Student Identification Detection
INTRODUCTION
The implementation and enforcement of dress codes are some of the steps that must be
considered when it comes to security protocols of both public and private schools. Dress codes
in such learning institutions are said to help socio-economic that affects the students who can’t
afford the latest trends especially at urban schools. This could also instill discipline and sense
of community among the students. It also helps the school staff and security to quickly spot
the intruders and any other individuals who do not belong to the institution. As school uniforms
are considered as an indicator of safety from school crimes caused by intrusion, though
uniforms alone cannot solve all the issues with regards to security, they can still be a positive
element to discipline.
With the continuous innovations of technology in this present time, modern
technologies are now being incorporated with these security protocols to develop devices to
serve as an aid as camera surveillance with database. These innovations with advanced
technological implementations will guarantee a stricter security through computer vision.
Computers are now starting to imitate human abilities such as having vision, and that is where
the notion of image detection and recognition takes the spotlight.
Despite the advantages enjoyed by these advancements in mobile technology, there are
threats that have been posed by their usage. Despite frisking of students before they enter into
examination halls, some manage to smuggle mobile phones into the halls. Mobile phone usage
in examination halls opens doors to examination irregularities as most phones have high
definition cameras and can read PDF documents therefore class notes are easily accessed
during the examination. The same can also be shared via Bluetooth, Wi-Fi and messaging.
Due to this problem that has been experienced in the university for years, there is a
need to design a system that can detect the presence and usage of mobile phones in the
examination halls. This project is therefore aimed towards designing a cell phone detector that
will be installed in the examination venues. This will curb the vice because even though some
may manage to smuggle them into the halls, their usage and presence are continuously
monitored by the system and offenders can be caught. This detector is not limited for use in
examination halls only. It may be used in hospitals, conference halls, correctional institutions
and other places where the use of mobile phones must be prohibited Every organization
requires a robust and stable system to record the attendance of their students. and every
organization have their own method to do so, some are taking attendance manually with a sheet
of paper by calling their names during lecture hours and some have adopted biometrics system
Dept Of CSE, SJCIT
4
2021-22
Student Identification Detection
such as fingerprint, RFID card reader, Iris system to mark the attendance. The conventional
method of calling the names of students manually is time consuming event. The proposed
system is designed for automating the attendance of the different organization and reduces the
flaws of existing manual system. The system calculate the attendance subject wise, that is the
data of students and subjects are added manually by administrator, and whenever time for
corresponding subject arrives the system automatically starts taking snaps and find whether
human faces are appear in the given image or not.
Dept Of CSE, SJCIT
5
2021-22
Student Identification Detection
LITERATURE REVIEW
1.”Face ,Object And Color Identification System In Schools For Dress-Code
Monitoring”
The technology has been developed which can make interaction between the human and the
computer very easy. The face recognition is the best example for that. For the past two decades
the researches are made in the face recognition. The face recognition can involve in all the
below mentioned process such as computer vision, pattern recognition, image processing and
the machine learning. In this paper they mainly process the face recognition and the color
identification. The faces are captured and the pattern segmentation, identification and
comparison are made. Then the next stage is the color identification which uses the Neural
Network Model which is applied in the color uniform of the college students. From the
captured image of the color uniform the RGB color components are extracted. The color
components of the resized images are scaled using SHM Simple Heuristic Method. From
feature vector identification in the color uniform the rescaled image is extracted. The accuracy
of the method is about 95%. The RGB and the neural network plays a main role in the color
identification.
Advantages:
It has proposed a new method of face recognition in colleges and schools with color recognition
of their corresponding uniform. Since the objects such as ID card, Belt and shoes are identified
this makes our design more effective and highly appreciable. This new method is proposed to
be used as a tool to make students follow the dress-code rules that improves a sense of
professionalism in them.
2. “Uniform Recognition Activated Gate for Dress Code”
Wearing of improper uniform has been one of the problems being faced due to a massive
number of students entering the university. The security guards do not have the ability to
monitor the student’s attire all the time. There are also some students who do not wear
Identification Cards (ID) upon entering the school premise which is also important for the
student’s or staff’s identification as well as the school’s security and integrity. This paper aims
to plan and built a device whose main function is to monitor student’s attire for most of the
Dept Of CSE, SJCIT
6
2021-22
Student Identification Detection
time. Uniform recognition activated gate for dress code implementation focused on improving
the security system upon entering the gate of the university. This device used biometrics,
barcode scanner of the Identification (ID) card and image recognition for uniform to open the
gate. The mechanism to open the gate uses a servo motor which is connected to the gate
structure. Based on the evaluation done by the professionals and preferred users, the device
has been considered very good for each criteria provided of its scores. The device will be
available for further improvement to develop more functions necessary to the workplace of its
application.
