Conference PaperPDF Available

Reserve Parking and Authentication of Guest Using QR Code

Authors:
  • Qaiwan International University (QIU)
Reserve Parking and Authentication of Guest Using
QR Code
Ahmed Abdullah Ahmed*1, Omar Ismael Al-Sanjary2, Saranya Kaeswaren2
1Faculty of Engineering & Science, Qaiwan International University/Raparin, Sulaymaniyah, Kurdistan Region-Iraq
2Faculty of Information Science & Engineering, Management & Science University, 40100 Shah Alam, Malaysia
* Corresponding author: ahmed.abdullah@kti.edu.krd
Abstract In the current world permeated by the use of
technology, parking appears to be an issue that has not been
given serious consideration. This paper developed and
proposed an online digital parking application, with the help of
Quick Response (QR) code for the reduction of workforce in
parking areas. In Android technology, every compatible device
can read QR codes and scan them to provide considerable
information. The QR code is scanned by the system for the
details of the user for authorized entrance. Following such
scan, the user is allotted a parking space on the basis of
availability, and upon leaving the allotted space, it will remain
an empty slot to be allotted to the next user. This can mitigate
human effort through the use of simple software and
hardware, while ensuring authorization and safety to users.
Keywords: QR code, android app, parking system, android
studio, and authentication.
I. INTRODUCTION
A parking lot or a car park is generally described as a
spacious empty area, intended for parking of vehicles and in
majority of countries, where cars are the primary
transportation mode, parking lots are important features of
cities and suburban regions. In modern parking lots,
technologies are used to assist motorists and drivers to find
empty spaces through parking guidance and information
systems, after which the vehicles are retrieved such is a
convenient traveling and daily experience. The benefits of
modern car parks include adaptive lighting, sensors, Indoor
Positioning System (IPS) and even mobile payment
alternatives.
In the same way, car parks in shopping malls are fitted
with cameras one each slot to keep track of total occupancy
and to determine where lost cars are located. In relation to
this, there are several online booking technologies that assist
drivers search for long-term parking in an automated way,
while facilitating cost-savings for those who book ahead of
time. Real time inventory management checking technology
is used to display available parking lots, categorized by price
and distance from the target destination. Thus, such modern
online booking technology assists guests to determine
parking spaces conveniently and easily. They facilitate easy
parking for the guest rather than having them go around and
around looking for an empty parking slot. This may be
resolved through the increase of the number of parking
spaces but such solution calls for significant investment and
construction, and also extra spaces block traffic and
inhabitants of the area.
Thus, this paper proposes an application that provides
easier and more convenient solution. The project involves
creating a system/application for parking, with the primary
idea of enabling guests find parking areas expediently
without hassle. Guests need to ensure that they have the app
in their device for logging in, filling up parking details and
time periods, after which, a QR code is sent to their email for
confirmation. They can proceed to scan the QR code upon
reaching the parking area for authentication and entry.
II. RELATED WORKS
The present study examines several smart parking
systems that can assist drivers to park their vehicles and
provides a discussion of their weaknesses. The focus is
placed on designing and proposing a new smart parking
system that could resolve the tedious search of drivers for
vacant parking spaces in parking lots.
In a related study [1], the aim was to furnish a dynamic
solution of the concept of parking guidance system via the
internet, through the use of current techniques. The system
improves the parking system existing components in
colleges, running on mobile phone platform and providing a
visual display of available lots. The primary requirements
included GPS, QR code scanner, and mobile web map. The
study examined six parking spaces in the College of
Engineering and published it on the web map server to be
made available for drivers [28].
Moreover, in another study, [2] proposed a solution to
parking issues, using Geographic Information System (GIS),
where all the activities are reflected in the database. The
system involved the publication of a Web Server Application
Programming Interface (API) over the internet, whereby the
driver can access it through an application.
Moving on to another work in this area, [3] proposed the
Ease Parking Application, to be integrated into the system
between hardware of parking sensor and software of mobile
application. The application had three major functions
namely, displaying information on available parking, setting
parking ID and location, and user information. It also
displayed the building map and the plan for each floor
highlighting the parking availability. For parking location,
the user has to set the parking ID through manual keying-in
or QR code reader, then the parking location can be accessed
from any place in the building.
