A

Project Presenta tio n

on
Fa ceMa rk Pro : Sma rt Attenda nce Tracker ith Liv eness Detectio n Fea ture
Present ed By
Akash Kumar(2000970100010)
Anshi kaVerma(2100970109002)
Har shi t Kushwah(2000970310077)
Gui ded By
Ms. Kari shmaArora
Assi st ant Professor, Depart ment of Comput er Sci ence and Engi neeri ng

Department of Comput er Sci ence & Engi neeri ng Gal got i as Col l ege of Engi neeri ng & Technol ogy , Greater Noi da
r. A
D .P.JA
du
bl Kalm Tech
ia
nlU
iv
nersity
, Lucknow, U
ttar Pradesh
TABLE OF CONTENTS
• Introduction
• Literature Survey
• Research Gap
• Research Objectives
• Problem Statement
• Proposed Work
• System Design
• Implementation
• Result
• Conclusion
• References
 INTRODUCTION

 Facial recognition attendance-based systems represent a

cutting-edge advancement in the field of attendance
tracking and management
 These systems leverage advanced facial recognition
technology to accurately and efficiently record and verify
the presence of individuals in various settings, such as
workplaces, educational institutions, events, and more.
 Face Recognition Attendance System is developed for the
Faculty to maintain attendance record.
 It uses facial recognition technology to identify the person’s
facial features and automatically mark attendance which is
very fast enough than conventional tedious methods.
 Unlike traditional attendance methods like manual sign-ins
or card swipes, facial recognition attendance systems offer a
seamless and contactless way to monitor attendance,
enhance security, and streamline administrative processes.
 Key Features
 Accuracy and Efficiency: Facial recognition systems provide a highly accurate and efficient way to
record attendance. They eliminate the errors and inefficiencies associated with traditional methods like
manual sign-ins or card swipes, reducing the risk of attendance fraud or human errors in data entry.

 Contactless and Hygienic: In a world increasingly conscious of hygiene and health considerations,
facial recognition systems offer contactless attendance tracking solutions. This reduces the risk of
spreading contagious diseases, which has become particularly relevant in the post-pandemic era.

 Real-time Tracking: Facial recognition attendance systems can operate in real-time, allowing
organizations to monitor attendance instantly. This enables quick responses to attendance-related
issues, such as identifying late arrivals or unauthorized access.

 Enhanced Security: These systems enhance security by ensuring that only authorized individuals gain
access to specific locations or events. They can also be integrated with security systems to trigger
alerts in case of unrecognized or suspicious individuals.

 User Convenience: For attendees, facial recognition is convenient as it eliminates the need to carry
physical cards or remember PINs or passwords. It offers a hassle-free and frictionless experience.
 Literature Survey

Student Attendance System Using Face Recognition

According to the research journal “Student Attendance System Using Face Recognition ”
(Samridhi Dev , et al., 2023).
 The attendance system is improved by using technology and mobile applications.
According to the research paper, each student is given an NFC tag that has a unique ID
during their enrolment into the college.
 Attendance of each class will then be taken by touching or moving these tags on the
lecturer’s mobile phone. The embedded camera on the phone will then capture the
student‟ ‘s face to send all the data to the college server to do validation and verification.
 The advantages of this method is that the NFC is simple to use, and the speed of
connection establishment is very high. It indeed speeds up the attendance-taking process
a lot.
 Hence, unique information about the student like biometrics or face recognition, which is
Student Attendance System using Face Recognition –
 The third research journal “Fingerprint Based Attendance System Using Microcontroller and View”
(Kumar Yadav et al., 2020) proposed a solution of using fingerprint to mark the attendance.
 This system is using 2 microcontrollers to deal with the fingerprint recognition process. Firstly, the
fingerprint pattern will be obtained through a fingerprint sensor, then the information will be transmitted
to microcontroller 1.
 Next microcontroller 1 will pass the information to microcontroller 2 to do the checking with the database
that resides in it.
 After finding a student‟s match, the details are sent to the PC through serial communication to be
displayed. This design is good as it accelerates development while maintaining design flexibility and
simplifies testing.
Attendance System Using NFC Technology with Embedded Camera on Mobile Device
 According to the research journal “Attendance System Using NFC (Near Field Communication) Technology with
Embedded Camera on Mobile Device” (Bhise, et al., 2015).

