, real time
database and the interface settings of the face recognition attendance system using real-time
video processing. By analyzing the situation of these problems, the concept of attendance
system based on face recognition technology is proposed, and the research on face
recognition attendance system based on real-time video processing is carried out.
Experimental data shows that the accuracy rate of the video face recognition system is up to
82%. The face recognition time and attendance system with real-time video processing
through the above experimental certification can quickly complete the tasks of students in
the time and attendance check-in system, get rid of the complex naming phenomenon,
greatly improve the efficiency of class, and play an important role in guiding the development
of the time and attendance system.
Literature Survey 1
:Year Title of the
Author
Material or
Existing system Proposed system
research paper software used

2022 A Real-Time DEEPTI Materials: Lightweight Provide an

CNN- Based MISHRA Mobile models may overview of the
Lightweight Devices, struggle with increasing
Mobile Masked Cameras. generalizing well importance of face
Face Recognition Face to diverse datasets. recognition,
System Detection Training on a especially in the
Libraries : specific dataset context of masked
Dlib , may lead to reduced faces.
OpenCV performance when Highlight the need
faced with different for a lightweight
lighting conditions, and real-time
poses, or solution suitable
demographics. for mobile devices.
 Literature Survey 2
Year
paper
:
Title of the research Author Material or
software
Existing system Proposed
system
used
2020 Face Recognition HAO YANG and Materials: Accuracy can be Utilize advanced
Attendance System XIAOFENG Cameras, affected by face recognition
Based on Real-Time HAN Computing factors such as algorithms,
Video Processing lighting potentially
Hardware. conditions, pose incorporating
variations, and multimodal
the quality of biometrics (e.g.,
the captured facial features
images. Some combined with
systems may iris recognition)
struggle with for enhanced
accuracy in real- accuracy.
world, dynamic
environments.
 Literature Survey 3
Year : the Author
Title of Material or Existing system Proposed
research paper software used system

2020 FACE YANG LI Face Detection Implementing Based on the theory of

deep learning, we built
RECOGNITION Libraries: and maintaining the network which will
Dlib :
SYSTEM A C++ toolkit a face train the neural network
based on similarities.
with Python recognition Then we examine and
bindings, system, especially compare the available
open source data set, we
including tools one that meets chose ORL dataset and
for face
detection and high standards of trained the model with
GPU. The model will take
facial accuracy and a human face image and
landmarking. security, can be extract it into a vector.
OpenCV (Open Then the distance
Source Computer costly for between vectors are
Vision Library): organizations. compared to determine if
two faces on different
Provides tools picture belongs to the
for real-time same person.
computer
vision tasks,
including face
detection.
 Literature Survey 4
Year Title of the
research paper
:
Author Material or
software used
Existing system Proposed system

2019 Deep MUHAMMAD Programming Facial recognition Develop

Unified Model For ZEESHAN Language: systems
Face Recognition KHAN Python may exhibit
Based on accuracy and implement
advanced
Convolution disparities across
Neural Network different facial
and demographic recognition
Edge groups. Bias can algorithms
Computing occur, leading to
higher error rates
for
to improve
certain accuracy, reduce
ethnicities, false
genders, or positives/negati
age groups ves,

and
mitigate

biases across
diverse
 Literature Survey 5
Year Title of the
research paper
:
Author Material or
software used
Existing system Proposed
system

2015 Real-Time Group ABDELFATAH AREF 1. SQL. Faces may be Integration of

Face-Detection TAMIMI and 2. Cloud Services. partially or advanced face
for an Intelligent OMAIMA N.A. fully occluded detection
Class-Attendance by objects, models and
System accessories, or algorithms can
other lead to
individuals in a enhanced
group. Existing accuracy, even
systems may in crowded
struggle to and dynamic
handle such environments,
occlusions improving the
effectively. reliability of
attendance
tracking.
EXISTING
SYSTEM :
Face recognition can be traced back to the sixties and seventies of the last century,
and after decades of twists and turns of development has matured. The traditional
face detection method relies mainly on the structural features of the face and the
color characteristics of the face Some traditional face recognition algorithms
identify facial features by extracting landmarks, or features, from an image of the
subject's face. For example, as an algorithm may analyze the relative position, size,
and/or shape of the eyes, nose, cheekbones, and jaw. These features are then used
to search for other images with matching features. These kinds of algorithms can
be complicated, require of compute power, hence could be
lots
slow in performance. And they can also be
emotional
inaccurate expressions,
when the since the sizefaces
and position of the landmarks
show clear can be altered
significantly in such circumstance.
 DRAWBACK OF THE EXISTING
SYSTEM :
• The traditional face detection method relies mainly on the structural features of
the face and the color characteristics of the face.
• Some traditional face recognition algorithms identify facial features by extracting
landmarks, or features, from an image of the subject's face. For example, as shown
in Figure 1.1, an algorithm may analyze the relative position, size, and/or shape of
the eyes, nose, cheekbones, and jaw. These features are then used to search for
other images with matching features. These kinds of algorithms can be
complicated, require lots of compute power, hence could be slow in performance.
• They can also be inaccurate when the faces show clear emotional expressions,
since the size and position of the landmarks can be altered significantly in
such circumstance.
PROPOSED
SYSTEM :
We aimed to propose a real-time lightweight model as to evaluate the use of deep
learning approaches as a computational model and to compare the overall
performance of learning on small data. Besides using only full facial images, we
have also proposed a model that allows recognition from the eyes only. The
proposed model has features that can run in real-time on any mobile application or
in a local environment. In the proposed masked face recognition study, we observed
that the performance of the model decreased as the data decreased. We used pre-
trained models to increase this performance. As a result of our studies, considering
the size and test results, we used the face recognition model that we created with
pre- trained Mobile net for our mobile application. The proposed mask detection
model is highly precise and works without sacrificing speed in a mobile
environment.
FLOW
Start :
CHART
Images stored in
system database