Advantages:
It had been tested each day per week to check if the schedules provided for the uniform
classification and recognition are working. The data gathered shown that the school uniform
images had been recognized by the system during Tuesdays, Wednesdays, Thursdays, and
Fridays only. P.E. Uniforms had been recognized by the system any day of the week. The result
from series of trials stated that the gate won’t provide an entry for any absence of requirements
for its input.
3. “ Classification Of Dress Codes Using Convolution Neural Networks ”
People now live in a world surrounded by corporate culture like workplaces and colleges,
schools, hospitals. In particular educational institutions will ensure the students to follow dress
code to obtain uniformity among the students. It is a tedious task to the management to identify
the students who doesn’t follow the dress code. Manual observation requires more human
involvement and it is not possible for the entire day. More over the campus is significantly
large and monitoring students all over the campus manually increases the workload. To resolve
those issues, the proposed model presents a neural network based classification system to
identify and categorize the students. Data set consists of 270 pictures of understudies and
professionals are used in the experimentation to recognize the dress code of individuals. The
results gave us precise expectations utilizing some graphical portrayals just as ages of the
different individuals.
Advantages:
The proposed model is developed to identify the dress code of the person in an institution.
Based on 3 layer convolutional neural network architecture the images are classified to identify
the formal and informal persons.. Proposed model classifies the dress code percentage
Dept Of CSE, SJCIT
7
2021-22
Student Identification Detection
accurately. Various images from webpages and real time images are used in the
experimentation process to observe the robustness of the proposed model. In future the
research work could be further extended by increasing the data size and training images.
4. “ Classroom Distraction Due to Mobile Phones Usage by Students: College
Teachers’ Perceptions ”
There are more than six billion users of mobile phones worldwide. Smart phones and other
handheld devices are largely used by the students. Research indicates that increasing use of
mobile phones by the students in the classroom is a big interruption. This paper presents the
result of a study conducted on teachers of various institutes of higher education in Oman. Total
32 teachers from both the public and private colleges and universities were responded the
questionnaire. The results of the study show that participants reported strong perceptions of
mobile phones as a classroom distraction in teaching and learning environment and students’
misconduct. It has been strongly confirmed that mobile phones are misused and is potential
source of stress among faculty and lack of concentration among students.
Advantages:
Based on participants’ data, the primary hypothesis was supported. Higher mean value reflect
more support for guidelines restricting mobile phone use in the classroom, stronger perception
regarding serious interruption in teaching and learning environment and students misconduct.
It has been strongly confirmed that mobile phones are misused and is potential source of stress
among faculty and lack of concentration among students. Most of the faculty members show
negative attitudes about cell phones use in college classrooms during lectures. Although some
past studies have explored college students’ cell phone usage, few studies have examined the
perceptions of faculty or university staff. This study only covered teachers’ perceptions.
However, the number of respondents was not large enough but included all type of institutions
and teachers. A further study on the topic is needed to detect significant association between
the variables. The study will help higher academic institution to identify the problems and
challenges faced by teachers in the classroom due to use of mobile phone
Dept Of CSE, SJCIT
8
2021-22
Student Identification Detection
OBJECTIVES
 To provide additional measures for a more effective enforcement and monitoring of the
university dress code policy compliance.
 To utilize the existing modern technology with identification and recognition of system
for the benefit of the university dress code policy.
 To detect if students are not complying with the University Dress Code Policy.
 To detect if students are wearing Identification Card (ID) or not.
 To detect the usage of mobile phone during the class hours or in an examination hall.
 To send an automatic message to respective class teacher and proctor of student in case
of violation of rules.
Dept Of CSE, SJCIT
9
2021-22
Student Identification Detection
STUDY AREA AND METHODOLOGY
The proposed research method that would be adopted is as follows:
i) Requirement Assessment: A thorough assessment of the current existing system
will be carried out and the requirements of the new systems will be clearly defined
by interviewing some students and lecturers.
ii) Application Program: At this stage, the design work flow will be converted to code
and debugged.
iii) Testing and Development: The completed algorithm will be tested and deployed on
remote web host, ready for use.
4.1 Methodology
Since every class room would be already having existing cameras, we would utilize that one.