 The attendance system is improved by using technology and mobile applications. According to the research paper, each
student is given an NFC tag that has a unique ID during their enrolment into the college.

 Attendance of each class will then be taken by touching or moving these tags on the lecturer’s mobile phone. The
embedded camera on the phone will then capture the student‟ ‘s face to send all the data to the college server to do
validation and verification.

 The advantages of this method is that the NFC is simple to use, and the speed of connection establishment is very high. It
indeed speeds up the attendance-taking process a lot.

 Hence, unique information about the student like biometrics or face recognition, which is guanine for a student should be
used in replacement of the NFC tag. This will ensure attendance is taken originally by the actual student.
RFID-based Student Attendance System
 According to the fourth research journal “RFID-based Student Attendance System” (Hussain, Dugar, Deka,
Hannan, 2014), the proposed solution is almost similar to the first research journal where RFID technology is
used to improve the older attendance system.
 In this system, a tag and a reader are again used as a method of tracking the attendance of the students.
 The difference between the first journals with this is that attendance‟s information can be accessed through a
web portal. It provides more convenience for information retrieval.
 Again, this system is imperfect in the sense that, firstly, it is not portable, as the RFID reader can only work when
it is connected to a PC. Secondly, the RFID tag is not genuine information that can uniquely identify a student,
thus, resulting in the inaccuracy of the collected attendance information.
The existing system hasResearch
a portability
Gap problem, we spotted portability
problems in some of the existing systems so we are trying to add the
portability.

The previous and existing system has a queuing problem, so we are

trying to remove that problem with the help of autodetection of student
faces.

Traditional systems had the risk of attendance Spoofing i.e. there is less,
so to remove this we are adding an additional feature of liveness
detection.

There are various implementation of existing software that are using

mobile application for attendance systems, which sometimes is time-
consuming.
 OBJECTIVE
 To accurately identify a person by comparing their facial features to a database of known
faces.
 To verify that the person presenting themselves is indeed the same person whose face is
on record.
 Easy to access and use
 To prevent attendance spoofing by adding a liveness detection feature into the system
 To prevent attendance manipulation
 To implement liveness feature efficiently
 Resolving the Portability issues.
 Problem Statement
 The main problem with traditional
attendance is that it is subject to
manipulation and there remains a chance of
human error during data entry though it is
easier to implement and save technology
expenses, the organization cannot benefit
from the innovations of data analysis which
has huge implications.

 In addition to this contemporary attendance

method in the classroom requires human
intervention and cooperation from student
which contribute to the wastage of precious
class time.
 Proposed Work
 All the students of the class must register themselves by entering the required details
and then their images will be captured and stored in the database and then the dataset
will be generated.
 During each session, faces will be detected from the live-streaming video of the
classroom.
 The faces detected will be compared with images present in the dataset. If a match is
found, attendance will be marked for the respective student.
 The task of the proposed system is to capture the face of each student and store it in the
database for their attendance.
 The face of the student needs to be captured in such a manner that all the feature of the
student's face needs to be detected, even the seating and the posture of the student need
to be recognized.
 There is no need for the teacher to manually take attendance in the class because the
system records a video and through further processing steps the face is recognized and
the attendance database is updated.
Hardware and Software Requirements
 4 Gb+ RAM
 Camera-120p or above
 Database – MySQL
 Vscode
 Python
 Tkinter
 HTML5
 CSS3
 Javascript
 OpenCV
 LBPH(Local Binary Pattern Histograms)
 ALGORITHM
 Local Binary Patterns Histograms (LBPH) (1996).
 Local Binary Pattern (LBP) is a simple yet very efficient texture operator which labels the pixels of an
image by thresholding the neighborhood of each pixel and considers the result as a binary number.
 When LBP is combined with histograms of oriented gradients (HOG) descriptor, it improves the
detection performance considerably on some datasets.
 LBPH is one of the easiest face recognition algorithms.
 It can represent local features in the images.
 It is possible to get great results (mainly in a controlled environment).
 It is robust against monotonic gray scale transformations.
 It is provided by the OpenCV library (Open Source Computer Vision Library).
 Training the Dataset

