2019
10
1
0
0
1

Jensen’s inequality for GGconvex functions
https://ijnaa.semnan.ac.ir/article_3725.html
10.22075/ijnaa.2017.11330.1555
1
In this paper, we obtain Jensen’s inequality for GGconvex functions. Also, we get inequalities alike to HermiteHadamard inequality for GGconvex functions. Some examples are given.
0

1
7


Gholamreza
Zabandan
Department of Mathematics, Faculty of Mathematical Sciences and Computer, Kharazmi University, Tehran, Iran
Iran
zabandan@khu.ac.ir
Jensen’s inequality
GGconvex
Integral inequality
1

Analysis of disassembled executable codes by abstract interpretation
https://ijnaa.semnan.ac.ir/article_4048.html
10.22075/ijnaa.2019.4048
1
The aim of this paper is to define the abstract domain, abstract operator, abstract semantic, the environments and states of disassembled executable codes as well as a way to analysis the disassembled executable codes. Nowadays, static analysis on disassembled code going to grow. Reverse engineering and malware analysis use this technique. Thus, we tried to perform pluralization the requirements of static analysis by abstract interpretation as well as report some specific and advantageous notes in this paper. In addition, we present an algorithm to obtain the control ow graph of disassembled code.
0

9
13


Mohammad hadi
Alaeiyan
Iran University of Science and Technology, Narmak, Tehran, 16844, Iran
Iran
hadi_alaeiyan@comp.iust.ac.ir
Static analysis
Abstract domain
Abstract operator
Abstract semantic
Environment and state of abstract interpretation
1

Optimally Local Dense Conditions for the Existence of Solutions for Vector Equilibrium Problems
https://ijnaa.semnan.ac.ir/article_3549.html
10.22075/ijnaa.2019.16783.1893
1
In this paper, by using Csequentially sign property for bifunctions, we provide sufficient conditions that ensure the existence of solutions of some vector equilibrium problems in Hausdorff topological vector spaces which ordered by a cone. The conditions which we consider are not imposed on the whole domain of the operators involved, but just on a locally segmentdense subset of the domain.
0

15
26


Sirous
Moradi
Arak University
Iran
sirousmoradi@gmail.com


Maryam
Shokouhnia
Department of Mathematics, Faculty of Science, Arak University, Arak, Iran
Iran
shokoohniam63@yahoo.com


Somaye
Jafari
Department of Mathematics, Arak University, Arak, Iran
Iran
s.jafari.math@gmail.com
locally segmentdense set
vector equilibrium problem
Csequentially sign property
1

Entropy of infinite systems and transformations
https://ijnaa.semnan.ac.ir/article_4050.html
10.22075/ijnaa.2019.17400.1931
1
The KolmogorovSinai entropy is a far reaching dynamical generalization of Shannon entropy of information systems. This entropy works perfectly for probability measure preserving (p.m.p.) transformations. However, it is not useful when there is no finite invariant measure. There are certain successful extensions of the notion of entropy to infinite measure spaces, or transformations with infinite invariant measures. The three main extensions are Parry, Krengel, and Poisson entropies. In this survey, we shortly overview the history of entropy, discuss the pioneering notions of Shannon and later contributions of Kolmogorov and Sinai, and discuss in somewhat more details the extensions to infinite systems. We compare and contrast these entropies with each other and with the entropy on finite systems.
0

27
33


Massoud
Amini
Department of Mathematics
Tarbiat Modares University
Tehran, Iran
Iran
mamini@modares.ac.ir
Infinite invariant measure
KolmogorovSinai entropy
Parry entropy
Krengel entropy
Poisson entropy
Pinsker factor
1

Solving a nonlinear inverse system of Burgers equations
https://ijnaa.semnan.ac.ir/article_4051.html
10.22075/ijnaa.2019.11008.1537
1
By applying finite difference formula to time discretization and the cubic Bsplines for spatial variable, a numerical method for solving the inverse system of Burgers equations is presented. Also, the convergence analysis and stability for this problem are investigated and the order of convergence is obtained. By using two test problems, the accuracy of presented method is verified. Additionally, obtained numerical results of the cubic Bspline method are compared to trigonometric cubic Bspline method, exponential cubic Bspline method and radial basis function method. Implementation simplicity and less computational cost are the main advantages of proposed scheme compared to previous proposals.
0

35
54


Hamed
Zeidabadi
School of Mathematics and Computer Science, Damghan University, P.O.Box 36715364, Damghan, Iran.
Iran
h.zeidabadi@std.du.ac.ir


