You are on page 1of 3

International Journals of Advanced Research in Research Article June

Computer Science and Software Engineering 2017


ISSN: 2277-128X (Volume-7, Issue-6)

Face Recognition - A Tool for Automated Attendance


System
Naeema Mohamed Kutty, Shelmy Mathai
Department of Computer Science and Engineering, Cochin College of Engineering and Technology,
Kerala, India
DOI: 10.23956/ijarcsse/V7I6/0268

Abstract— Student attendance in a classroom is a time consuming task when done manually. Face recognition is a
biometric powerful tool to authenticate a person. The other biometric attendance methods waste time as the students
have to make a queue to touch their thumb on the scanning device. So, automated attendance system using face
recognition is the efficient one for student attendance. Image acquisition, face detection and face recognition are the
three parts of this system. The issue of fake attendance and proxies can be solved by using this system. This paper
gives an overview of some known methods used to implement this system and also the benefits and drawbacks of it.
This paper also proposes an efficient method by which we can implement such a system with high accuracy.

Keywords— Student attendance, biometric, automated attendance system, face detection, face recognition

I. INTRODUCTION
In every foundations, maintaining the attendance is essential for checking the performance of students. When there
are so many students in an institution, it will become more and more difficult to mark attendance for each student. And it
is time consuming too. Traditional method of attendance marking is the manual attendance system in which the
attendance are recorded and maintained manually. This system faces the issue of wastage of time and also becomes
complicated when the strength is more. And can be easily manipulated. Whenever we have to measure the performance
of students, finding and calculating the average of the attendance of each enrolled student is also a complicated task.
Therefore we are in need of an automated system for marking and maintaining attendance. So that we can maintain a
valid and correct record of attendance easily.
Automation of attendance system offer some benefits to the faculty by lessening the administrative burden of the staff.
This system saves time and is also used for security purpose. By using this system, we can prevent fake attendance and
proxies. Skipping classes without the staff’s knowledge will become difficult for students by introducing this system.
Many attendance management system are introduced to market such as RFID system, punch card systems, swipe card
systems, biometric systems that include fingerprint analysis, iris analysis etc. But these all are not always applicable for
the students in an institute, college or university. Therefore we are in need of a system that would mark attendance
without any human intervention. So, we shall implement an effective system which will mark the attendance of the
students automatically by recognizing their faces, i.e. automated attendance system using face recognition.
An automated Attendance System using face recognition generally consists of Image Acquisition, Database
development, Face detection, Pre-processing, Feature extraction, and Classification stages followed by Post-processing
stage [4]. At first, the face images of the each student should be fed to the system and saved in the database. Then the
attendance of students is recorded by using the camera attached in the classroom at a suitable location from where the
whole classroom can be snapped by the camera that is continuously capturing images of students, detect the faces in
images and compare the detected faces with the database and mark the attendance. In some method, camera is fixed at
the entry point of the classroom to get the image of students while they enter the classroom. By this system, we can save
much time than the manual attendance system and can maintain the record easily.
The paper is categorized as follows. Section II describes the related work in the field of attendance system. Section III
presents the proposed method. Finally, the conclusion is given in Section IV.

II. LITERATURE SURVEY


A. Algorithm for Efficient Attendance Management: Face Recognition based approach
The image of the classroom is captured using a high definition camera. Histogram normalization is used for contrast
enhancement in the spatial domain. Median filter is used for removal of noise in the image. Skin classification is used to
increase the efficiency of the face detection algorithm. Voila and Jones method is used for detection. The system is
trained by the images of faces and then the algorithm is applied on the class room image for detection of multiple faces in
the image. Face recognition is done by cropping the detected face from the image and verifying one by one with the face
database using EigenFace method and the attendance is marked on the server.
The proposed method is more efficient and accurate than the old manual methods. It is secure enough, reliable and
available for use. Multiple face detection was possible. No specialized hardware was needed for installation. 70% of the
faces captures were detected and 50% of them were recognized. Masked face were not recognized using this method.