Recognition process starts

Camera captures the users image

Check
continuously
C Doesn’t match
o Absent
m Send data to database (Firebase)
p
a Attendance
Match r
uploaded in web
e database End
Present to the student A file generated with student details
with automatically
METHODOLO
GY :
• The code implements a real-time facial recognition attendance system using OpenCV,
face recognition, and Firebase integration.
• It begins by initializing the Firebase app with credentials and specifying database and
storage URLs. The script captures video frames, locates faces, and compares them
with known encodings.
• Upon recognizing a face, it updates a background image with student information
and interacts with Firebase to retrieve and update attendance data. Different display
modes and counters control the flow of information, showing details such as total
attendance, major, and student ID.
• The system continuously operates in a loop, providing a dynamic and real-time user
interface. Cleanup involves releasing the video capture object and closing OpenCV
windows upon user input. The methodology focuses on seamless integration of facial
recognition, Firebase, and dynamic display to facilitate attendance tracking.
 MODULE 1

Haar Cascade
Algorithm
• Haar cascade is an algorithm that can detect objects in images, irrespective of
their scale in image and location.
• This algorithm is not so complex and can run in real-time. We can train a
Haar-Cascade detector to detect various objects like cars, bikes, buildings,
fruits, etc.
 MODULE
CNN: 2
In deep learning, a convolutional neural network (CNN/Conv. Net) is a class of deep
neural networks, most commonly applied to analyze visual imagery. Now when we think
of a neural network we think about matrix multiplications but that is not the case with
Conv. Net. It uses a special technique called Convolution. Now in mathematics
convolution is a mathematical operation on two functions that produces a third function
that expresses how the shape of one is modified by the other.
 Face Alignment
Theory
• Theoretically, if an image is aligned, the training of the model will be more successful because the
center of the face will be equal for all the images in a dataset.
• Also, the vector with the face embeddings, the output of our model, will have certain parts of the
face in different places in the vector. For example, if the face is oval, you may have embeddings of
that face in places that a rounder face does not have. This way, when calculating the distance or
similarity between the two faces, we can get a more accurate result of whether they are the same
person.
Hardware
Requirements:
1. Camera: High-resolution
cameras capable of capturing clear and detailed images are
essential. For optimal results, consider HD webcams or high-quality surveillance
cameras.
2. Processing Unit: Powerful CPUs or GPUs are necessary for real-time image processing.
GPUs, especially those suitable for parallel processing, can significantly boost the speed of
facial recognition algorithms.
3. Memory: Sufficient RAM to handle the processing of images and data. The amount of
memory needed depends on the size of the dataset and the complexity of the recognition
algorithms.
4. Storage: Adequate storage to manage the facial database and store attendance records.
Consider scalable and reliable storage solutions to accommodate the growth of data.
5. Network Connectivity: Stable network connections are important, especially if the
system
uses cloud-based services for database management or updates.
SOFTWARE
REQUIREMENTS
1) : OR EARLIER)
PYCHARM(VERSION 23.4.0
2) PYTHON IDLE (VERSION 12.1.0)
3) PACKAGES - DLIB, FACE_RECOGNITION,PICKLE,
OPEN CV, ETC.
4) FIREBASE (FOR DATA STORING IN REAL TIME)
5) OPEN CV LIBRARY
6) VS CODE (LATEST VERSION)
CONCLUSIO
N :College attendance management for students has become one of the hot issues in the
society, so the management of college students should be strengthened. However, most
college students still use traditional manual attendance for daily attendance, using paper
signatures or teacher orders, but now with the gradual rise of technology, some new
methods point out that gradually, a few colleges and universities will use punch card
fingerprints and smart attendance methods. Although there are some ways to stimulate
attendance, the effect is not so effective. Attendance and these methods have a common
shortcoming, fraud will occur, thereby increasing the rate of absenteeism. This repeated
phenomenon not only has a negative impact on students’ psychology and physiology, but
also maintains the normal order of university teaching and hinders the quality of teaching.
At the same time it will have a very unfavorable situation training and the formation of
university spirit and discipline.
REFERENC
E:
• 1] K. Solanki and P. Pittalia, ‘‘Review of face recognition techniques,’’ Int. J.
Computer Appl., vol. 133, no. 12, pp. 20–24, Jan. 2016.
• [2] C. Stoll, R. Palluel-Germain, R. Caldara, J. Lao, M. W. G. Dye, F. Aptel, and O.
Pascalis, ‘‘Face recognition is shaped by the use of sign language,’’ J. Deaf Stud.
Deaf Educ., vol. 23, no. 1, pp. 1–9, 2018.
• [3] W. Deng, J. Hu, and J. Guo, ‘‘Face recognition via collaborative
representation: Its discriminant nature and superposed representation,’’ IEEE
Trans. Pattern Anal. Mach. Intell., vol. 40, no. 10, pp. 2513–2521, Oct. 2018.
• [4] T. Pei, L. Zhang, B. Wang, F. Li, and Z. Zhang, ‘‘Decision pyramid classifier for
face recognition under complex variations using single sample per person,’’
Pattern Recognition, vol. 64, pp. 305–313, Apr. 2017.
• [5] H. Shi, X. Wang, D. Yi, Z. Lei, X. Zhu, and S. Z. Li, ‘‘Cross-modality face
recognition via heterogeneous joint Bayesian,’’ IEEE Signal Process. Lett., vol. 24,
no. 1, pp. 81–85, Jan. 2017.
THANKYOU