Feature Selection Using a Neuro-Genetic Approach for Arabic Text Recognition

In: Science

Submitted By marwaamara
Words 945
Pages 4
Feature Selection Using a Neuro-Genetic Approach For Arabic Text Recognition
M. Amara1 and K. Zidi2
Laboratoire de recherche Stratégies d’Optimisation et Informatique intelligentE SOIE ISG Tunis, 41, Rue de la Liberté, Cité Bouchoucha 2000 Le Bardo, Tunis -TUNISIE 1. amara1marwa@gmail.com Université de Gafsa, Tunisie 2. kamel_zidi@yahoo.fr

Keywords : Feature selection, Genetic algorithm, PML, AOCR.

1

Introduction

There are a wide variety of measurable characteristics in images. And we usually think that each feature is important to distinguish one form from another. Researchers in this domain confirmed that the number of primitives increases; the performance of a recognition system becomes poor and the computation time increases [1]. Consequently, a feature selection process is needed to resolve such a problem. Researchers categorized feature selection methods into three groups; heuristic methods, complete methods and random methods. Random method of research is rather new in its use of methods for selecting primitive compared to the other two categories heuristic and complete. Genetic algorithms (GA) are recently received considerable attention regarding their potential as an optimization technique based on the mechanism of natural selection. The features selection using GA has been used in various research areas such as camera calibration [2], verification of signatures [3], medical diagnosis [4], face recognition [5] and recognizing numbers [1]. We intend here to develop an Arabic optical character recognition system based on the optimization of the selected primitives. Since no Arabic OCR, has treated the problem of selection primitives. The perceptron multilayers (PML) are the networks most used by developers. Satisfactory results have been highlighted in various application areas. The most important characteristic of PML is their ability to learn.…...

Similar Documents

Human Face Detection and Recognition Using Web-Cam

...Human Face Detection and Recognition using Web-Cam Petcharat Pattanasethanon and Charuay Savithi Depatment of Business Computer, Faculty of Accountancy and Management, Mahasarakham UniversityKamreang, Kantharawichai, Mahasarakham 44150, Thailand Abstract: Problem statement: The illuminance insensitivity that reflects the angle of human facial aspects occurs once the distance between the object and the camera is too different such as animated images. This has been a problem for facial recognition system for decades. Approach: For this reason, our study represents a novel technique for facial recognition through the implementation of Successes Mean Quantization Transform and Spare Network of Winnow with the assistance of Eigenface computation. After having limited the frame of the input image or images from Web-Cam, the image is cropped into an oval or eclipse shape. Then the image is transformed into greyscale color and is normalized in order to reduce color complexities. We also focus on the special characteristics of human facial aspects such as nostril areas and oral areas. After every essential aspectsarescrutinized, the input image goes through the recognition system for facial identification. In some cases where the input image from the Web-Cam does not exist in the database, the user will be notified for the error handled. However, in cases where the image exists in the database, that image will be computed for similarity measurement using Euclidean......

Words: 1996 - Pages: 8

Narrative Texts

...H. Mohamed and Majzoub R. Omer Texts Texture and Culture: Cohesion as a Marker of Rhetorical Organisation in Arabic and English Narrative Published by: http://www.sagepublications.com Additional services and information for RELC Journal can be found at: Email Alerts: http://rel.sagepub.com/cgi/alerts Subscriptions: http://rel.sagepub.com/subscriptions Reprints: http://www.sagepub.com/journalsReprints.nav Permissions: http://www.sagepub.com/journalsPermissions.nav Citations: http://rel.sagepub.com/content/31/2/45.refs.html Downloaded from rel.sagepub.com at SIMON FRASER LIBRARY on March 28, 2011 45 TEXTURE AND CULTURE: COHESION AS A MARKER OF RHETORICAL ORGANISATION IN ARABIC AND ENGLISH NARRATIVE TEXTS AYISHA H. MOHAMED Police Training College in Abu Dhabi and MAJZOUB R. OMER College of Girls’ Education in Tabuk Abstract This paper claims that the differences at the cultural level between the Arabic-speaking and the English-speaking communities have a direct effect on the rhetorical organisation of Arabic and English texts as evident in the different ways in which cohesive devices are used. It is suggested that the two speech communities differ along the following cultural dimensions: oralised v. literate, collectivism v. individualism, high-contact v. low-contact, and reader-responsible v. writer-responsible. In order to test the influence of these cultural differences on the use of cohesive devices on written texts produced in the two......

