Department of Electronics and Telecommunication Engineering

SMART ATTENDANCE SYSTEM


Keywords — pycharm, face-recognition, cmake,
Abstract— Face is the representation of one’s dlib, opencv, python.
identity. Hence, we have proposed an
automated student attendance system based on I. INTRODUCTION
face recognition. Face recognition system is The main objective of this project is to develop
very useful in life applications especially in face recognition based automated student
security control systems. The airport protection attendance system. In order to achieve better
system uses face recognition to identify suspects performance, the test images and training
and FBI (Federal Bureau of Investigation) uses images of this proposed approach are limited
face recognition for criminal investigations. In to frontal and upright facial images that consist
our proposed approach, firstly, video framing of a single face only. The test images and
is performed by activating the camera through training images have to be captured by using
a userfriendly interface. The face ROI is the same device to ensure no quality
detected and segmented from the video frame difference.of various users.Use of face
by using Viola-Jones algorithm. In the pre- recognition for the purpose of attendance
processing stage, scaling of the size of images is marking is the smart way of attendance
performed if necessary in order to prevent loss management system.Face recognition is more
of information. The median filtering is applied accurate and faster technique among other
to remove noise followed by conversion of techniques and reduces chance of proxy
colour images to grayscale images. After that, attendance.Face recognition provide passive
contrast-limited adaptive histogram identification that is a person which is to be
equalization (CLAHE) is implemented on identified does not to need to take any action
images to enhance the contrast of images. In for its identity. Face recognition involves two
face recognition stage, enhanced local binary steps, first step involves the detection of faces
pattern (LBP) and principal component and second step consist of identification of
analysis (PCA) is applied correspondingly in those detected face images with the existing
order to extract the features from facial images. database. Face recognition works either in
In our proposed approach, the enhanced local form of appearance based which covers the
binary pattern outperform the original LBP by features of whole face or feature based which
reducing the illumination effect and increasing covers the geometric feature like eyes, nose,
the recognition rate. Next, the features eyebrows, and cheeks to recognize the face
extracted from the test images are compared
with the features extracted from the training
images. The facial images are then classified
and recognized based on the best result
obtained from the combination of algorithm,
enhanced LBP and PCA. Finally, the
attendance of the recognized student will be II. LITERATURE REVIEW
marked and saved in the excel file. The average
2.1 Student Attendance System
accuracy of recognition is 100 % for good
quality images, 94.12 % of low-quality images
and 95.76 % for Yale face database when two
images per person are trained.

DISADVANTAGES OF RFID (RADIO FREQUENCY background, illumination, pose, expression,
IDENTIFICATION) CARD SYSTEM, FINGERPRINT occlusion, rotation, scaling and translation.
SYSTEM AND IRIS RECOGNITION SYSTEM. RFID
CARD SYSTEM IS IMPLEMENTED DUE TO ITS Methodology
SIMPLICITY. HOWEVER, THE USER TENDS TO HELP  The proposed system is designed for
THEIR FRIENDS TO CHECK IN AS LONG AS THEY automating the attendance of the different
HAVE THEIR FRIEND’S ID CARD. THE FINGERPRINT organization and reduces the flaws of
SYSTEM IS INDEED EFFECTIVE BUT NOT EFFICIENT existing manual system.
BECAUSE IT TAKES TIME FOR THE VERIFICATION  The system calculate the attendance
PROCESS SO THE USER HAS TO LINE UP AND subject wise, that is the data of students
PERFORM THE VERIFICATION ONE BY ONE. and subjects are added manually by
HOWEVER FOR FACE RECOGNITION, THE HUMAN administrator, and whenever time for
FACE IS ALWAYS EXPOSED AND CONTAIN LESS corresponding subject arrives the system
INFORMATION COMPARED TO IRIS. IRIS automatically starts taking snaps and find
RECOGNITION SYSTEM WHICH CONTAINS MORE whether human faces are appear in the
DETAIL MIGHT INVADE THE PRIVACY OF THE USER. given image or not.
VOICE RECOGNITION IS AVAILABLE, BUT IT IS LESS  We have used Histogram of Oriented
ACCURATE COMPARED TO OTHER METHODS. Gradient for face detection and deep
HENCE, FACE RECOGNITION SYSTEM IS SUGGESTED learning techniques to calculate and
TO BE IMPLEMENTED IN THE STUDENT compare 128-d face features for face
ATTENDANCE SYSTEM. recognition.
 Once faces are detected and recognize with
Advantages & Disadvantages of Different the existing database, system calculate
Biometric System attendance for the recognize students with
the respective subject id in real time.
System Type Advantages Disadvantages  And an excel sheet generated and saved by
the system automatically.
RFID card Simple Fraudulent
system usage
Fingerprint Accurate Time- FACE RECOGNITION PROCESS
system consuming
Voice - Less accurate
recognition compared to
system others
Iris Accurate Privacy
recognition Invasion
system

II.2 Face Detection

Difference between face detection and face
recognition are often misunderstood. Face
detection is to determine only the face segment
or face region from image, whereas face
recognition is to identify the owner of the III. RESULTS AND DISCUSSIONS
facial image. A few factors which cause face
detection and face recognition to encounter
difficulties. These factors consist of
 will be very helpful and less prone to errors as
compared to manual process. This will also reduce
manipulation of attendance record done by
students and it will save time as well. The future
scope of the proposed work can be, capturing
multiple detailed images of the students and using
any cloud technology to store these images. The
system can be configured and used in Atm
machines to detect frauds.Also, the system can be
used at the time of elections where the voter can
be identified by recognizing the face.

Testing of Images V. CONCLUSION

 Smart attendance management system is
designed to solve the issues of existing
manual systems.
 We have used face recognition concept to
mark the attendance of student and make
the system better.
 The system performs satisfactory in
different poses and variations.
Attendance Marking  In future this system need be improved
because these system sometimes fails to
recognize students from some distance.
 Also we have some processing limitation,
working with a system of high processing
may result even better performance of this
system.

VI. REFERENCES
 [1] Kar, Nirmalya, et al. "Study of implementing
automated attendance system using face recognition
technique." International Journal of computer and
communication engineering 1.2 (2012): 100.
 [2] RoshanTharanga, J. G., et al. "Smart attendance
using real time face recognition (smart-fr)."
Department of Electronic and Computer
Engineering, Sri Lanka Institute of Information
Technology (SLIIT), Malabe, Sri Lanka (2013)
 [3] Selvi, K. Senthamil, P. Chitrakala, and A.
Face Recognition Antony Jenitha. "Face recognition based attendance
marking system." Corresponding Author: S.
IV. FUTURE SCOPE Rajkumar*, Email: rajkumarsrajkumar@ gamil.
com (2014).
Almost all academic institutions require
 [4] Joseph, Jomon, and K. P. Zacharia. "Automatic
attendance record of students and maintaining attendance management system using face
attendance manually can be hectic as well as time recognition." International Journal of Science and
consuming task. Hence maintaining attendance Research (IJSR) 2.11 (2013): 327- 330.
automatically with the help of face recognition
 [5] MuthuKalyani, K., and A. VeeraMuthu. "Smart
application for AMS using face recognition."
Computer Science & Engineering 3.5 (2013): 13.
 [6] Deshmukh, Badal J., and Sudhir M. Kharad.
"Efficient Attendance Management: A Face
Recognition Approach." (2014).