fromm-feed是什么意思
外文标题：
Face Recognition-Based Mobile Automatic Classroom Attendance
Management System
外文作者：
Refik Samet,Muhammed Tanriverdi
文献出处
: 2018 International Conference on Cyberworlds (
如觉得年份太老，
可改为近
2
年，毕竟很多毕业生都这样做
)
英文
2937
单词，
20013
字符
(
字符就是印刷符
)
，中文
4819
汉字。
Face Recognition- Based Mobile Automatic Classroom
Attendance Management System
Abstract
—
Classroom attendance check is a contributing factor to student participation
and the final success in the courses. Taking attendance by calling out names or
passing around an attendance sheet are both time-consuming, and especially the latter
is open to easy fraud. As an alternative, RFID, wireless, fingerprint, and iris and face
recognition-based methods have been tested and developed for this purpose. Although
these methods have some pros, high system installation costs are the main
disadvantage. The present paper aims to propose a face recognition-based mobile
automatic classroom attendance management system needing no extra equipment. To
this end, a filtering system based on Euclidean distances calculated by three face
recognition techniques, namely Eigenfaces, Fisherfaces and Local Binary Pattern, has
been developed for face recognition. The proposed system includes three different
mobile applications for teachers, students, and parents to be installed on their smart
phones to manage and perform the real-time attendance-taking process. The proposed
system was tested among students at Ankara University, and the results obtained were
very satisfactory.
Keywords
—
face detection, face recognition, eigenfaces, fisherfaces, local binary
pattern, attendance management system, mobile application, accuracy
UCTION
Most educational institutions are concerned with st
udents’ participation in courses
since student participation in the classroom leads to effective learning and increases
success rates [1]. Also, a high participation rate in the classroom is a motivating factor
for teachers and contributes to a suitable environment for more willing and
informative teaching [2]. The most common practice known to increase attendance in
a course is taking attendance regularly. There are two common ways to create
attendance data. Some teachers prefer to call names and put marks for absence or
presence. Other teachers prefer to pass around a paper signing sheet. After gathering
the attendance data via either of these two methods, teachers manually enter the data
into the existing system. However, those non-technological methods are not efficient
ways since they are time- consuming and prone to mistakes/fraud. The present paper
aims to propose an attendance- taking process via the existing technological
infrastructure with some improvements. A face recognition-based mobile automatic
classroom attendance management system has been proposed with a face recognition
infrastructure allowing the use of smart mobile devices. In this scope, a filtering
system based on Euclidean distances calculated by three face recognition techniques,
namely Eigenfaces, Fisherfaces, and Local Binary Pattern (LBP), has been developed
for face recognition. The proposed system includes three different applications for
teachers, students, and parents to be installed on their smart phones to manage and
perform a real-time polling process, data tracking, and reporting. The data is stored in
a cloud server and accessible from everywhere at any time. Web services are a
popular way of communication for online systems, and RESTful is an optimal
example of web services for mobile online systems [3]. In the proposed system,
RESTful web services were used for communication among teacher, student, and
parent applications and the cloud server. Attendance results are stored in a database
and accessible by the teacher, student and parent mobile applications.
The paper is organised as follows. Section II provides a brief literature survey. Section
III introduces the proposed system, and section IV follows by implementation and
results. The last section gives the main conclusions.
TURE SURVEY
Fingerprint reading systems have high installation costs. Furthermore, only one
student at a time can use a portable finger recognition device, which makes it a
time- consuming process [4]. In the case of a fixed finger recognition device at the
entrance of the classroom, attendance-taking should be done under the teacher's
supervision so that students do not leave after the finger recognition, which makes the
process time- consuming for both the teacher and the students. In case of RFID card
reading systems, attendance-taking is available via the cards distributed to students [5].
In such systems, students may resort to fraudulent methods by reading their friends'
cards. Also, if a student forgets his/her card, a non- true absence may be saved in the
system. The disadvantage of the classroom scanning systems with Bluetooth or
beacon methods is that each student must carry a device. Because the field limit of the
Bluetooth Low Energy (BLE) system cannot be determined, students who are not in
the classroom at the moment but are within the Bluetooth area limits may appear to be
present in the attendance system [6]. There are different methods of classroom
attendance monitoring using face recognition technology. One of these is a camera
placed at the classroom entrance and the students entering the classroom are
registered into the system by face recognition [7]. However, in this system students’
faces could be recognised, although students can leave the classroom afterwards, and
errors can occur in the polling information. Another method is the observation carried
out with a camera placed in the classroom and the classroom image taken during the
course. In this case, the cameras used in the system need to be changed frequently to
keep producing better quality images. Therefore, this system is not very useful and
can become costly. In addition to all the aforementioned disadvantages, the most
common disadvantage is that all these methods need extra equipment. The proposed
system has been developed to address these disadvantages. The main advantages of
the proposed system are flexible usage, no equipment costs, no wasted time, and easy
accessibility.