III. AUTHENTICATION TECHNIQUES
Schematic code methods like that proposed in [4], which is
Datamatrix QR codes, involve easy print image and scan
procedure, where print image and scan procedure provide
invisible alterations to a copy. In case the image is
written/printed, the pixel values will be changed, and this
idea was extensively used for the detection of original QR or
forged. It assists data authentication and authentication of
duplicates. Moreover, there are several methods that the idea
of sensitivity towards patterns and scan procedure has been
utilized, with some for the purpose of digital authentication
or duplicate authentication [5]. In relation to this, a
reproduction detection design or CDP is referred to as an
optimum entropy copyproduced using secret password key.
Based on the application and system, CDP is combined with
random image that has expressive data (e.g., stamp, logo and
barcode). The verification result depends on the contrast of
pixel values in image and printed CDP. Another method is
used for detecting fake data through textured copy [6], with
the textured copy having a visual letter. The system is useful
for the detection of real or fake data. Textured copy, in this
case, comprises of many patterns and sequences. The
technique of pattern recognition largely depends on the
amount of correlation found in authentication request.
Meanwhile, extra authentication application can be
conducted through symmetrical distortion in pattern and
image process [7]. This encapsulates pre-processing
procedure involving copy, discovery of symmetrical
distortion and alteration process with the last one based on
the achievement of exploration of points.
IV. PROPOSED METHOD
The proposed study was suggested to be suitable for
commercial areas for employees working in the area. One of
the advantages is the clarification of issues linked to the
implementation, synchronization, load balancing (e.g.,
communication, overhead and reservation) as the reservation
authority was fitted in each parking lot
Fig. 1. The algorithm of the system
This study used the AGILE development methodology to
develop the system. Such method is simple and easy to
understand when developing an application. The next figure
displays AGILE method, with its six development steps
(requirements, plan, design, develop, release, and track &
monitor).
Fig. 2. Displays AGILE method, with its six development steps
The entire steps are achieved after which they are tested and
the whole system flow is displayed in the following flow
chart.
Fig. 3. Displays guests book their parking
The figure depicts the way the guests book their parking
spaces for a specific time and day. They first need to log into
the application and complete their sign in details, after
which, they can book a parking space or sing in to view the
QR code that was earlier booked
Fig. 3. Booking the data and lots
After the selection of parking date and completion of
personal details, a QR code is stored in one of the application
tabs for the guests to retrieve on the date of booking. This is
scanned by the parking lot security guard. But after the guest
has entered the parking lot, the QR code cannot be reused in
the same day or any other day after.
An identity authentication method is integrated for the
implementation of admission control for staff attempting to
attach to the network. Authenticated operators can be
attached to the system and for the authorization of guests to
the network, they can access the innovativeness exhibition
room, wherein managers can provide QR code and the guests
can be admitted through the network via QR code scanning.
The system enables 1) public QR code verification, 2)
organize visitor’s account policy for public QR codes
generation, 3) generate and transfer public QR code, pattern
and post it in public zones that visitors can have scanned by
the system, 4) modify the authentication and verification
success sheets; following the verification of the pass, the
public QR code is skimmed and the verification success
sheet is automatically displayed, 5) organize a gateway sheet
push rule to provide the customized verification sheet to
guests, and 6) improve visitor authorization consequences
and authorization instructions to appropriate access consent
to guests following the confirmation of their validity
V. SYSTEM DESIGN AND INTERFACE
The system is designed in such a way that the guest needs
to login through the login screen with first time users
requested to sign up. After completing the signup details, the
user can move on to the login screen, and after logging in, a
calendar for the selective preferred data for booking of a
parking space appears. After the date selection, memos and
remarks can be left for the system to take note.
The QR code reader application is built on a smart
reserve parking system, implementing reservation service,
using data details to generate QR code algorithm. The
architecture of the system design (refer to Figure 1) proposes
a three component-scheme in the smart reserve parking
model: counting user, admin and security management
system. The application illustrates the parking lot based on
the designated area, with the corresponding value, category
and time. Data is obtained by the user of the parking lot area
and the designated period. The unique QR code of the user is
generated by the management system, wherein the individual
user’s details are encoded, to be authenticated by the system.
Every user reservation data is updated to display and
pinpoint the empty and reserved slots. Moreover, the security
management system determines each user through arbitrary
production of unique QR code and it scans the QR code
through a scanner to authenticate the details. The system is
time-effective eradicating the need to relay messages
between user and security management system for
authentication.