As it captures the whole class, we can connect it our developed system to take automatic
attendance system of respective classes, and also detect whether wearing mask, Identification
Card (ID) and also usage of mobile during class hours or in an examination hall.
4.1.1 Face Recognition : The main aim of this is to recognize the face of the school/college
student and to recognize the color of the uniform through the color identification algorithm
method. The face recognition follows the identification, pattern segmentation and
classification, comparison and extraction. The input is image is trained in the training set and
the following process takes place. After the stage of face recognition, the color identification
is made by the RGB and neural network method which measures the edges of the images and
color of the images. The edges are measure when the image shows identical color.
Dept Of CSE, SJCIT
10
2021-22
Student Identification Detection
4.1.1.1 Face Recognition Process
Fig 2 : Block Diagram
Face Detection and Extraction: Face detection is important as the image taken through the
camera given to the system, face detection algorithm applies to identify the human faces in that
image, the number of image processing algorithms are introduce to detect faces in an images
and also the location of that detected faces. We have used HOG method to detect human faces
in given image.
Face Positioning: There are 68 specific points in a human face. In other words we can say 68
face landmarks. The main function of this step is to detect landmarks of faces and to position
the image. A python script is used to automatically detect the face landmarks and to position
the face as much as possible without distorting the image.
Face Encoding: Once the faces are detected in the given image, the next step is to extract the
unique identifying facial feature for each image. Basically whenever we get localization of
Dept Of CSE, SJCIT
11
2021-22
Student Identification Detection
face, the 128 key facial point are extracted for each image given input which are highly
accurate and these 128-d facial points are stored in data file for face recognition.
Face matching: This is last step of face recognition process. We have used the one of the best
learning technique that is deep metric learning which is highly accurate and capable of
outputting real value feature vector. Our system ratifies the faces, constructing the 128- d
embedding (ratification) for each.
Attendance Marking: Once the face is identify with the image stored in JSON file, python
generate roll numbers of present students and return that, when data is returned, the system
generates attendance table which includes the name, roll number, date, day and time with
corresponding subject id. And then passes the data to python to store the table into an excel
sheet automatically. Each sheet is saved according to the subjects which already entered by the
administrator, for example when system generates excel sheet by sending the compiled sheet
in an array to python, the python first checks whether there exit any excel sheet of that date, if
yes then it create separate worksheet by subject id, so that attendance is differentiated for
different subjects. faces function is used to compute the Euclidean distance between face in
image and all faces in the dataset. If the current image is matched with the 60% threshold with
the existing dataset, it will move to attendance marking.
4.1.2 Detection Of Mobile Phones
The detectors already in the market employ different detection techniques. Each manufacturer
has their design although the basic procedure how the detection is done may be common.
4.1.2.1 RF Spectrum Approach: Every mobile phone uses the frequency spectrum for
communication. Manufacturers use different frequencies in their mobile phones for
communication depending on the federal laws of the country and radiation regulations. A study
carried out by Pacific Northwest National Laboratory for the United States Department of
Energy on cell phone detection using this technique showed that different phones propagated
using different frequency ranges.
 An LG cellular phone had distinctive signals from 260MHz to 300MHz.
 A Motorola cellular phone had distinct signals in the range of 240MHz and 400MHz.
 A Samsung cell phone had distinctive signals between 340MHz and 385MHz.
Nokia cell phone had distinct signal at 245MHz In this detection approach, a passive circuit
listens for any emissions from a cellular phone when it is either waiting for a call or
transmitting and does not require an external signal to detect the phone. This is advantageous
especially in areas where power emissions from electromagnetic sources are highly prohibited.
Dept Of CSE, SJCIT
11
2021-22
Student Identification Detection
The circuit implementation of this approach differs in so many ways. One of the approaches
is in fig 3 as a block diagram.
Fig 3: Block Diagram
For versatility, an LCD can be interfaced to notify the person monitoring of a cell phone
detected. This ensures that even when the power level is low, like in the case of standby phone,
to drive the buzzer, a notification like “MOBILE PHONE DETECTED” will be of use as an
alarm. Fig 4: LCD Integration
Fig 4 : LCD Integration
4.1.3 Uniform Detection
The complete process of proposed model is depicted in figure 5 as a convolutional neural
network.