Words: 10090 - Pages: 41

R&D Project Selection Using the Ahp

...ENGINEERING MANAGEMENT, VOL. 49, NO. 1, FEBRUARY 2002 59 R&D Project Selection Using the Analytic Network Process Laura M. Meade and Adrien Presley Abstract—The analytic network process (ANP) is presented as a potentially valuable method to support the selection of projects in a research and development (R&D) environment. This paper first discusses the requirements of the R&D project selection problem, which requires the allocation of resources to a set of competing and often disparate project proposals. Among the factors complicating this task is the need to make the decision within the framework of an enterprise’s strategic objectives and organizational structure while considering and integrating financial and strategic benefits of each project. The paper discusses the use of the ANP, a general form of Saaty’s analytic hierarchy process, as a model to evaluate the value of competing R&D project proposals. A generic ANP model developed by the authors, which includes in its decision levels the actors involved in the decision, the stages of research, categories of metrics, and individual metrics, is presented. The paper concludes with a case study describing the implementation of this model at a small high-tech company, including data based on the actual use of the decision making model. Index Terms—Analytic hierarchy process, analytic network process, multicriteria decision making, project selection, R&D management, R&D projects. I. INTRODUCTION OR MANY firms,......

Words: 6750 - Pages: 27

Genetic Algorithm

...Classification Using Genetic Algorithm N. Suguna1, and Dr. K. Thanushkodi2 1 Professor in Computer Science and Engg, Akshaya College of Engineering and Technology, Coimbatore, Tamil Nadu, India. 2 Director, Akshaya College of Engineering and Technology, Coimbatore, Tamil Nadu, India.   Abstract k-Nearest Neighbor (KNN) is one of the most popular algorithms for pattern recognition. Many researchers have found that the KNN algorithm accomplishes very good performance in their experiments on different data sets. The traditional KNN text classification algorithm has three limitations: (i) calculation complexity due to the usage of all the training samples for classification, (ii) the performance is solely dependent on the training set, and (iii) there is no weight difference between samples. To overcome these limitations, an improved version of KNN is proposed in this paper. Genetic Algorithm (GA) is combined with KNN to improve its classification performance. Instead of considering all the training samples and taking k-neighbors, the GA is employed to take k-neighbors straightaway and then calculate the distance to classify the test samples. Before classification, initially the reduced feature set is received from a novel method based on Rough set theory hybrid with Bee Colony Optimization (BCO) as we have discussed in our earlier work. The performance is compared with the traditional KNN, CART and SVM classifiers. Keywords: k-Nearest Neighbor, Genetic Algorithm,......

Words: 3528 - Pages: 15

Text Compression Using Ambigrams

...Text Compression Using Ambigrams Arun Prasad R., Gowtham S., Iyshwarya G. ,Kaushik Veluru, Tamarai Selvi A., Vasudha J. Amrita School of Engineering, Coimbatore. {arun837, gowtham035, iysh16, kaushikveluru, tamarai1990, vasudha.1990}@gmail.com Abstract Networking field is looking forward for improved and efficient methods in channel utilization. For some text, data recovery becomes indispensable because of importance of data it holds. Therefore, a lossless decomposition algorithm which is independent of the nature and pattern of text is today’s top concern. Efficiency of algorithms used today varies greatly depending on the nature of text. Such algorithms need some characters to be frequently appearing in the text and randomness in the characters present distorts the consistency to a large extent. This paper brings in the idea of using an art form called ambigram to compress text with consistency in the efficiency of the compression. Keywords Ambigrams, lossless compression, steganography, stego key, embedded algorithms, encryption. 1. Introduction When so many algorithms are available for compressing text, they hamper the readability of the text once compressed. Compressing the text using ambigrams also reduces the text to nearly 50% of its size. When most of the other compressing techniques depend on the nature of the text to be compressed, this technique is independent of the type of the text and requires......