Furthermore, a related study [17] used QR Code (Rapid
Response Code), launched in 1994 by the Denso
Corporation. With over 40 versions of the QR Code
generator, and over four levels of error alteration, the
maximum representation size (current version) can include
7089 numeric information/4296 alphanumeric information
[17]. In this regard, the highest error alteration level enables
a 30% retrieval of representation code words, with the QR
Code having several progressive features enumerated as
follows [17];
1. High size information encryption QR code scanner
possesses high-sized information encoding, with
maximum representation of 7089 letterings, compared to
the 2710 letterings of PDF417.
2. High-sensitive interpretation fitted with Charge Coupled
Device (CCD) interpretation, which enables the
identification of more QR Codes representations per
second, compared to PDF417 with the same volume of
data.
3. Readable from any way from 360 degree in this regard,
the QR Code generator consists of a matrix 2D barcode
that can be read from anywhere in a 360 degree angle
while the PDF417 2D barcode is difficult to be read in
the same way.
The following are the phases of QR Code Generator
algorithm encoding and decoding:
a. Algorithm QR Encode
PHASE 1: Start
PHASE 2: Input the source file(infilled) or Text.
PHASE 3: Call GenSig(infile)
PHASE 4: Compress 'suepk','sig' and 'infile' into 'test.zip'
file
PHASE 5: Create an empty string data
PHASE 6: Convert 'test.zip' into string and store in 'data'
PHASE 7: Input the image format and resolution of the QR
Code to be generated
PHASE 8: Input Error Correction Level
PHASE 9: Using zxing[1] library method convert 'data' into
a BitMatrix object 'bitmatrix'
PHASE 10: Write bitmatrix to an image
PHASE 11: End BitMatrix represents a 2D matrix of bits.
QR Code Decoding
b. Algorithm QR Decode
PHASE 1: Start
PHASE 2: Input QR Code image
PHASE 3: Construct a Binary Bitmap object 'bitmap' from
source image
PHASE 4: Using zxing library method decode the 'bitmap'
and store it in the object 'result'
PHASE 5: Convert 'result' into string and write it to
'result.zip'.
PHASE 6: Extract result.zip
PHASE 7: If requested by user call VerSig('supek','sig',infile)
PHASE 6: End
VI. CONCLUSIONS
The creation and application of the system comes on quite
handy for parking guests as it fits their convenience. The
project process provided a learning experience, with skills
and knowledge being clarified for the creation of application.
Specifically, the QR code technology has been extensive
used as a technology in day-to-day life. Within such
technology, algorithms are integrated in real time data
processing used in parking-related technologies, self-parking
vehicles, speech parking, sensor-based parking and robotic
parking to enhance daily lives. This study proposed a system
that could enhance the lifestyle of individuals, particularly
those with vehicles. Online car parking application could
benefit drivers as they can book their parking slots ahead of
time. Universities should leverage this idea as it provides
countless advantages to the users.
ACKNOWLEDGMENT
We would like to thank the anonymous reviewers whose
comments have improved this paper and those who assisted
or participated in this research.
REFERENCES
[1] Muhammad, K., Ahmad, J., Sajjad, M., & Zubair, M. (2015).
Secure image steganography using cryptography and image
transposition. arXiv preprint arXiv:1510.04413.
[2] Chandramouli, R., &Memon, N. (2001, October). Analysis of
LSB based image steganography techniques. In Proceedings
2001 International Conference on Image Processing (Cat. No.
01CH37205) (Vol. 3, pp. 1019-1022). IEEE.
[3] Silman, J., 2001. Steganography and steganalysis: an
overview. Sans Institute, 3, pp.61-76.
[4] Jamil, T., 1999. Steganography: the art of hiding information in
plain sight. IEEE potentials, 18(1), pp.10-12.
[5] Wang, H. and Wang, S., 2004. Cyber warfare: steganography
vs. steganalysis. Communications of the ACM, 47(10), pp.76-82.
[6] Anderson, R.J. and Petitcolas, F.A., 1998. On the limits of
steganography. IEEE Journal on selected areas in
communications, 16(4), pp.474-481.
[7] Vembrina, Y., 2006. Spread Spectrum Steganograpy. Bandung:
Sekolah Teknik Elektro dan Informatika.
[8] Artz, D., 2001. Digital steganography: hiding data within
data. IEEE Internet computing, 5(3), pp.75-80.
[9] Pandya, M. and Jani, A., 2018. A Hybrid Approach for Secure
Message Communication and Color Image
Watermarking. Elixir Int. J. Digit. Process, 1(114), p.4.
[10] Bauer, F.L., 2002. Decrypted secrets: methods and maxims of
cryptology. Springer Science & Business Media.