Reza
Pourgholi
School of Mathematics and Computer Science, Damghan University, P.O.Box 36715364, Damghan, Iran.
Iran
pourgholi@du.ac.ir


Seyyed Hashem
Tabasi
School of mathematics and computer sienceses, Damghan University, Semnan, Iran.
Iran
tabasi@du.ac.ir
System of Burgers equations
Cubic Bspline
Collocation method
Inverse problems
Convergence analysis
Stability analysis
Tikhonov regularization method
Illposed problems
Noisy data
1

Completely Continuous Banach Algebras
https://ijnaa.semnan.ac.ir/article_4052.html
10.22075/ijnaa.2019.1184.1268
1
For a Banach algebra $mathfrak{A}$, we introduce ~$c.c(mathfrak{A})$, the set of all $phiin mathfrak{A}^*$ such that $theta_phi:mathfrak{A}to mathfrak{A}^*$ is a completely continuous operator, where $theta_phi$ is defined by $theta_phi(a)=acdotphi$ for all $ain mathfrak{A}$. We call $mathfrak{A}$, a completely continuous Banach algebra if $c.c(mathfrak{A})=mathfrak{A}^*$. We give some examples of completely continuous Banach algebras and a sufficient condition for an open problem raised for the first time by J.E Gale, T.J. Ransford and M. C. White: Is there exist an infinitedimensional amenable Banach algebra whose underlying Banach space is reflexive? We prove that a reflexive, amenable, completely continuous Banach algebra with the approximation property is trivial.
0

55
62


Bahman
Hayati
Faculty of Mathematical Sciences, Malayer University, P. O. Box 1684613114, Malayer, Iran
Iran
hayati@malayeru.ac.ir
Amenability
Completely continuous
Banach algebra
1

Solvability of infinite system of nonlinear singular integral equations in the $C(Itimes I, c)$ space and modified semianalytic method to find a closedform of solution
https://ijnaa.semnan.ac.ir/article_4053.html
10.22075/ijnaa.2019.16525.1875
1
In this article, we discuss about solvability of infinite systems of singular integral equations with two variables in the Banach sequence space $C(I times I, c)$ by applying measure of noncompactness and MeirKeeler condensing operators. By presenting an example, we have illustrated our results. For validity of the results we introduce a modified semianalytic method in the case of two variables to make an iteration algorithm to find a closedform of solution for the above problem. The numerical results show that the produced sequence for approximating the solution of example is in the $c$ space with a high accuracy.
0

63
76


Anupam
Das
Department of Mathematics, Rajiv Gandhi University, Rono Hills, Doimukh791112, Arunachal Pradesh, India
India
anupam.das@di.ku.dk


Mohsen
Rabbani
Department of Mathematics, Sari Branch, Islamic Azad University, Sari, Iran
Iran
mrabbani@iausari.ac.ir


Bipan
Hazarika
Department of Mathematics, Rajiv Gandhi University, Rono Hills, Doimukh791112, Arunachal Pradesh, India
India
bh_rgu@yahoo.co.in


Reza
Arab
Department of Mathematics, Sari Branch, Islamic Azad University, Sari, Iran
Iran
mathreza.arab@gmail.com
Measure of noncompactness
Infinite systems of singular integral equations
MeirKeeler condensing operators
Fixed point theorem
Modified homotopy perturbation
1

Coupled fixed point theorems for rational type contractions via Cclass functions
https://ijnaa.semnan.ac.ir/article_4054.html
10.22075/ijnaa.2018.11820.1591
1
In this paper, by using Cclass functions, we will present a coupled fixed problem in bmetric space for the singlevalued operators satisfying a generalized contraction condition. The first part of the paper is related to some fixed point theorems, the second part presents the uniqueness and existence of the solution of the coupled fixed point problem and in the third part, we discuss data dependence, wellposedness, UlamHyers stability and limit shadowing property of the coupled fixed point set.
0

77
98


Arslan
Hojat Ansari
Department of Mathematics, Karaj Branch, Islamic Azad University, Karaj, Iran
Iran
analsisamirmath2@gmail.com


Bahman
Moeini
Department of Mathematics, Hidaj Branch, Islamic Azad University, Hidaj, Iran
Iran
moeini145523@gmail.com


Isa
Yildirim
Department of Mathematics, Faculty of Science, Ataturk University, 25240 Erzurum,
Turkey
Turkey
isayildirim@atauni.edu.tr


