an automated student attendance management …

7
AN AUTOMATED STUDENT ATTENDANCE MANAGEMENT SYSTEM USING FACE RECOGNITION Mrs. K. Geetha Rani Assistant Professor Department of Information Technology Rajalakshmi Institute of Technology Kuthambakkam, Chennai -602107 Tamilanadu, India Mail ID: [email protected] Parthiban. S Department of Information Technology Rajalakshmi Institute of Technology Kuthambakkam, Chennai -602107 Tamilanadu, India Mail ID: [email protected] Sivasubramanian. S Department of Information Technology Rajalakshmi Institute of Technology Kuthambakkam, Chennai -602107 Tamilanadu, India Mail ID: [email protected] Abstract- 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 student’s answer multiple times. Face recognition-based attendance system is a problem of recognizing face for taking attendance by using face recognition technology based on High Definition monitor video and other information technology. Face detection is used in searching the input image of any face whereas Face recognition is used to detect and process it with database. This project provides benefits massively for many Institutions. Thus, the amount of time and human errors are reduced to make it more efficient. KeywordsImage enhancement, face recognition, face detection, High quality webcam. I. INTRODUCTION Maintaining attendance, is important and compulsory in all the region of management and institution for tracking the performance of students. In improving educational standards attendance plays a major role. In manual attendance system a teacher has to mark attendance for every student manually and in this process there is a possibility of missing someone or someone may repeat foe several times and there is a chances of proxy attendance also, when it comes to manual attendance it is a very time consuming task when there is more of students. To overcome these situations some biometric systems have proposed into field but it is not good for students as they have to wait in the queue to give their thumb impression on the system. Final to overcome the disadvantage of biometric system, face recognition-based attendance system is introduced, this system doesn’t require any physiological connection between the student and the system. In face recognition-based attendance system it captures the image of every individual student with digital image processing and stores it in a face database. Then an image enhancement module detects the face with the database and mark the attendance of the respective students automatically. Thus, this system is more advanced than the existing available models in both time consuming and avoids proxy attendance. The face recognition is being used in various fields for making not only taking the attendance but also it makes the work easier for humans. Now there are many techniques being used in face recognition. Face recognition detects the students face very carefully and represents whether the student is present or not. Facial recognition technology performs the comparison of the digital photos which include Wutan Huatan Jisuan Jishu Volume XVI, Issue VI, JUNE/2020 ISSN:1001-1749 Page No:228

Upload: others

Post on 08-Feb-2022

9 views

Category:

Documents


0 download

TRANSCRIPT

AN AUTOMATED STUDENT ATTENDANCE

MANAGEMENT SYSTEM USING FACE RECOGNITION

Mrs. K. Geetha Rani Assistant Professor

Department of Information Technology

Rajalakshmi Institute of Technology

Kuthambakkam, Chennai -602107

Tamilanadu, India

Mail ID: [email protected]

Parthiban. S Department of Information Technology

Rajalakshmi Institute of Technology

Kuthambakkam, Chennai -602107

Tamilanadu, India

Mail ID: [email protected]

Sivasubramanian. S Department of Information Technology

Rajalakshmi Institute of Technology

Kuthambakkam, Chennai -602107

Tamilanadu, India

Mail ID: [email protected]

Abstract- 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 student’s answer multiple

times. Face recognition-based attendance system is a problem of recognizing face for taking attendance by using face

recognition technology based on High Definition monitor video and other information technology. Face detection is used

in searching the input image of any face whereas Face recognition is used to detect and process it with database. This

project provides benefits massively for many Institutions. Thus, the amount of time and human errors are reduced to

make it more efficient.

Keywords— Image enhancement, face recognition, face detection, High quality webcam.

I. INTRODUCTION

Maintaining attendance, is important and compulsory in all the region of management and institution for tracking the

performance of students. In improving educational standards attendance plays a major role. In manual attendance system a

teacher has to mark attendance for every student manually and in this process there is a possibility of missing someone or

someone may repeat foe several times and there is a chances of proxy attendance also, when it comes to manual attendance it is a

very time consuming task when there is more of students. To overcome these situations some biometric systems have proposed

into field but it is not good for students as they have to wait in the queue to give their thumb impression on the system. Final to

overcome the disadvantage of biometric system, face recognition-based attendance system is introduced, this system doesn’t

require any physiological connection between the student and the system. In face recognition-based attendance system it captures

the image of every individual student with digital image processing and stores it in a face database. Then an image enhancement

module detects the face with the database and mark the attendance of the respective students automatically. Thus, this system is

more advanced than the existing available models in both time consuming and avoids proxy attendance. The face recognition is

being used in various fields for making not only taking the attendance but also it makes the work easier for humans. Now there

are many techniques being used in face recognition. Face recognition detects the students face very carefully and represents

whether the student is present or not. Facial recognition technology performs the comparison of the digital photos which include

Wutan Huatan Jisuan Jishu

Volume XVI, Issue VI, JUNE/2020

ISSN:1001-1749

Page No:228

object identification and categorization as well as face detection. Each photo is converted into a unique numerical value based on

measurements of facial features and associated with an identity in face database. Here many algorithms are being implemented for an effective model to be built for face recognition.