ED SYSTEM
ecture of the Proposed System
The proposed system's architecture based on mobility and flexibility is shown in
Fig.1.
Figure 1. System Architecture
The system consists of three layers: Application Layer, Communication Layer, and
Server Layer.
Application Layer: In the application layer, there are three mobile applications
connected to the cloud server by web services. a) Teacher Application: The teacher is
the head of the system, so he/she has the privilege to access all the data. By his/her
smart mobile device, he/she can take a photo of students in a classroom at any time.
After the taking the photograph, the teacher can use this photo to register attendance.
For this aim, the photo is sent to the cloud server for face detection and recognition
processing. The results are saved into a database together with all the reachable data.
The teacher gets a response by the mobile application and can immediately see the
results. The teacher can also create a student profile, add a photo of each student, and
add or remove a student to/from their class rosters. He/she can as well create and
delete courses. Each course has a unique six- character code. The teacher can share
this code with his/her students so they can access their attendance results via the
student application. The teacher can access to all data and results based on each
student's recognized photo stamped with a date. Additionally, an email message with
attendance data of a class in Excel format can be requested, while the analytics of the
attendance results is provided in the application. b) Student Application: Students can
sign in courses with the teacher's email address and the six-character course code.
They can add their photos by taking a photo or a 3-second long video. In case of
errors, their uploaded photos can be deleted. Students can only see limited results of
the attendance- taking process related to their attendance. To protect personal privacy,
the class photos and detected portrait photos of each student can be accessed only by
the teacher. If students are not in the classroom when an attendance-check is
performed, they are notified of the attendance-check. In case of errors (if a student is
present, but not detected by the system), he/she can notify the teacher so he/she can
fix the problem. c) Family Application: Parents can see their children's attendance
results for each class. Additional children profiles can be added into the system. Each
parent is added to the student's application with name, surname, and email address.
When a student adds his/her parents, they are automatically able to see the attendance
results. They are also notified when their child is not in the classroom.
2) Communication Layer: RESTful web services are used to communicate between
the applications and server layers. Requests are sent by the POST method. Each
request is sent with a unique ID of the authorised user of the session. Only the
authorised users can access and respond the the data to which they have right to
access. Due to its flexibility and fast performance, JSON is used as the data format for
web services response [8]. With this abstract web service layer, the system can easily
be used for a new item in the application layer, such as web pages or a new mobile
operating system.
3)Server Layer: The server layer is responsible for handling the requests and sending
the results to the client. Face detection and recognition algorithms are performed in
this layer and more than 30 different web services are created for handling different
requests from mobile applications.
Detection
Accurate and efficient face detection algorithms improve the accuracy level of the
face recognition systems. If a face is not detected correctly, the system will fail its
operation, stop processing, and restart. Knowledge-based, feature- based,
template-based, and statistics-based methods are used for face detection [9]. Since the
classroom photo is taken under the teacher's control, pose variations could be limited
to a small range. Viola-Jones face detection method with Ada- boost training is shown
as the best choice for real-time class attendance systems [9, 10]. In the most basic
sense, the desired objects are firstly found and introduced according to a certain
algorithm. Afterwards, they are scanned to find matches with similar shapes [11].
Recognition
There are two basic classifications of face recognition based on image intensity:
feature-based and appearance-based [12]. Feature-based approaches try to represent
(approximate) the object as compilations of different features, for example, eyes, nose,
chin, etc. In contrast, the appearance-based models only use the appearance captured
by different two-dimensional views of the object-of- interest. Feature-based techniques
are more time-consuming than appearance-based techniques. The real-time attendance
management system requires low computational process time. Therefore, three
appearance-based face recognition techniques such as Eigenfaces, Fisherfaces and
LBP are used in the tested system. Fisherfaces and eigenfaces techniques have a
varying success rate, depending on different challenges, like pose variation,
illumination, or facial expression [13]. According to several previous studies, face
recognition using LBP method gives very good results regarding speed and
discrimination performance as well as in different lighting conditions [14, 15].