Anca
Maria Oprea
Babe sBolyai University, Faculty of Mathematics and Computer Sciences, 400084 ClujNapoca, Romania
Romania
anca.oprea@math.ubbcluj.ro
Fixed point
ordered metric space
rational type contraction
Coupled fixed point
data dependence
wellposedness
UlamHyers stability
limit shadowing property
1

Nash Equilibrium Strategy for Bimatrix Games with LR Fuzzy Payoffs
https://ijnaa.semnan.ac.ir/article_4055.html
10.22075/ijnaa.2018.13073.1674
1
In this paper, bimatrix games are investigated based on LR fuzzy variables. Also, based on the fuzzy max order several models in nonsymmetrical LR fuzzy environment is constructed and the existence condition of Nash equilibrium strategies of the fuzzy bimatrix games is proposed. At last, based on the Nash equilibrium of crisp parametric bimatrix games, we obtain the Pareto and weak Pareto Nash equilibrium strategies of the fuzzy bimatrix games.
0

99
109


Fatemeh
Madandar
Department of Mathematics, Karaj Branch, Islamic Azad University, Karaj, Iran
Iran
fatemeh.madandar@kiau.ac.ir


Somayeh
Haghayeghi
Department of Mathematics, Karaj Branch, Islamic Azad University, Karaj, Iran
Iran
s.haghayeghi@kiau.ac.ir


S.Mansour
Vaezpour
Department of Mathematics and Computer Sciences, Amirkabir University of Technology, Tehran, Iran
Iran
vaez@aut.ac.ir
Bimatrix game
Nash equilibrium
LR fuzzy variable
1

Fixed point theorems for new Jtype mappings in modular spaces
https://ijnaa.semnan.ac.ir/article_4056.html
10.22075/ijnaa.2019.1816.1475
1
In this paper, we introduce $rho$altering $J$type mappings in modular spaces. We prove some fixed point theorems for $rho$altering and $rho$altering $J$type mappings in modular spaces. We also furnish illustrative examples to express relationship between these mappings. As a consequence, the results are applied to the existence of solution of an integral equation arising from an ODE system.
0

111
118


Esmaiel
Feizi
Mathematics Department, BuAli Sina University, P.O. Box 651744161, Hamadan, Iran
Iran
efeizi1@gmail.com


Zahra
Hossseini
Mathematics Department, BuAli Sina University, P.O. Box 651744161, Hamadan, Iran
Iran
z.hoseini@basu.ac.ir
Modular space
$rho$Altering mapping
$rho$Asymptotically regular mapping
$rho$$J$type mapping
$rho$altering $J$type mapping
Integral equation
1

Periodic Wave Shock solutions of Burgers equations
https://ijnaa.semnan.ac.ir/article_4057.html
10.22075/ijnaa.2018.10791.1524
1
In this paper we investigate the exact peroidic wave shock solutions of the Burgers equations. Our purpose is to describe the asymptotic behavior of the solution in the cauchy problem for viscid equation with small parametr ε and to discuss in particular the case of periodic wave shock. We show that the solution of this problem approaches the shock type solution for the cauchy problem of the inviscid burgers equation. The results are formulated in classical mathematics and proved with infinitesimal techniques of non standard analysis.
0

119
129


Saida
Bendaas
Department of Mathematics, Faculty of Sciences, Ferhat Abbas University, Campus Elbez, Setif  19000, Algeria
Algeria
saida_bendaas@yahoo.fr


Noureddine
Alaa
Department of Mathematics, Faculty of Science and Technics, University of Marrakesh, Morocco
Morocco
n.alaa@uca.ac.ma
Non Standard Analysis
Boundary Problem
Viscid Burgers Equation
Inviscid Burgers Equation
Heat Equation. Peroidic wave shock
1

On soft ultrafilters
https://ijnaa.semnan.ac.ir/article_4058.html
10.22075/ijnaa.2017.12670.1645
1
In this paper, the concept of soft ultrafilters is introduced and some of the related structures such as soft StoneCech compactification, principal soft ultrafilters and basis for its topology are studied.
0

131
138


Alireza
Bagheri Salec
Department of Mathematics, Faculty of Basic Sciences, University of Qom, Qom, Iran
Iran
alireza_bagheri_salec@yahoo.com
StoneCech compactification
ultrafilter
soft set
1

