BANGALORE INSTITUTE OF

TECHNOLOGY
K.R Road, V.V Pura,Bengaluru-04
DEPARTMENT OF COMPUTER SCIENCE &
ENGINEERING

“AI BASED FACE RECOGNITION SYSTEM

TO KEEP CLASS DAY TRACKING
MANAGEMENT USING DEEP LEARNING
AND AWS CLOUD”

Presented by
16P55
SUKANYA R<1BI15CS208>
RIZA UR REHAMAN<1BI15CS209>
YOGESH KUMAR M<1BI16CS185> Under the Guidance of
PRITI MUNDA<1BI16CS226> D R NAGAMANI
Asst. Professor
Dept. of CSE
Agenda
• Introduction
•Literature Survey
•Existing Survey
•Problem Statement
•Proposed System
•Architecture
•Applications
•Conclusion
•References

1/20
Introduction
Most educational institutions are concerned with
students’ participation in courses since student
participation in the classroom leads to effective
learning and increases success rates. The present
paper aims to propose an attendance-taking process
via the existing technological infrastructure with some
improvements. Face recognition system to take
attends accurately
2/20
 Objectives
Face recognition can be applied for a wide variety of
problems like image and film processing, human-
computer interaction, criminal identification etcIt is
observed that efficient face detection from different
angles reduces the occurrence of occlusion.
Moreover, the system’s recognition accuracy is
influenced by how effectively students’ faces are
detected. The validation and the classification of face
detected is based on face detection.
Literature Survey
Title Author and Year Methodologies Limitations
Smart Security System for Danish Ali Chowdhry we proposed a smart security It takes lot of time to process
Sensitive Area Using Face system for access-controlled
Recognition 2013 area by exploiting face
recognition. Firstly, we detect
the human motion from CCTV
human face

Implementation of Face Anto Satriyo Nugroho . Principal Component the system is it only recognizes
Recognition Algorithm for Analysis (PCA) is developed face up to 30 degrees angle
Biometrics Based Time 2014 in order to overcome expensivevariations
Attendance System computation and the need of
great amounts of storage of
older face recognition
technique

Attendance System based on Roshani Thakare The image of person will be due to the negative light
Face Recognition using Eigen captured from the camera and exposure and high noise level
face and PCA Algorithms 2015 then it will be enhanced using more than the other statistical
histogram equalization and methods
noise filtering. Then after this
process, the features are
extracted from the image

Intelligent Classroom Ran Li Face feature extraction and Verification is tough using
Attendance System on Face comparison with RFID multiple angles
Recognition 2015 technology

5/20
 Title Author and Year Methodologies Limitations
Implementation of Refik Samet The System performs Fingerprints has to be
Attendance Management managing students with refreshed, updated and time
System using SMART-FR 2016 Open CV and raspberry pi consuming.
module that is interfaced
with fingerprint device.

An Evaluation of Face Manop Phankokkruad Face tracking is the process For particular faces only
Recognition Algorithms and to search for a human face in
Accuracy based on Video in 2016 the video frames. This process
Unconstrained Factors was done by using a good face
detection method.

Face Recognition-Based Mobile Muhammed Tanriverdi . In this scope, a filtering system The results regarding students
Automatic Classroom based on Euclidean distances sitting in front seats are more
Attendance Management 2017 calculated by three face accurate in comparison to
System recognition techniques, namely results regarding students sitting
Eigenfaces, Fisherfaces, and in the back.
Local Binary Pattern (LBP), has
been developed for face
recognition.

Automatic Attendance Mathana Gopala et. Al they use Viola-Jones the student is marked
System Using Face algorithm and PCA present only if he/she is
Recognition 2017 algorithm for face detection recognized in both the
and two face recognition images
respectively
Title Author and Year Methodologies Limitations
An Efficient Attendance Michel Local Binary Pattern (LBP) comparison is done only for
Management System based and Histogram of Oriented 40% percent
on Face Recognition using 2018 Gradients (HOG) . Support
Matlab and Raspberry Pi 2 vector machine (SVM)
classifier

Smart Attendance Shubhobrata Having a video sequence as Match up to 60%

Monitoring System (SAMS): Bhattacharya, Gowtham the input to the system the
A Face Recognition based Sandeep details of face detection,
Attendance System for facial features extraction,
Classroom Environment 2018 normalization of facial
features and quality score
assignment are described in
the following subsections