Fig 5 : Convolution Neural Networks
Dept Of CSE, SJCIT
12
2021-22
Student Identification Detection
So far the building blocks for building the network model with the help of Convolution
neural network has been shown above . Let us move to the next face that is constructing our
network module as every model has a few steps for its implementation our model has four
basic steps to train our network model
● The implication of data-Sets into our Model
● Validating our data sets
● Training our Model
● Processing the acquired data from Model
Dept Of CSE, SJCIT
13
2021-22
Student Identification Detection
4.1.4 Flow Chart:
Start
Face captured
Is face
matches
Create database
Check for id, mask
If no id
or mask
Wearing id, mask
No mask or id
mobile
No mobile
Use mobile
Stop
Dept Of CSE, SJCIT
14
2021-22
Student Identification Detection
DESIGN:Block diagram – Workflow of Face Detection
Loading Haar
CascodeFace
Algorithm
Obtaining Face
coordinates by
passing
algorithm
Converting
Color image
into Greyscode
image
Recoding
Frame from
camera
Initializing
camera
Drawing
Rectangle on the
Face Coordinates
Display the
output Frame
Block Diagram – Workflow of Face recognition
Loading face
detection
algorithm
Face detection
by its
algorithm
Dept Of CSE, SJCIT
Loading
Classifier for
face
recognition
Tracking
classifier for
our dataset
Predicting face
by loading
frame into
model
Recoding
frame from
camera & preprocessing
Displays
recognized
class with its
accuracy
14
2021-22
Student Identification Detection
Block Diagram – Workflow of Color Object Tracking
Recoding
frame from
camera
Pre-processing
image
Finding centre
of contour Area
Finding
counters
Drawing
Minimum
enclosing
circle
Direction based
on radius &
Position
Drawing circle
& centre
ObjectRecognition
Object recognition is a computer vision technique for identifying
objects in images or videos. Object recognition is a key output of deep
learning and machine learning algorithms. When humans look at a
photograph or watch a video, we can readily spot people, objects,
scenes, and visual details.
Dept Of CSE, SJCIT
14
2021-22
Student Identification Detection
Block Diagram – Workflow of Attendance System
Dataset Connection
with CSY name &
fallon
Load Model, LE
& CSV
Dept Of CSE, SJCIT
Preprocessing
Face
Detection
Pre-processing
120-D embedding
for ML
Pre-process
frame from
Camera
TrainingML-SVM
Classification
14
2021-22
Student Identification Detection
Block Diagram – Workflow of Dnn in OpenCV
Load Model
Select
Backend
Convert to
Blob
Dept Of CSE, SJCIT
Recoding
frame from
camera
Select target
Post Process
Forward
14
2021-22
Student Identification Detection
IMPLEMENTATION :-
Converting Color Image to Greyscale Image:-
import cv2
image = cv2.imread(‘sample1.png’)
greyImage = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
cv2.imwrite(‘grey_image.png’,greyImage)
cv2.imshow(‘Color_image’,Image)
cv2.imshow(‘Grey_image’,greyImage)
cv2.watKey(0)
cv2.destroyAllWi ndows()
Dept Of CSE, SJCIT
14
2021-22
Student Identification Detection
Creating Face Dataset
import cv2
haar_file = ‘haarcascade_frontalface_default.xml’
datasets = ‘dataset’
sub_data = ‘champ’
path = os.path.join(datasets,cubdata)
if not os.path.isdir(path)
os.mkdir(path)
(width,height) = (130,100)
face_cascade = cv2.VideoCapture(haar_file)
webcam= = cv2.VideoCapture(0)
count = 1
Haar Cascade FrontalFace Algorithm

It is based on the Haar Wavelet technique to analyse pixels in the image into squares
by function.

This uses machine learning techiques to get a high degree of accuracy from what is
called “training data”.

This uses “integral image” concepts to compute the “features”detected.

Haar Cascades use the Adaboost learning algorithm which selects a small number of
important features from a large set to give an efficient result of classifiers.
Dept Of CSE, SJCIT
14
2021-22
Student Identification Detection
Fisherface Recognizer :
Fisherfaces algorithm extracts principle components that seperates one individual from
another. So, now an individual’s Features can’t dominate another person’s features.

Fisherface method will be applied to generate feature vector of facial image data used
by system and then to match vector of traits of training image with vector characteristic
of test image using Euclidean distance formula.
Dept Of CSE, SJCIT
14
2021-22
Student Identification Detection
LBPHFaceRecognizer :
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.
It doesn’t look at image as a whole, but instead tries to find its local structure by comparing
each pixels to its neighboring pixels.
LBPH uses 4 parameters
•
Radius – to build the circular local binary pattern and represent the radius around the
central pixel it is usually set to 1.