[11] Luo, W., Huang, F. and Huang, J., 2010. Edge adaptive image
steganography based on LSB matching revisited. IEEE
Transactions on information forensics and security, 5(2),
pp.201-214.
[12] Muhammad, K., Ahmad, J., Rho, S. and Baik, S.W., 2017.
Image steganography for authenticity of visual contents in social
networks. Multimedia Tools and Applications, 76(18),
pp.18985-19004.
[13] Bailey, K. and Curran, K., 2006. An evaluation of image-based
steganography methods. Multimedia Tools and
Applications, 30(1), pp.55-88.
[14] Muhammad, K., Ahmad, J., Rehman, N.U., Jan, Z. and Qureshi,
R.J., 2015. A secure cyclic steganographic technique for color
images using randomization. arXiv preprint arXiv:1502.07808.
[15] Karim, S.M., Rahman, M.S. and Hossain, M.I., 2011,
December. A new approach for LSB based image
steganography using secret key. In 14th international
conference on computer and information technology (ICCIT
2011) (pp. 286-291). IEEE.
[16] Morkel, T., Eloff, J.H. and Olivier, M.S., 2005, June. An
overview of image steganography. In ISSA (pp. 1-11).
[17] Pund-Dange, S., 2018. Steganography: A Survey. In Cyber
Security (pp. 327-333). Springer, Singapore.
[18] Xiao Steganography 2.6.1, 2006/7, (<http://xiao-
steganography.en.softonic.com/>)
[19] Sloan, T. and Hernandez-Castro, J., 2018. Dismantling
OpenPuff PDF steganography. Digital Investigation, 25, pp.90-
96.
[20] Vaidya, S., 2017. OpenStego. Retrieved from OpenStego
website: https://www. openstego. com/features. html.
[21] Mike Williams. (2011).SteganographX Plus
https://www.downloadcrew.com/article/6634steganographx_plus
[22] Viceconti, M., Zannoni, C., Testi, D., Petrone, M., Perticoni, S.,
Quadrani, P., Taddei, F., Imboden, S. and Clapworthy, G., 2007.
The multimod application framework: a rapid application
development tool for computer aided medicine. Computer
methods and programs in biomedicine, 85(2), pp.138-151.
[23] Al-Sanjary, O. I., Ahmed, A. A., Jaharadak, A. A. B., Ali, M.
A., & Zangana, H. M. (2018, April). Detection clone an object
movement using an optical flow approach. In 2018 IEEE
Symposium on Computer Applications & Industrial Electronics
(ISCAIE) (pp. 388-394). IEEE.
[24] Al-Sanjary, O. I., Ghazali, N., Ahmed, A. A., & Sulong, G.
(2017, April). Semi-automatic Methods in Video Forgery
Detection Based on Multi-view Dimension. In International
Conference of Reliable Information and Communication
Technology (pp. 378-388). Springer, Cham.
[25] Al-Sanjary, O. I., Ahmed, A. A., Ahmad, H. B., Ali, M. A.,
Mohammed, M. N., Abdullah, M. I., & Ishak, Z. B. (2018,
December). Deleting Object in Video Copy-Move Forgery
Detection Based on Optical Flow Concept. In 2018 IEEE
Conference on Systems, Process and Control (ICSPC) (pp. 33-
38). IEEE.
[26] Al-Sanjary, O. I., & Sulong, G. (2015). Detection of video
forgery: A review of literature. Journal of Theoretical &
Applied Information Technology, 74(2).
[27] Ahmed, A. A., Al-Tamimi, M. S., Al-Sanjary, O. I., & Sulong,
G. (2017, April). Classification of arabic writer based on
clustering techniques. In International Conference of Reliable
Information and Communication Technology (pp. 48-58).
Springer, Cham.
[28] Ishak, Z., Rajendran, N., Al-Sanjary, O. I., & Razali, N. A. M.
(2020, February). Secure Biometric Lock System for Files and
Applications: A Review. In 2020 16th IEEE International
Colloquium on Signal Processing & Its Applications
(CSPA) (pp. 23-28). IEEE.
... Therefore, we gathered 3000 samples at a sampling rate of 10 Hz (10 samples per second), together with the timestamp-associated activity labels (hand-labelled by the observer). 76 A. Almusawi and A. H. Ali ...