. II. GOAL

The main objective of this system is to make the attendance process easier and also helps the class teachers to make the work

easier. It also reduces human error of attendance. The facial recognition type of attendance marking will be helpful for not only in

the field of education but also in various fields like medicine, IT industries, financial purpose, military purposes etc. using face

recognition based attendance system, students won’t be able to answer attendance for other student and hence false attendance

will not be there.

III. LITERATURE SURVEY

[1] The author proposes the system of attendance system by using an algorithm called as HOG (Histogram of Oriented Gradients)

algorithm. It uses a sliding detection window which is moved around the image. At each position of the detection window, a

HOG descriptor is computed for the detection window. It is then shown to the trained SVM. Which classifies it either as person

or not a person. The main disadvantage is that it gives the result of the image having a poor clarity and computation of the

algorithm is slow.

This type of system uses. [2] a type of student attendance management system by using the concept called RFID technology and

SURF algorithm. The Speeded Up Robust Feature constructs a pyramid scale space like SIFT and repeatedly smooth the image

with gaussian and then sub sample the image, the SURF directly changes the scale of box features to implement the scale space

using box filter and integral image.

The system deals with [3] the problem faced in this type of attendance system is that sometimes the students may lose their ID

cards for some reasons and there will be another time to take the details of the students. It takes a very long process. Also, the

algorithm processing is very slow when compared to other types of algorithms used for face recognition.

The system implementation uses [4] furthermore face recognition-based attendance system included one functionality called

voice recognition where the system is setup with the speaker. The speaker will recognize the voices of the student Say present

and the voice changes to audio file and sent to respective database. The advantage of the proposed system is the introduction to

voice management system where the system will have a speaker like a set and recognize the voice and predicts the student.

The implementation of [5] the system then introduces the concept of iris recognition system where the system has the provision

of iris scanning separately and scans the iris of each student and marks the attendance to the database. This system is worked and

being implemented in all areas like government sectors, Corporate companies and also for some highly confidential meeting in

the field of military. The advantage is it clearly scans the retina of each student and predicts whether the student is of the same

class or different class.

[6] The project gives more importance to fingerprint scanning but not form face recognition system. The project will just

recognize the student face in one direction and marks the attendance of the particular student. Here a new technology is being

implemented by the author called fingerprint scanning, the system consists of a fingerprint scanner along with a camera. The

main advantage is when the camera is not recognized the student face properly even after the face registration the student can be

marked attendance by using this fingerprint scanner.

The system deals with [7] The type of an algorithm for detecting faces of student using face recognition called as Viola-jones

algorithm. The camera first captures the face of student and the algorithm converts the captured face into a grayscale image and

then finds the location of the colored image. With smaller steps, the number of boxes in the image called pixels detect Haar like

features and algorithm helps to determine where the face is. The advantage is that this algorithm processes the image without

converting the image into grayscale

[8] The system implements the attendance system by recognizing the faces of each and every student by face recognition by

using PCA (Principle Component Analysis) algorithm. It is a statistical approach used for reducing the number of variables in

face recognition. In PCA, every image in the training set is represented as a linear combination of weighted eigenvectors called

eigenfaces. These eigenvectors are obtained from covariance matrix of a training image sets. The advantage is that this algorithm

has high computational power when compared to other algorithms.

Wutan Huatan Jisuan Jishu

Volume XVI, Issue VI, JUNE/2020

ISSN:1001-1749

Page No:229

IV. PROPOSED SYSTEM

Figure 1. System Architecture.

Figure 2. Student registration module

Wutan Huatan Jisuan Jishu

Volume XVI, Issue VI, JUNE/2020

ISSN:1001-1749

Page No:230

Figure 3. Face Recognition process

Figure 4. Training Images.

Wutan Huatan Jisuan Jishu

Volume XVI, Issue VI, JUNE/2020

ISSN:1001-1749

Page No:231

Figure 5. Student attendance update (CSV File).