Hermitian solutions to the system of operator equations $T_iX=U_i$
https://ijnaa.semnan.ac.ir/article_4059.html
10.22075/ijnaa.2017.1475.1378
1
In this article, we consider the system of operator equations $T_iX=U_i$ for $i=1,2,...,n$ and give necessary and sufficient conditions for the existence of common Hermitian solutions to this system of operator equations for arbitrary operators without the closedness condition. Also, we study the MoorePenrose inverse of a $ntimes 1$ block operator matrix and then give the general form of common Hermitian solutions to this system of equations. Consequently, we give the necessary and sufficient conditions for the existence of common Hermitian solutions to the system of an operator equation and also present the necessary conditions for the solvability of the equation $sum_{i=1}{n}T_iX_i=U$.
0

139
152


S.Mansour
Vaezpour
Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran
Iran
vaez@aut.ac.ir


Zahra
Bakhtiari
Department of Mathematics, Payame Nour University, Tehran, Iran
Iran
za_bakhtiari@yahoo.com
Operator equation
Hermitian solution
Common solution
Existence of solution
Moore penrose inverse
1

Adaptive fuzzy sliding mode and indirect radialbasisfunction neural network controller for trajectory tracking control of a carlike robot
https://ijnaa.semnan.ac.ir/article_4060.html
10.22075/ijnaa.2019.4060
1
The evergrowing use of various vehicles for transportation, on the one hand, and the statistics of soaring road accidents resulting from human error, on the other hand, reminds us of the necessity to conduct more extensive research on the design, manufacturing and control of driverless intelligent vehicles. For the automatic control of an autonomous vehicle, we need its dynamic model, which, due to the existing uncertainties, the unmodeled dynamics and the performed simplifications, is impossible to determine exactly. Add to this, the external disturbances that exist on the movement path. In this paper, two adaptive controllers have been proposed for tracking the trajectory of a carlike robot. The first controller includes an indirect radialbasisfunction neural network whose parameters are updated online via gradient descent. The second controller is adaptively updated online by means of fuzzy logic. The proposed controller includes a nonlinear robust section that uses the sliding mode method and a fuzzy logic section that updates some of the nonlinear control parameters online. The fuzzy logic system has been designed to deal with the chattering problem in the controller of a carlike robot. In both controllers, the parameters have been determined by means of genetic algorithm. The obtained results indicate that even with the consideration of unideal effects such as uncertainties and external disturbances, the proposed controller has been able to perform successfully.
0

153
166


Masoud
Shirzadeh
Dept. of Electrical Engineering,
Amirkabir University of Technology,
Tehran 158754413, Iran
Iran
masoud_shirzad@aut.ac.ir


Abdollah
Amirkhani
Dept. of Automotive Engineering,
Iran University of Science and Technology,
Tehran 1684613114, Iran
Iran
amirkhani@iust.ac.ir


Mohammad H.
Shojaeefard
Department of Automotive Engineering, Iran University of Science and Technology, Tehran 1684613114, Iran
Iran


Hamid
Behroozi
Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran
Iran
dynamic model
trajectory tracking
carlike robot
sliding mode
fuzzy logic system
1

Home appliances energy management based on the IoT system
https://ijnaa.semnan.ac.ir/article_4061.html
10.22075/ijnaa.2019.4061
1
The idea of the Internet of Things (IoT) has turned out to be increasingly prominent in the cutting edge period of innovation than at any other time. From little family unit gadgets to extensive modern machines, the vision of IoT has made it conceivable to interface the gadgets with the physical world around them. This expanding prominence has likewise made the IoT gadgets and applications in the focal point of consideration among aggressors. Officially, a few sorts of pernicious exercises exist that endeavor to bargain the security and protection of the IoT gadgets. One fascinating rising risk vector is the assaults that misuse the utilization of sensors on IoT gadgets. IoT gadgets are powerless against sensorbased dangers because of the absence of legitimate security estimations accessible to control the utilization of sensors by applications. By abusing the sensors (e.g., accelerometer, gyrator, mouthpiece, light sensor, and so on) on an IoT gadget, assailants can separate data from the gadget, exchange malware to a gadget, or trigger a pernicious movement to bargain the gadget. In this review, we investigate different dangers focusing on IoT gadgets and talk about how their sensors can be mishandled for malignant purposes. Specifically, we present an itemized study about existing sensorbased dangers to IoT gadgets and countermeasures that are grown specifically to verify the sensors of IoT gadgets. Besides, we talk about the security and protection issues of IoT gadgets with regards to sensorbased dangers and finish up with future research headings.
0