... Such properties entail the protection of organizational data and optimal information systems. Information security assists in the prevention of breaches in confidential assets, data losses, erroneous deletion of data, and inaccurate production of data [73,76]. The Central Intelligence Agency (CIA) represents the four basic supports of information security as confidentiality, integrity, availability and non-repudiation. ...
Book
Full-text available
page:423 Big Data Analytics for Large Scale Wireless Body Area Networks; Challenges, and Applications
... The IoT refers to interconnected computing mechanisms, objects, animals, individuals and digital machines that make use of distinct identifiers and data transfer through a network sans interaction of human to human or human to computers [3][4][5][6][7]. A comprehensive IoT system combines four major elements, namely sensors, connectivity, data processing and user interface [8][9][10]. Sensors include 'talk' to the cloud using a connectivity device and following the entrance of data to the cloud, it is processed by software to carry out actions like alerting/adjusting the sensor device without the user's involvement [11][12][13]. ...
... The proposed system uses sensors as well as weather forecasting (E-SPEAK) [18,10] module to provide the conditions of the weather through an auditory process throughout the whole time and this is considered to be a crucial step towards the digital world, whereby inbuiltcloud/website is not required for weather prediction. The system requirements are presented in Table 1, wherein which a list of what needs to be done by the user is tabulated as well as the design. ...
... Forgery detection methods can be generally categorized into two categories, active and passive [6]. Active forgery detection methods aim to prevent forgery through the inclusion of active information in the printed document, e.g., watermarks, bar codes, etc. [7][8][9]. However, these methods suffer from a major drawback that documents cannot be verified unless such active information is included during or immediately after printing. ...
Conference Paper
Printed documents continue to be the most commonly used media for information transfer in official context. However, such documents may be subject to illegitimate modification or malicious purposes. Therefore, agencies must be able to verify their authenticity before accepting them. This work aims to identify and classify the current computational methods that are used to identify and detect a forgery in printed documents. We focus on methods that detect forger passively, i.e., no requirement of active information to be included in the document during or shortly after printing. Hence, we classify the methods into four general categories. First, detection based on printer and ink properties. The second is based on character-level features analysis that is based on detecting imperfections produced by scan, edit, and print forgery techniques. It is also possible to detect forgery through analysis of paper properties. Finally, forgery detection can be achieved by analyzing the pixel-level features.
... Such properties entail the protection of organizational data and optimal information systems. Information security assists in the prevention of breaches in confidential assets, data losses, erroneous deletion of data, and inaccurate production of data [73,76]. The Central Intelligence Agency (CIA) represents the four basic supports of information security as confidentiality, integrity, availability and nonrepudiation. ...
Chapter
There are minimal studies have attempted to shed light on the reality of the challenges and as such, the present paper brings forth studies identifying, quantifying, and prioritizing the challenges to motivate future authors to focus on the issues affecting the domain. Accordingly, a survey was conducted among researchers and practitioners (at the level of law enforcement and organizations) in order to investigate actual challenges and differentiate them from perceived challenges for the purpose of providing insight into the effects upon digital forensic domain in the near future. The study provided and collated a compact survey of the top significant challenges highlighted in the design/development of modern digital forensics tools. The study contributes to the identification of the important, mid- and long-term opportunities and issues that need to be taken into account by the security experts and network forensics in the field investigations fields.