Face recognition-based attendance system is implemented in different areas with advanced technology and with different types of

algorithms now a days in the field of corporate, conference and even in schools and colleges, this type of concept is becoming

advanced day by day. The system that we proposed consist of camera with a high clarity of motion and image capture facility as a

front end and excel sheet to save the details of the student in .csv format as back end and also to mark the attendance of the

student at the time of arrival to the classroom is being updated in excel sheet will be in the form of .csv format. Here the datasets

will be the faces of each student and the student details. The process starts with entering the details of the student like roll no and

name of the particular student. That details will be first stored in a separate excel sheet as studentDetails in .csv format as a

backend. Then the face of the particular student or a person is being captured by a high definition camera, the image is being

stored in a separate folder as Training Images. Then the next step or process in the face recognition-based attendance system is

IMAGE ENHANCEMENT.

In this process, the camera will take the image of a person not only in one direction using image enhancement process, the

camera will take 61 different angles of image of a person and store it in a folder or database. Then the next step involves training

of captured images, here the algorithm is being implemented called as LOCAL BINARY PATTERN HISTOGRAM (LBPH).

This algorithm is used only for training of images. LBPH algorithm is a simple solution of face recognition problem, which can

recognize both front face and side face. This algorithm uses four parameters namely radius, neighbors, grid x, grid y. first the

captured images are being converted into a grayscale image. From the grayscale image, we can get the image in 3*3 pixels. Then

the pixels are converted to matrix representation, here the central value of the matrix used as threshold value. This value used to

define values of neighbor. Using the threshold values, the algorithm sets the binary value for each image with other image. Using

the binary values, the images will defer and indicate whether the registered face is present or not by checking the database. then

the images are being trained by using the LBPH algorithm, the algorithm trains the images by feature extraction process where

the parts of the face like eyes, ears, nose, eyebrows are being trained by the algorithm. Then the details of the students are being

updated in the excel sheet as .csv format as shown in the fig 1.4. Then the attendance is being tracked and the attendance is

recorded for the particular student in separate database.

Wutan Huatan Jisuan Jishu

Volume XVI, Issue VI, JUNE/2020

ISSN:1001-1749

Page No:232

V. CODE

def clear():

txt.delete(0, 'end')

res = ""

message.configure(text= res)

def clear2():

txt2.delete(0, 'end')

res = ""

message.configure(text= res)

def is_number(s):

try:

float(s)

return True

except ValueError:

pass

try:

import unicodedata

unicodedata.numeric(s)

return True

except (TypeError, ValueError):

pass

return False

VI. CONCLUSION

The system has been proposed for maintaining the attendance record. The main aim of the attendance system project is to make

the work easier for teachers to take the attendance in a classroom by eliminating the manual attendance system. The feature

extraction process is used to increase the rate of face recognition technique. Even in the poor light available in the classroom, the

system will be able to capture the face of student with high quality image.

Wutan Huatan Jisuan Jishu

Volume XVI, Issue VI, JUNE/2020

ISSN:1001-1749

Page No:233

VII. ACKNOWLEDGEMENT

We would like to acknowledge, Mrs. K. Geetha Rani, Assistant Professor, Department of Information Technology, Rajalakshmi

Institute of Technology, Chennai, for the valuable support throughout the project.

REFERENCES

[1] Face recognition-based attendance management system using machine learning by Anushka waigankhar,

Akash Upadhyay, Ruchi shah. (IJRET) volume 05 2018.

[2] Face Recognition using SURF algorithm by Roberto Morales Caporal, Federico Ramirez Cruz conference

paper 2015.

[3] ali akbar punjani, chowdhary obaid, automated attendance management system using face recognition

international journal of advanced computer science and technology vol 6 2017.

[4] Nandhini R, Duraimurugan Face Recognition Based Attendance System IJEAT Vol-8 2019.

[5] Rajath S Bharadhwaj, Vinay T.R Face Recognition Based Attendance System (IJITEE) Vol-8 2019.

[6] Multimodal student attendance management system by khalel mohammed, A.S. Toba, Mohammed Elmogy

Ain shams engineering journal 2019.

[7] Deep learning-based face recognition attendance system by Marco Arsenvoic, Andras Anderla, Darco

Stefanovoic IEEE symposium of intelligent systems and informatics 2017.

[8] Smart student attendance management system using face recognition by V.P.Chitragar, Rohan Charmore,

Mahesh Yeshwanthrao IJARIIE vol-4 2018.

Wutan Huatan Jisuan Jishu

Volume XVI, Issue VI, JUNE/2020

ISSN:1001-1749

Page No:234