167
175


Heliasadat
Hosseinian
Faculty of Mechanics, Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
Iran
helia.hosseinian@aut.ac.ir


Hamidreza
Damghani
Faculty of Mechanics, Electrical and Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
Iran
hamidreza.damghani@gmail.com


Leila
Damghani
Faculty of Computer Engineering Artificial intelligence, Kharazmi University, Tehran, Iran
Iran


Golnoosh
Nezam
Faculty of architecture engineering, West Tehran Branch, Islamic Azad University, Tehran, Iran
Iran
golnooshnezam@gmail.com


Hediyehsadat
Hosseinian
Faculty of architecture engineering, South Tehran Branch, Islamic Azad University, Tehran, Iran
Iran
hediyehsadat.hosseinian@gmail.com
Energy management
Internet of Things (IoT)
Intelligent Systems
Smart home
Home Appliances
Energy consumption
1

A new SDNbased framework for wireless local area networks
https://ijnaa.semnan.ac.ir/article_4062.html
10.22075/ijnaa.2019.4062
1
Nowadays wireless networks are becoming important in personal and public communication and growing very rapidly. Similarly, Software Defined Network (SDN) is an emerging approach to overcome challenges of traditional networks. In this paper, a new SDNbased framework is proposed to finegrained control of 802.11 Wireless LANs. This work describes the benefits of programmable Access Points. The proposed framework is evaluated on a prototype. We show that this architecture allows us to react to application needs, adjust network configuration for a priority application, detect network problems, and improve the user experience of the network. Our architecture relies on the IEEE 802.11 standard, and exploits it to collect information from the stations.
0

177
183


Ahmad
Jalili
Faculty of Computer Engineering, Gonbad Kavous University, Gonbad Kavous, Iran
Iran
jalili@gonbad.ac.ir
Software Defined Networks
Wireless Networks
Control Plane
Wireless LANs
Data Plane
1

A Novel Approach for Detecting Relationships in Social Networks Using Cellular Automata Based Graph Coloring
https://ijnaa.semnan.ac.ir/article_4063.html
10.22075/ijnaa.2019.4063
1
All the social networks can be modeled as a graph, where each roles as vertex and each relation roles as an edge. The graph can be show as $G = [V;E]$, where $V$ is the set of vertices and $E$ is the set of edges. All social networks can be segmented to $K$ groups, where there are members in each group with same features. In each group each person knows other individuals and is in touch with them. In this study, the main goal is introducing a new approach for detecting these groups and minimizing the number of these groups using a cellular automat algorithm. There are two types of social networks, containing simulated social network and real social network. The results show that the introduced method has a great potential to significantly reduce the number of colors assigned and running time of the program.
0

185
192


M.
Kashani
Department of Electrical Engineering and Information Technology Iranian Research Organization for Science and
Technology (IROST), Tehran, Iran
Iran
m.kashani@irost.ir


S.V.
Shojaedini
Department of Electrical Engineering and Information Technology Iranian Research Organization for Science and
Technology (IROST), Tehran, Iran
Iran


S.
Gorgin
Department of Electrical Engineering and Information Technology Iranian Research Organization for Science and
Technology (IROST), Tehran, Iran
Iran
Social networks
Graph coloring
Cellular automata
1

Cystoscopy Image Classification Using Deep Convolutional Neural Networks
https://ijnaa.semnan.ac.ir/article_4064.html
10.22075/ijnaa.2019.4064
1
In the past three decades, the use of smart methods in medical diagnostic systems has attracted the attention of many researchers. However, no smart activity has been provided in the field of medical image processing for diagnosis of bladder cancer through cystoscopy images despite the high prevalence in the world. In this paper, two wellknown convolutional neural networks (CNNs) and a multilayer neural network was applied to classify bladder cystoscopy images. One of the most important issues in training phase of neural networks is determining the learning rate because selecting too small or large learning rate leads to slow convergence, volatility and divergence, respectively. Therefore, an algorithm is required to dynamically change the convergence rate. In this respect, an adaptive method was presented for determining the learning rate so that the multilayer neural network could be improved. In this method, the learning rate is determined using a coefficient based on the difference between the accuracy of training and validation according to the output error. In addition, the rate of changes is updated according to the level of weight changes and output error. The proposed method was evaluated on 720 bladder cystoscopy images in four classes of blood in urine, benign and malignant masses. Based on the simulated results, the second proposed method (CNNs) achieved at least 17% decrease in error and increased the convergence speed of the proposed method in the classification of cystoscopy images, compared to the other competing methods.
0