•
Neighbors – The more sample points you include, the higher the computational cost.
It is usually set to 8.
•
X Grid – the number of cells in the horizontal direction.
•
Y Grid – the number of cells in the vertical direction.
Dept Of CSE, SJCIT
14
2021-22
Student Identification Detection
Algorithm for Image Scaling
Algorithm 1:- Adaptive image scaling.
Input: W and H are the width and height of the input image.
TW and TH are the width and height of the object image of standard size.
Begin
scaling_ratio ← min{TW/W, TH/H}
new_w ← W × scaling_ratio
new_h ← H × scaling_ratio
dw ← TW − new_w
dh ← TH − new_h
d ← mod(max(dw, dh ), 64)
padding ← d/2
if (W, H) 6= (neww_, new_h):
image ← resize(input_image,(new_w, new_h))
new_image ← add_border(image,(padding,padding))
End
Output: new_image
Algorithm 2 : Viola-Jones Face Detection Algorithm
1: Input : original test image
2: Output: image with face indicators as rectangles
3: for i <- 1 to num of scales in pyramid of images do
4:
Downsample image to create image i
5:
Compute integral image, image ii
6:
for j <- 1 to num of shift steps of sub-window do
7:
for k <- 1 to num of stages in cascade classifier do
Dept Of CSE, SJCIT
14
2021-22
Student Identification Detection
8:
for l <- 1 to num of filters of stage k do
9:
Filter detection sub-window
10:
Accumulate filter outputs
11:
12:
end for
if accumulation fails per-stage threshold then
13:
Reject sub-window as face
14:
Break this k for loop
15:
end if
16:
end for
17:
if sub-window passed all per-stage checks then
18:
19:
20:
21:
Accept this sub-window as a stage
end if
end for
end for
Algorithm 3 : Anomaly-Based Duplicate Detection
Interval Method
algorithm interval-method is
input: set of feature vectors {ζ𝑖,𝑗 ∈ ℝ 𝑓 } in the dataset to be analysed
set of feature vectors {ζ̂ 𝑖,𝑗 ∈ ℝ 𝑓 } in duplicate-free training
data
multidimensional interval 𝐼ℎ ⊂ ℝ 𝑓
number of samples 𝑁
Dept Of CSE, SJCIT
14
2021-22
Student Identification Detection
output: duplicate probability 𝑃(𝐷|ζ𝑖,𝑗 ∈ 𝐼ℎ) for pairs of records in 𝐼ℎ
𝑚 ← |{ζ𝑖,𝑗 ∈ ℝ 𝑓 }|
// sample size = size of the
dataset to be analyzed
𝜚ℎ ← |{ζ𝑖,𝑗 |ζ𝑖,𝑗 ∈ 𝐼h}|
// count of feature vectors in
𝐼ℎ
for 𝑛=1 to 𝑁:
{ζ̂ 𝑖,𝑗 𝑠 } ← sample of 𝑚 feature vectors from {ζ̂ 𝑖,𝑗 ∈ ℝ 𝑓 }
𝜚̂ℎ,𝑛 ← |{ζ̂ 𝑖,𝑗 𝑠 |ζ̂ 𝑖,𝑗 𝑠 ∈ 𝐼ℎ}|
// count of feature vectors in
𝐼ℎ in sample 𝑛
for 𝑘=1 to 𝑚:
𝑃̂(𝜚̂ℎ = 𝑘) ← 1 𝑁 ∑ 𝕀{𝜚̂ℎ,𝑛=𝑘} 𝑁 𝑛=1 // probability of 𝑘 counts in
training data
𝐸̂(𝜚̂ℎ) ← ∑ 𝑘 ⋅ 𝑃̂(𝜚̂ℎ = 𝑘) 𝑚 𝑘=1
// expected value in duplicate-
free data
if 𝜚ℎ > 𝐸̂(𝜚̂ℎ):
// test for anomaly
𝑃(𝐷|ζ𝑖,𝑗 ∈ 𝐼ℎ) ← ∑ 𝑃̂(𝜚̂ℎ=𝜚ℎ−𝜚ℎ 𝐷)⋅𝜚ℎ 𝜚ℎ 𝐷 𝜚ℎ 𝐷=0 𝜚ℎ
//
estimated duplicate probability
return 𝑃(𝐷|ζ𝑖,𝑗 ∈ 𝐼ℎ)
else:
return 0
// no anomaly, duplicate
probability zero
Dept Of CSE, SJCIT
14
2021-22
Student Identification Detection
Dept Of CSE, SJCIT
14
2021-22
Student Identification Detection
REQUIREMENTS
Functional Requirements:




The system should validate detected face with the database.