© www.ijarcsse.com, All Rights Reserved Page | 334


Kutty et al., International Journals of Advanced Research in Computer Science and Software Engineering
ISSN: 2277-128X (Volume-7, Issue-6)
B. Smart Application For AMS Using Face Recognition
*This method uses CCTV and an android mobile for its operation. The CCTV camera is fixed at the entry point of the
classroom and when the student enters, it automatically captures the image and send to the android mobile to which it has
been connected with. A 3D face recognition algorithm is used in this method which is enriched in the android mobile.
After verification, dual process is done. First, if the captured image is matched with any of the image in the student
database, then the attendance is marked for corresponding student. Second, if it is observed to be unmatched with student
database then the image of the person will be consider as new and saved in the separate database called stranger database.
This proposed method overcome feature localization, pose and illumination problems. Provides high security. But,
the installation of CCTV and connection to android is very expensive. Masked face were not recognized. Single face
detected at a time. Recognition rate was low.

C. Automatic Attendance Management System Using Face Recognition


In this method, PIC micro-controller along with as servo motor mechanism is used. The data or images obtained by
the camera are sent to a computer programmed system for further analysis.
This method uses a face recognition technique based on feature extraction. This method uses eigen face approach for
face recognition. If the eigen values matches, then the recognition process will start soon. If the eigen value does not
matches with the existing one, save it as a new face image. Using PCA algorithm, the face information of matched face
image in the database is found and then updates the log table with corresponding face image and system time that makes
completion of attendance for an individual students.
The proposed face recognition method was very sensitive to face background and head orientations. The system had
overcome illumination problem. The use of dark glasses and masks didn’t give positive results. Recognition rate was
better. Most of the mismatches occur for the images with large head orientations. The disadvantage is that only the
frontal views of face images can be recognized. Had to use extra hardware and so expensive. Single face was detected at
a time.

D. Automated Attendance Management System Based On Face Recognition Algorithms


In this work, several algorithms were used for feature extraction and classification to identify the best algorithm. The
camera is mounted at a distance from the entrance to capture the frontal images of the students. Viola Jones algorithm is
used for face detection. After the histogram equalization and resizing the captured image, the featured is extracted using
several algorithms. PCA with distance classifier, LDA with distance classifier, PCA with SVM classifier, PCA with
Naive Baiyes classifier, LBPH with distance classifier where different approaches implemented by them. When
recognised the attendance is marked and if unrecognised is noted as unknown person. Anti-spoofing technique like eye
blink detector is included in the system.
The paper says that LBPH outperforms other algorithms with better recognition rate and low false positive rate. SVM
and Bayesian also prove to be better classifiers when compared to distance classifiers. When LBPH is used, recognition
rate was high. Tonsured head, beard, use of scarf or mask were not recognized. Head orientation was also a factor that
prevented from detecting a face.

E. Attendance System based on Face Recognition using Eigen face and PCA Algorithms
The camera is to be fixed in the classroom at a suitable location from where the whole class can be covered. The
captured image is converted to grayscale, then histogram equalization is performed. Illumination invariant algorithm is
used to overcome light intensity problem. Viola and Jones algorithm is used for face detection. For the face recognition,
the concept of selection of region of interest is used, and the faces are verified one by one using the EigenFace and PCA
method.
This method have overcome light intensity problem and head pose problem. No specialized hardware is required. Use
of scarf and masked faces were not recognized.

F. Face detection and recognition for automatic attendance system


In this method, the picture of the classroom is captured and then the pre-processing is done. Then Viola Jones
detection algorithm is used for face detection. Features like eyes, nose and mouth are extracted. The face image is then
compared with the stored image. If the face image is matched with the stored image then the face is recognized. Then for
that particular student the attendance is recorded.
In this method, multiple face detection was possible. A desktop version is only implemented. Recognition rate may
be lower when a whole classroom is considered. Illumination problem and head pose problem was found.

G. Student Attendance System in Classroom Using Face Recognition Technique


This method uses a high definition camera situated in the classroom from where the whole class can be covered. This
recognition process is a combination use of Discrete Wavelet Transform and Discrete Cosine Transform. At first
grayscale normalization and histogram equalization is done. A two-level 2-D DWT decomposition is used so as to reduce
the computation time. Then 2-D DCT operations are performed and then Radial Basis Function (Neural) Network
(RBFN) is performed.
Multiple face detection was possible. But, the recognition rate was low. The proposed method had a success rate of
82% only.

© www.ijarcsse.com, All Rights Reserved Page | 335


Kutty et al., International Journals of Advanced Research in Computer Science and Software Engineering
ISSN: 2277-128X (Volume-7, Issue-6)
H. Attendance System Using Face Recognition and Class Monitoring System
This method has used OpenCV for face detection. The picture of the whole class is captured by a camera and loaded
to the system. Then, OpenCV library is used for face detection. After histogram equalization, the feature is extracted. The
feature extraction is done by PCA algorithm. Then MySQL database is used for maintaining attendance records of the
students. A GUI has developed using WampServer.
The proposed method is fast and secure. Obtained better recognition rate and low false positive rate. Recognition rate
may be lower when a whole classroom is considered. Masked faces were not recognized.

