Classroom Attendance Using Face Detection and Raspberry-Pi: Sayali Mhaske

Download as pdf or txt
Download as pdf or txt
You are on page 1of 4

Classroom Attendance Using Face Detection and Raspberry-Pi

Sayali Mhaske
Student, Department of Computer Engineering, Pune, Maharashtra, India

ABSTRACT
The attendance system will remain primitive. Where the teacher calls the name of students to mark their
attendance. This system can be easily manipulated .in order to overcome the issues biometrics of the students
can involve. this method of camera is fixed in the class room and its capture the images then the faces are
detected. To store the dataset and capture the images. Otherwise the faces is recognize and marking the attendance.

Keywords: Face detection, face recognition, camera, attendance system, database

I. INTRODUCTION burden of its staff. Particularly, for attendance system


which adopts human face recognition (HFR) technique,
Attendance monitoring system is very important such a system commonly involves the process of
process in almost all the organization and institutions. extracting key features from any facial image of student
It have used python high level language and currently captured at the time he/she is entering the classroom, or
advanced level of open CV source to used in this when everybody already occupies his/her seat in the
system. In traditional face-to-face (F2F) class setting, classroom. Upon its successful recognition, it proceeds to
student attendance record is one of the important issues marking that recognized student’s attendance
dealt with any school, college and university from time automatically. Following that general idea, the discussion
to time. To keep the student attendance record valid and of this paper is based on the known face recognition
correct, the faculty staff should have a proper mechanism techniques in its endeavour to develop a specific
for verifying and maintaining or managing that computer application which can be used for recognizing
attendance record on regular basis. any enrolled student automatically from the digital
images captured in classroom.
In general, there are two types of student attendance
system, i.e. manual attendance system (MAS) and II. BLOCK DIAGRAM
automated attendance system (AAS). By practicing
manual recording, faculty staff may experience difficulty
in both verifying and maintaining each student’s record
in classroom environment on regular basis, especially in
classes attended by a large number of students. In practice,
the manual system also requires more time for recording
and calculating the average attendance of each enrolled
student. On the other hand, the

automated attendance system may offer some benefits to


the faculty, at least it may lessen the administrative

Department Of Computer Engineering,Dr.DY Patil School Of Engineering,Lohegaon,Pune 1


A. Capture Video:
The Camera is fixed at a specific distance inside a
classroom to capture videos of the frontal images of the
entire students of the class.
A. RASPBERRY Pi 3:
The Raspberry-Pi is a low cost, credit card sized computer B.SEPARATE AS FRAMES FROM VIDEO:
that plugs into computer monitor or tv and uses a standard The captured video needs to be converted into frames
keyboard or mouse. per second for easier detection and recognition of the
The Raspberry Pi is equipped with ENC28J60 which is a students face to generate the attendance database.
ethernet chip to get connected to internet.

B. CAMERA:
A camera is an instrument which is used for capturing
video or image which may be stored locally , transmitted
to another location or both.

C. SQL DATABASE :
Structured Query Language is a domain-specific
language used in programming and designed for
managing data held in a relational database management C. FACE DETECTION:
system (RDBMS), or for stream processing in a relational Face Detection is the process where the image, given as
data stream management system (RDSMS). It is an input (picture) is searched to find any face, after
particularly useful in handling structured data. finding the face the image processing cleans up the
facial image for easier recognition of the face.

III. PROPOSED APPROACH

The main working principle of the project is that, the


video captured data is converted into image to detect and
recognize it. Further the recognized image of the student
is provided with attendance, else the system marks the
database as absent.

D.FACE RECOGNITION:

Department Of Computer Engineering,Dr.DY Patil School Of Engineering,Lohegaon,Pune 2


After the completion of detecting and processing the face,
it is compared to the faces present in the numbers. For example, the integral of area ABCD is
students' database to update the attendance of the students. calculated as II(yA,xA) – II(yB,xB) – II(yC,xC) +
II(yD,xD).

Detection happens inside a detection window. A


minimum and maximum window size is chosen, and for
each size a sliding step size is chosen. Then the detection
window is moved across the image as follows:

1.Set the minimum window size, and sliding step


corresponding to that size.
2.For the chosen window size, slide the window vertically
and horizontally with the same step. At each step, a set of
N face recognition filters is applied. If one filter gives a
positive answer, the face is detected in the current widow.
3.If the size of the window is the maximum size stop the
E.POST PROCESSING: procedure. Otherwise increase the size of the window and
The post-processing mechanism involves the process of corresponding sliding step to the next chosen size and go
updating the names of the student into an excel sheet. The to the step 2.
excel sheet can be maintained on a weekly basis or 4.Each face recognition filter (from the set of N filters)
monthly basis to record the students' attendance. contains a set of cascade-connected classifiers. Each
classifier looks at a rectangular subset of the detection
IV. ALGORITHM window and determines if it looks like a face. If it does,
the next classifier is applied. If all classifiers give a
The Viola-Jones algorithm is a widely used mechanism positive answer, the filter gives a positive answer and the
for object detection. The main property of this algorithm face is recognized. Otherwise the next filter in the set of
is that training is slow, but detection is fast. This N filters is run.
algorithm uses Haar basis feature filters, so it does not use
multiplications. Each classifier is composed of Haar feature extractors
(weak classifiers). Each Haar feature is the weighted sum
The efficiency of the Viola-Jones algorithm can be of 2-D integrals of small rectangular areas attached to
significantly increased by first generating the integral each other. The weights may take values ±1.
image.

The classifier decision is defined as:

The integral
image allows integrals for the Haar extractors to be
calculated by adding only four

Department Of Computer Engineering,Dr.DY Patil School Of Engineering,Lohegaon,Pune 3


fm,i is the weighted sum of the 2-D integrals. is the
decision threshold for the i-th feature extractor. αm,i and
βm,i are constant values associated with the i-th feature
extractor. θm is the decision threshold for the m-th
classifier.

V. CONCLUSION

Thus, the aim of this paper is to capture the video and


images of the students, convert it into frames, relate it
with the database to ensure their presence or absence,
mark attendance to the particular student to maintain the
record. The Automated Classroom Attendance System
helps in increasing the accuracy and speed ultimately
achieve the high-precision real-time attendance to meet
the need for automatic classroom evaluation.

VI. REFERENCES

[1] M. Turk and A. Pentland, “Eigenfaces for recognition," Journal of


Cognitive Neuroscience, vol. 3, no. 1, pp.71-86, 1991.

[2] K. I. Diamantaras and S. Y. Kung, Principal Component Neural


Networks: Theory and Applications, John Wiley & Sons, Inc., 1996.

[3] Viola, P., & Jones, M. (2001). Rapid object detection using a
boosted cascade of simple features. In Computer Vision and Pattern
Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE
Computer Society Conference.

[4] Rohit, C., Baburao, P., Vinayak, F., &Sankalp, S. (2015).


attendance management system using face recognition. International
Journal for Innovative Research in Science and Technology, 1(11), 55-
58.

[5] NirmalyaKar, MrinalKantiDebbarma, AshimSaha, and


DwijenRudra Pal, “Implementation of Automated Attendance
System using Face Recognition”, International Journal of Computer
and Communication Engineering, Vol. 1, No. 2, July 2012.

[6] Benfano Soewito, Ford Lumban Gaol,” Attendance System on


Android Smartphone”, 2015 International Conference on Control,
Electronics, Renewable Energy and Communications (ICCEREC).

Department Of Computer Engineering,Dr.DY Patil School Of Engineering,Lohegaon,Pune 4

You might also like