193
215


Seyyed Mohammad Reza
Hashemi
Faculty of Computer Engineering and IT, Shahrood University of Technology, Shahrood, Iran
Iran
smr.hashemi@shahroodut.ac.ir


Hamid
Hassanpour
Faculty of Computer Engineering and IT, Shahrood University of Technology, Shahrood, Iran
Iran
h.hassanpour@shahroodut.ac.ir


Ehsan
Kozegar
University of Guilan, Guilan, Iran
Iran
kozegar@guilan.ac.ir


Tao
Tan
Eindhoven University of Technology, Eindhoven, The Netherlands
Netherlands
t.tan1@tue.nl
Cystoscopy Images
Medical Image Classication
MLP Neural Network
Adaptive Learning Rate
CNNs
1

Realtime Prediction and Synchronization of Business Process Instances using Data and Control Perspective
https://ijnaa.semnan.ac.ir/article_4065.html
10.22075/ijnaa.2019.4065
1
Nowadays, in a competitive and dynamic environment of businesses, organizations need to monitor, analyze and improve business processes with the use of Business Process Management Systems (BPMSs). Management, prediction and time control of events in BPMS is one of the major challenges of this area of research that has attracted lots of researchers. In this paper, we present a 4phase pipeline approach to the problem of synchronizing each pair of dependent process instances to arrive at the corresponding pair of tasks simultaneous or nearsimultaneous. In the first phase, the process model is mined from the event log and enriched by the probabilistic distributions of time information. In the second phase, the hidden processing dependency between the each pair of dependent process instances is formally defined and is mined from the event log. In the third phase, a process state prediction algorithm is presented to predict the future route of process instance and then predict the remaining time of the process instance to a given point in a predicted route of the business process. In the fourth phase, an iterative synchronization algorithm is presented based on the presented process state prediction algorithm to make each pair of dependent process instances arrive at the corresponding pair of tasks simultaneous or nearsimultaneous. Experimental results on a reallife event log of BPI challenge 2012 show that the proposed method leads to 39% reduction in cycle time for dependent process instances.
0

217
228


Iman
Firouzian
Faculty of Computer and IT,
Shahrood University of Technology, Shahrood, Iran
Iran
iman.firouzian@gmail.com


Morteza
Zahedi
Faculty of Computer and IT,
Shahrood University of Technology, Shahrood, Iran
Iran


Hamid
Hassanpour
Faculty of Computer Engineering and IT, Shahrood University of Technology, Shahrood, Iran
Iran
h.hassanpour@shahroodut.ac.ir
Business Process
Synchronization
Cycle Time Prediction
Dependent Process Instances
1

Natural scene text localization using edge color signature
https://ijnaa.semnan.ac.ir/article_4066.html
10.22075/ijnaa.2019.4066
1
Localizing text regions in images taken from natural scenes is one of the challenging problems due to variations in font, size, color and orientation of text. In this paper, we introduce a new concept so called Edge Color Signature for localizing text regions in an image. This method is able to localize both Farsi and English texts. In the proposed method first a pyramid using different scales of the input image is created. Then for each level of the pyramid an edge map is extracted. Afterwards, several geometric features are employed to filter out the nontext edges from the extracted edges. At this stage we describe an edge using colors of its neighboring pixels. We use the meanShift algorithm to obtain the color modes surrounding each edge pixel. Subsequently, the connected edge pixels with similar color signatures are clustered using SingleLinkage clustering algorithm to construct meaningful groups. Finally, each of the clusters is labeled as text or nontext using an MLP based cascade classifier. The proposed method has been evaluated on wellknown ICDAR 2013 and our Farsi dataset, the result is very promising.
0

229
237


Jalil
Ghavidel
Faculty of Computer Engineering, Shahrood University of Technology, Shahrood, Iran
Iran
jalil_ghavidel@shahroodut.ac.ir


Alireza
Ahmadyfard
Faculty of Electrical and Robotic Engineering, Shahrood University of Technology, Shahrood, Iran
Iran
ahmadyfard@shahroodut.ac.ir


Morteza
Zahedi
Faculty of Computer Engineering, Shahrood University of Technology, Shahrood, Iran
Iran
Text localization
Natural scene images
Edge color signature
Clustering
Farsi language