The system should be able to identify the attire of the students.
The system should be able to identify mask wearing by the students.
The system must be able to detect the Identification Card of students.
Non-Functional Requirements:








The system should be easy to maintain.
The system should be compatible with different platforms.
The system should be fast as customers always need speed.
The system should be secure.
The system should be accessible to online users.
The system should be easy to learn by both sophisticated and novice users.
The system should provide easy, navigable and user-friendly interfaces.
The system should produce reports in different forms such as tables and graphs for easy
visualization by management.
 The system should have a standard graphical user interface that allows for the online
data entry, editing, and deleting of data with much ease.
Hardware Requirements
Processor
Monitor
Keyboard
Mouse
:
:
:
:
intel core i7
LCD
Normal
Compatible
Software Requirements:
Operating system
Front end
Database
Software
Processor
Monitor
Keyboard
Mouse
Dept Of CSE, SJCIT
:
:
:
:
:
:
:
:
windows 10
HTML, PHP
my sql
Pycharm
intel core i7
LCD
Normal
Compatible
Student Identification Detection
Software Requirements:
Operating system
Front end
Database
Software
Dept Of CSE, SJCIT
:
:
:
:
windows 10
HTML, PHP
my sql
Pycharm
16
2021-22
Student Identification Detection
EXPECTED OUT COME
The proposed model is developed to identify the new method of face recognition in universities
and organizations with color recognition of their corresponding uniform to classify based on
formal and informal individuals. Since the objects such as identification card, face mask, usage
of mobile phones etc. are identified which makes our design more effective and highly
appreciable. This new method is proposed to be used as a tool to make individuals to follow
certain etiquette rules that improves a sense of professionalism in them. In future the research
work could be further extended by increasing the data size and training images.
By using image processing and identity recognition, Pi camera is integrated together with the
barcode scanner having the source code installed that will make the system run its functions.
A monitor was placed that will display an interface for the user to be instructed by the system.
The device had been tested each day per week to check if the schedules provide for the uniform
classification and id card, face mask as well as usage of mobile phones recognition are
working. The result from series of trials stated that the gate or the classrooms won’t provide
an entry for any absence of requirements for its input.
Dept Of CSE, SJCIT
16
2021-22
Student Identification Detection
REFERENCES
[1] Edgardo Manuel H. Mariveles, Jimwell G. Porcare, Jovelyn M. Regonay, Meryll R. Cruz,
Engr. Mary Grace P. Beaño, Engr. Florante M. Andaya, Engr. Ericson A. Mandayo, Engr.
Bernie B. Domingo, “Uniform Recognition Activated Gate for Dress Code “,2020 IEEE
REGION 10 CONFERENCE (TENCON) Osaka, Japan, November 16-19, 2020.
[2] Papineni Bhanu Kowshik, Annavarapu vamsi krishna, Purandhar reddy, P Syam Sundar,
“Classification Of Dress Codes Using Convolution Neural Networks “,Proceedings of the
Second International Conference on Inventive Research in Computing Applications (ICIRCA2020) IEEE Xplore Part Number: CFP20N67-ART; ISBN: 978-1-7281-5374-2.
[3] Alka Shrivastava, Manish Shrivastava, “Classroom Distraction Due to Mobile Phones
Usage by Students: College Teachers’ Perceptions “,International Journal of Computer and
Information Technology (ISSN: 2279 – 0764) Volume 03 – Issue 03, May 2014.
[4] B Prabhavathi, V Tanuja, V Madhu Viswanatham and M Rajashekhara Babu, “ A smart
technique for attendance system to recognize faces through parallelism “,IOP Conf. Series:
Materials Science and Engineering 263 (2017) 042095 doi:10.1088/1757-899X/263/4/042095.
[5] Kaneez Laila Bhatti, Laraib Mughal, Faheem Yar Khuhawar, Sheeraz Ahmed Memon, “
Smart Attendance Management System Using Face Recognition”, doi: 10.4108/eai.13-72018.159713.
[6] Boddu Praveen, P.Jagadeesh, “FACE ,OBJECT AND COLOUR IDENTIFICATION
SYSTEM
IN
SCHOOLS
FOR
DRESS-CODE
MONITORING”,
https://www.researchgate.net/publication/339662636
Dept Of CSE, SJCIT
17
2021-22