Chapter
Nowadays, with the rapid growth of online marketing or online purchasing is increasing day by day as customers tend to purchase or buy goods online rather than physical shopping. This was due to the recent Covid-19 outbreak, which lead to a massive or vast of online shopping businesses or franchises to have emerged. However, with this vast growth of online businesses with massive online purchases being done every day, questions are being raised by customers as were these online businesses secure enough when comes to parcel delivery. With regards to that, a survey was conducted to gather customer’s feedback on the current online shopping method, whether was it secure enough or not and this gathered data was the main reason or input that provided purpose to initiate this research, where surprisingly, majority of the customers agreed that the current online shopping is not secured in terms of parcel delivery, in which there is no customer authentication process being done upon parcel delivered. Besides that, no designated parcel lockers are being built for unattended customers and even though there are parcel lockers, these lockers have low-security levels [1]. Therefore, the customer's concerns and the issues highlighted by previous researchers, explain the purpose of this research which was conducted to help curb the issues by implementing an alphanumeric sequence for customer verification and fingerprint sensing for customer confirmation during parcel delivery. Finally, this method will also be implemented for parcel lockers to enhance the security levels upon parcel collection.Keywordsalphanumeric sequencefingerprint sensingsecure parcel locker
Chapter
The banking industry performs credit score analysis as an efficient credit risk assessment method to determine a customer’s creditworthiness. In the banking industry, machine learning could be used for a variety of uses involving data analysis. A method of data analysis that is capable of self-regulation has been made possible by the development of modern techniques, such as classification approaches. The classification method is a form of supervised learning in which the computer acquires knowledge from the provided input data and then utilizes it to classify the dataset, which is used for training purposes. This study presents a comparative analysis of the various machine learning algorithms that are utilized to evaluate credit risk. The methods are used by utilizing the German Credit dataset that was collected from Kaggle, which consists of 1,000 instances and 11 attributes, all of which are used to determine if transactions are good or bad. The findings of data analysis using Logistic Regression, Linear Discriminant Analysis, Gaussian Naive Bayes, K-Nearest Neighbors Classifier, Decision Tree Classifier, Support Vector Machines, and Random Forest are compared and contrasted in this study. The findings demonstrated that the Random Forest algorithm forecasted credit risk effectively.KeywordsCredit RiskBankingMachine LearningPredictionFeatures
Conference Paper
Full-text available
Abstract— Digital video can be manipulated and edited easily because of the available robust video processing and editing software. In the current times, the digital video and digital image editing tools has contributed to the challenge in authenticating multimedia content in an accurate manner. It is now possible to modify, through adding and removing, pertinent evidence form a video recording without leaving a clue as to the tampering process. Even worse, some post-methods effects, which can insert and deleting object in order to mimic or hide a particular event in the frames of video, are also diffuse. Many endeavors have been focusing to detect like video copy-move manipulate to date; but, the accuracy rates are still far from satisfactory for improvement and the method do not locate the issue of region tampering detection and determine localization. Consequently, the study of this paper is aims to design and develop a new video copy-move forgery detection scheme with high accuracy based on optical flow methods.
Conference Paper
Full-text available
The availability of powerful editing software sophisticated digital cameras, and region duplication is becoming more and more popular in video manipulation where parts of video frames is pasted to another location to conceal undesirable objects. Most existing techniques to detect such tampering are mainly at the cost of higher computational complexity. Multi-view video contains locating a moving object (or multiple objects) over time and several frames representing different views of the same scene of the true width and height of an object in the front view are placed in the sequences of frames plane. In this paper, a new technique for video forgery detection using semi-automatic methods can be used for the three types of video forgery detection: (1) Copy-Move, (2) Splicing, and (3) Swapping-Frames based on a new dimension of multi-view frames. Thus, this idea is proposing new video views based on slices of video frames in Top-View and Side-View in doctored video. Experiment results show that our proposed schemes for new video views enable easy detection of visual inspection is used for the evaluation.
Article
Full-text available
Social networks are major sources of image sharing and secret messaging among the people. To date, such networks are not strictly bounded by copyright laws due to which image sharing, secret messaging, and its authentication is vulnerable to many risks. In addition to this, maintaining the confidentiality, integrity, and authenticity of secret messages is an open challenge of today’s communication systems. Steganography is one of the solutions to tackle these problems. This paper proposes a secure crystographic framework for authenticity of visual contents using image steganography, utilizing color model transformation, three-level encryption algorithm (TLEA), and Morton scanning (MS)-directed least significant bit (LSB) substitution. The method uses I-plane of the input image in HSI for secret data embedding using MS-directed LSB substitution method. Furthermore, the secret data is encrypted using TLEA prior to embedding, adding an additional level of security for secure authentication. The qualitative and quantitative results verify the better performance of the proposed scheme and provide one of the best mechanisms for authenticity of visual contents in social networks.
Conference Paper
Arabic text categorization for pattem recognitions is challenging. We propose for the first time a novel holistic method based on clustering for classifying Arabic writer. The categorization is accomplished stage-wise. Firstly, these document images are sectioned into lines, words, and characters. Secondly, their structural and statistical features are obtained from sectioned portions, Thirdly, F-Measure is used to evaluate the erformance of the extracted features and their combination in different linkage methods for each distance measures and different numbers of groups. Finally, experiments are conducted on the standard KHATT dataset of Arabic handwritten text comprised of varying samples from 1000 writers. The results in the generation step are obtained from multiple runs of individual clustering methods for each distance measures. The best results are achieved when intensity, lines slope and their combination set offeatures are applied. It is demonstrated that different numbers of clusters having good set offeatures can deliver significant improvements for the handwritten structures clustering.