Euclidean distance is calculated by finding similarities between images for face
recognition. A filtering system based on Euclidean distances calculated by Eigenfaces,
Fisherfaces and LBP has been developed for face recognition. According to the
developed system, firstly, minimum Euclidean distances of LBP
, Fisherfaces and
Eigenfaces algorithms are evaluated in defined order. If the Euclidean distance of LBP
algorithm is less than 40; else if Euclidean distance of Fisherfaces algorithm is less
than 250; else if Euclidean distance of Eigenfaces algorithm is less than 1500,
recognized face is recorded as the right match. Secondly, if the calculated Euclidean
distances by the three methods are greater than the minimum Euclidean distances, the
second level Euclidean distances (40-50 (for LBP), 250-400 (for Fisherfaces), 1500-
1800 (for Eigenfaces)) are evaluated in the same way. If the second level conditions
are also not met, the filter returns the wrong match. Thirdly, if any two algorithms
give the same match result, the match is recorded correctly. Finally, if no conditions
are met, the priority is given to the LBP algorithm and the match is recorded correctly.
The system’s specific architecture aimed for flexibility, mobility, and low
-cost by
requiring no extra equipment. At the same time, its objective was to provide access to
all users at any time. The system thus offers a real-time attendance management
system to all its users.
ENTATION AND RESULTS
The following platform was used. The cloud server has a 2.5 GHz with 4-core CPU,
8GB RAM, and 64-bit operating system capacity. Viola-Jones face detection
algorithm and Eigenfaces, Fisherfaces and LBP face recognition algorithms were
implemented based on OpenCV. Tests were done with both iOS and ANDROID.
Forty different attendance monitoring tests were performed in a real classroom,
including 11 students, and 264 students’ faces were detected. Tables I, II, and III show
detection and recognition accuracy of all three different types of tested algorithms
related to the Euclidean distance.
Priority ordering for 3 algorithms was arranged according to accuracy rate for each
interval. In test results, 123, 89, and 85 false recognitions were detected for
Eigenfaces, Fisherfaces and LBP
, respectively. By the help of the developed filtering
system, the number of false recognitions decreased to 65. Out of 40 implemented
attendance monitoring tests, 10 were conducted with 1 face photo of each student in
database in Step-I, 20 were conducted when the number of face photos increased up
to 3 in Step-II, and 10 recognition processes were conducted with more than 3 face
photos in database in Step-III. Table IV shows the obtained results.
The most important limitation of tested attendance monitoring process is decreased
success with increasing distance between the camera and students. The results
regarding students sitting in front seats are more accurate in comparison to results
regarding students sitting in the back. Secondly, the accuracy rates may have
decreased due to the blurring caused by vibration while the photo was taken. Thirdly,
in some cases one part of the student's face may be covered by another student sitting
in front of him/her, which may hamper a successful face recognition process. Since
the classroom photos are taken in uncontrolled environments, the illumination and
pose could, to a large extent, affect the accuracy rate. The developed filtering system
minimizes these effects. To increase accuracy, pose tolerant face recognition approach
may also be used [16, 17].
SIONS
The present paper proposes a flexible and real-time face recognition-based mobile
attendance management system. A filtering system based on Euclidean distances
calculated by Eigenfaces, Fisherfaces, and LBP has been developed. The proposed
system eliminates the cost for extra equipment, minimizes attendance- taking time, and
allows users to access the data anytime and anywhere. Smart devices are very user-
friendly to perform classroom attendance monitoring. Teachers, students, and parents
can use the application without any restrictions and in real-time. Since the internet
connection speed has been steadily increasing, high quality, larger images can be sent
to the server. In addition, processor capacity of the servers is also increasing on daily
basis. With these technological developments, the accuracy rate of the proposed
system will also be increased. Face recognition could be further tested by other face
recognition techniques, such as Support Vector Machine, Hidden Markov Model,
Neural Networks, etc. Additionally, detection and recognition processes could be
performed on smart devices once their processor capacity is sufficiently increased.
REFERENCES
[1]L. Stanca,
Evidence for Introductory Microeconomics,
–
266, 2006.
[2]P
.K. Pani and P
. Kishore,
A quantile regression analysis,
8 no. 3, pp. 376-389, 2016.
fromm-feed是什么意思
fromm-feed是什么意思
fromm-feed是什么意思
fromm-feed是什么意思
fromm-feed是什么意思
fromm-feed是什么意思
fromm-feed是什么意思
fromm-feed是什么意思
本文更新与2021-01-20 05:35，由作者提供，不代表本网站立场，转载请注明出处：https://www.bjmy2z.cn/gaokao/536856.html