 First, we need to train the model.

 To do so, we need to use a dataset with the facial images
of the people we want to recognize.
 We need to also set an ID (it may be a number or the
name of the person) for each image, so the algorithm will
use this information to recognize an input image and give
you an output.
 Images of the same person must have the same ID.
 With the training set already constructed, the first
computational step of the LBPH is to create an
intermediate image that describes the original image in a
better way, by highlighting the facial characteristics. To
do so, the algorithm uses a concept of a sliding window,
based on the parameters radius and neighbors.
 When the algorithm is already trained, each histogram
created is used to represent each image from the training
dataset. So, given an input image, we perform the steps
again for this new image and creates a histogram which
represents the image.
System Design
 main.py
 It is where the actual project runs and
shows the output.
 It basically provides the project main
windows .
 Here, user can enter student details ,mark
attendance train data and import and
export attendance.
 It combines all the methods from the
other files and then shows predicted
output.
 FACE_RECOGNITION FILE

 It is used for marking the attendance by

using face recognition method.
 It will open the camera for the face
recognition process.
 Student whose data is stored in database
will be recognized and his attendance will
be marked.
 ATTENDANCE File

 It is basically used to import and

export the attendance files.
 The file can be saved in the form
of excel files.
 The data can be checked here.
 TRAINing of the model

 Model is loaded with predefined

libraries and algorithms of
python
 It uses data set stored in data as
image
 It trains itself from the dataset
and recognizes the person
according to it with much
accuracy.
 STUDENT Details

 It is where all the necessary student

details are entered.
 The photo sample for the dataset will
also get collected.
 The data can be uploaded for the
future.
 The data is stored in the database.
 IMPLEMENTATION
 Step 1: Input image is captured
 Step 2: Convert colored image to grey scale image
 Step 3: Face detection using haar cascade classifier
 Step 4: Face recognition using local binary pattern
histogram
 Step 5: Face is matched with trained dataset
 Step 6: If it matches then attendance will be marked
as Present
 Step 7: If not,then attendance will be marked as
Absent
 Step 8: Generate report
 Step 9: Update attendance
 Step 10: Continue step 6
 Step 11: Stop
CODE STRUCTURE
 FUTURE SCOPE
 Some of the future enhancements that
can be done to this system are as
follows:
 Facility of Defaulter list in which
system update the defaulter student.
 For students, we can develop a
dedicated login page in which they can
see their details and attendance record
 In future we can update the modules
like notices for student and many
more.
 REFERENCES
 [1]. “Attendance System Using NFC Technology with Embedded Camera on Mobile
Device” (Bhise, Khichi, Korde, Lokare, 2015)

 [2]. K.SenthamilSelvi, P.Chitrakala, A.AntonyJenitha, "Face Recognition Based

Attendance Marking System", IJCSMC, Vol. 3, Issue. 2, February 2014.

 [3]. “Fingerprint-Based Attendance System Using Microcontroller and LabView” (Kumar

Yadav, Singh, Pujari, Mishra, 2015)

 [4]. “RFID-based Student Attendance System” (Hussain, Dugar, Deka, Hannan, 2014)

 [5]. OpenCvDocumentation -https://opencv.org

 [6]. Numpy - https://numpy.org

THANK YOU