Real-Time Smart Shreyak Sawhney The Does not not include more
Attendance System using system consists of two data base
Face 2019 databases, a student database,
Recognition Techniques and an
attendance database. The
student database is for
storing the
details of the student in a
particular class.
Conceptual Model of the Louis Mothwa It demonstrates how a multi- As more cameras are used
Smart Attendance camera installation reduces highly expensive
Monitoring System Using 2018 the
Computer Vision effect of occlusion in the
process of face detection,
since
 Existing System
There are many systems have developed in engineering
colleges and industries to keep a track of the attendance.
The developed systems are good but their performance
and stability problems. The developed systems are:
1) Biometric based System
2) Bluetooth based System
3) RFID based System

6/20
1) Biometric based System

The Biometric based systems take a unique part of the human

body and use it for attendance management system for
example iris, nostrils, retina, palm, fingerprints etc.
The data keeps scaling up and the system needs to be
maintained, refreshed and regularly updated for later use.
The attendance system using Computer or android devices
provides a cheaper solution compared to the biometric based
systems .
2) Bluetooth based System

This system has high usability and proxy removal methods

can be included to make the system perfect.
The system is not scalable and requires 8 connections active
at a time.
Bluetooth do not allow more than 8 connections at a time
this is due to a master and slave concept.
This redundancy makes it a feasible resource for a limited
population .
3) RFID based System

The RFID systems are popular than Bluetooth based system.

Students are given RFID cards in their schools and colleges
along with their Identity cards.
These cards are put into the RFID reader before the student
enters the classroom.
These systems require permanent supervision because students
can put two cards in the RFID reader leading to a proxy and also
inappropriate usage can harm the RFID reader .
Problem statement
“Attendance is an important part of daily classroom
evaluation. At the beginning and ending of class, it is
usually checked by the teacher, but it may appear that a
teacher may miss someone or some students answer
multiple times. Face recognition-based attendance system
is a problem of recognizing face for taking attendance by
using face recognition technology and informing the
parents about absent of that particular student
3/20
Input:
Face Detection – where the input image is searched to
find any face, then image processing cleans up the facial
image for easier recognition

Output:
Face Recognition – where the detected and processed
face is compared to the database of known faces to
decide who that person is
 Proposed System

Proposed system sends the images of the students sitting

in the classroom to the server using the web service and
captured image sent to the Face Detection and
Recognition modules and then the attendance is marked
in the database. At the time of enrolment, templates of
face images of individual students are stored in the Face
database.

14/20
AWS
CLOUD

REGISTER STUDENT

AUTOMATIC
SAVE IN DATABASE
ATTENDENCE
SYSTEM

PROVIDE FRAME GENERAATION GET

CLASS STUDENT
IMAGE IMAGE

FACE
RECOGNITIO
N
Data Flow Diagram/Flowchart

16/20
Sample Data Set

17/20
Applications

1.The system can be used for places that require

security like bank, military etc.
2.It can also be used in houses and society to
recognize the outsiders and save their identity.
3.The software can used to mark attendance based
on face recognition in organizations.

18/20
Conclusion

Attendances of every student are being maintained

by every school, college and university. Empirical
evidences have shown that there is a significant
correlation between students attendances and their
academic performances. Therefore faculty has to
maintain proper record for the attendance.
The limitation is there is no 100% accuracy. Only
80% of face recognition and face detection is done.
19/20
References
[1] Seema Rao and Prof.K.J.Satoa, “An Attendance Monitoring System Using
Biometrics Authentication”, International Journal of Advanced Research in
Computer Science and Software Engineering, Volume 3, Issue 4, April 2013,
ISSN: 2277 128X
[2] SeifedineKadry and Khaled Smaili. “A Design And Implementation Of A
wireless Iris Recognition Attendance Management System ”, Information
Technology And Control, 2007, Vol.36, No.3; ISSN 1392 – 124X.
[3] Nirmalya Kar, Mrinal KantiDebbarma, AshimSaha, and Dwijen Rudra Pal.
“Study of Implementing Automated Attendance System Using Face
Recognition Technique” International Journal of Computer and
Communication Engineering, Vol. 1, No. 2, July 2012
[4] Arulogun O. T., Olatunbosun A., Fakolujo O. A., and Olaniyi O. M, “RFID
Based Students Attendance Management System ” International Journal of
Scientific & Engineering Research”, Volume 4, Issue 2, February-2013; ISSN
2229-5518.
[5] UnnatiA.Patel and Dr. Sawminarayan Priya R. 2014. “Development of a
Student Attendance Management System Using RFID and Face Recognition: A
Review”, International Journal of Advance Research in Computer Science and
Management Studies, Volume 2, Issue 8, August 2014; Online ISSN: 2321-
7782.. 21