III. PROPOSED METHOD


We have discussed different methods for automated attendance system in the previous section. Each of the method
has several drawbacks such as illumination problem, head pose problem, multiple face detection, etc. So this paper
proposes a new method to overcome all these problems. This method uses Viola and Jones algorithm for face detection
as it is an efficient face detection method. This method can also detect multiple faces and can be easily used in a
classroom. Then the detected faces are cropped from the captures image and then verified with face database. For this, an
efficient EigenFace algorithm is used which can overcome the illumination and head pose problem. And the recognition
rate can be increased using this method.

IV. CONCLUSION
The institutions around the world face the difficulty in recording and maintaining the attendance of the students day
by day. Many solutions were proposed to overcome this problem but still the problem remains unsolved in many cases.
Using this proposed method, automated attendance system can be implemented and operated in the institutions easily.

ACKNOWLEDGMENT
I am thankful to Ms Shelmy Mathai, Assistant Professor of Computer Science and Engineering Department, Cochin
College of Engineering and Technology, India for her keen interest and useful guidance in my paper.

REFERENCES
[1] Naveed Khan Balcoh, M. Haroon Yousaf, Waqar Ahmad and M. Iram Baig, “Algorithm for Efficient
Attendance Management: Face Recognition based approach ”, International Journal of Computer Science Issues
(IJCSI), Vol. 9, Issue 4, No 1, July 2012
[2] MuthuKalyani.K, VeeraMuthu.A, “Smart Application For AMS Using Face Recognition”, Computer Science &
Engineering: An International Journal (CSEIJ), Vol. 3, No. 5, October 2013
[3] Jomon Joseph, K. P. Zacharia, “Automatic Attendance Management System Using Face Recognition”,
International Journal of Science and Research (IJSR), Volume 2 Issue 11, November 2013
[4] Shireesha Chintalapati, M.V. Raghunadh, “Automated Attendance Management System Based On Face
Recognition Algorithms”, IEEE International Conference on Computational Intelligence and Computing
Research, Jan 2014
[5] Priyanka Wagh, Jagruti Chaudhari, Roshani Thakare, Shweta Patil, “Attendance System based on Face
Recognition using Eigen face and PCA Algorithms”, International Conference on Green Computing and
Internet of Things (ICGCloT), 2015
[6] Dr. Nita Thakare, Meghna Shrivastava, Nidhi Kumari, Neha Kumari, Darleen Kaur, Rinku Singh, “Face
Detection And Recognition For Automatic Attendance System”, International Journal of Computer Science and
Mobile Computing, Vol.5 Issue.4, April- 2016, pg. 74-78
[7] Samuel Lukas, Aditya Rama Mitra, Ririn Ikana Desanti, Dion Krisnadi, “Student Attendance System in
Classroom Using Face Recognition Technique”, International Conference on Information and Communication
Technology Convergence (ICTC), Dec 2016
[8] Prof. Arun Katara, Mr. Sudesh V. Kolhe, Mr. Amar P. Zilpe, Mr. Nikhil D. Bhele, Mr. Chetan J. Bele,
“Attendance System Using Face Recognition and Class Monitoring System”, International Journal on Recent
and Innovation Trends in Computing and Communication, Vol.5 Issue.2, Feb 2017

ABOUT AUTHOR

Naeema Mohamed Kutty received the B.Tech degree in Information Technology from University of Calicut, India,
in 2016. Currently, she is Post Graduate student with the Department of Computer Science and Engineering, Cochin
College of Engineering and Technology, Kerala. Her current research include Computer Vision, Image Processing,
Security and Privacy.

Shelmy Mathai obtained her Bachelor’s degree in Computer Science and Engineering from MG University, India
and Master’s degree in Computer Science and Information Technology from MG University, India. Currently, she is
working as Assistant Professor in the department of Computer Science and Engineering, Cochin College of Engineering
and Technology, India. Her current research include Computer Vision, and Image Processing, Image Saliency Detection,
Data Management System and Artificial Intelligence.

© www.ijarcsse.com, All Rights Reserved Page | 336

You might also like