Words: 1801 - Pages: 8

Series of Revenue Recognition Research Cases Using the Codification

...2308/iace-50029 A Series of Revenue Recognition Research Cases Using the Codification R. Mark Alford, Teresa M. DiMattia, Nancy T. Hill, and Kevin T. Stevens ABSTRACT: This series of four short cases is designed to help students develop the skills to research the Financial Accounting Standards Board’s (FASB) Accounting Standards Codification and other authoritative literature. It also is designed to help improve students’ ability to analyze and critique the complex issues that often surround the accounting for revenue recognition. The case scenarios describe transactions in which students must decide whether, when, and how much revenue to recognize. The issues analyzed involve bill-and-hold, multiple-element arrangements, gross versus net revenue reporting, and sales incentives. The cases are also designed to improve teamwork and communication skills. The sequence of cases is intended for use in an intermediate accounting class that covers revenue recognition, or in a capstone class that emphasizes critical thinking and research skills. Keywords: revenue; recognition; codification; research. INTRODUCTION evenue recognition is one of the top causes for financial statement restatements (Whitehouse 2010). In addition, revenue recognition is an area commonly questioned by the Securities and Exchange Commission (SEC) staff in their review of public filings and resultant comment letter process (Deloitte 2009). Furthermore, revenue recognition is often prey to financial fraud......

Words: 4631 - Pages: 19

Automatic Resume Recommender System Using Artificial Immune Systems Approach

...37 - 41 Automatic Resume Recommender system Using Artificial Immune Systems Approach Fatma Masooma Nigar Tel : +91-7398084314 Email: masoomanigar5@gmail.com Department of Computer Science,Jamia Hamdard University, Delhi, India Abstract: In today’s competitive world people across the globe post resumes over various sites of different organizations. Huge amount of documented resumes get stored. The HR manager needs the best among the stored documented resumes. The outcome of this research is a proposed architecture for classification,retreivel of the best selected resumes for the HR based on the ideas and principles of artificial immune system. Based on the research an attempt is made to automate the HR resume selection process by building an automated resume recommender system using the concepts of information extraction and artificial immune system. Keywords: Artificial immune system, information extraction, classification. 1. INTRODUCTION In today’s e-world, many of the applications are automated to ease the task carried out with accuracy. Many organizations across the globe are flooded with hundreds of resumes every month. The task of the HR manager is to create a job based on some criteria and filter out the best suitable resumes among the repository. Since the HR are having rich text of huge data, a computational tool shall help to ease down the task for......

Words: 1878 - Pages: 8

Arabic

...THINKING ARABIC TRANSLATION _______________________________ A Course in Translation Method: Arabic to English Supplement James Dickins Contents: Supplement Introduction 1 1 Preliminaries to translation as a process 3 1.3.1 3 Annotation: gist, exegesis and rephrasing Practical 1.3 Gist translation: ‫ﳑﺎ ﻫﻮ ﺟﺪﻳﺮ ﺑﺎﻟﺬﻛﺮ‬ 8 2 Preliminaries to translation as a product 9 2.1.1 2.1.5 2.2.2.1 2.2.2.2 Interlinear translation From interlinear to free translation Translation by omission Translation by addition 9 10 11 11 Practical 2.3 Literal vs. free translation: ‫ﻣﻌﻠﻘﺔ ﻟﺒﻴﺪ‬ 11 3 Cultural transposition 14 3.1 3.3 14 14 Basic principles Calque Practical 3.2 (extension) Cultural transposition: ‫وﻟﻴﺲ ﻫﻨﺎك إﺧﺼﺎﺋﻲ‬ Practical 3.3 Cultural transposition: ‫وﻗﺎدﺗﻪ ﺧﻄﻮاﺗﻪ‬ 15 15 4 Compensation 17 4.1 4.2 17 17 Basic principles Categories of compensation Practical 4.1 Compensation: ‫ﻗﺪ ﳝﺮ وﻗﺖ ﻃﻮﻳﻞ‬ 18 ii Contents: Supplement 5 Denotative meaning and translation issues 19 5.1 5.1.2 5.1.3 5.1.4 5.2 5.2.2 19 20 20 22 23 23 Denotative meaning Hyperonymy-hyponymy Particularizing translation and generalizing translation Partially overlapping translation Semantic repetition in Arabic List restructuring Practical 5.3 Semantic repetition, parallelism and list restructuring: ‫إن اﻟﺮﺳﻮل اﻟﻜﺮﱘ‬ 26 6 Connotative meaning and translation issues ...

Words: 30452 - Pages: 122

Neuro Marketing

...NEURO-MARKETING Project work Paper No. – CH 6.3 (b) UNDER THE SUPERVISION OF MS. VARTIKA KHANDELWAL DECLARATION BY STUDENT This is to certify that the material embodied in this study entitled “NEURO-MARKETING” is based on my own research work and my indebtedness to other work/publications has been acknowledged at the relevant places. This study has not been submitted elsewhere either wholly or in part for award of any degree. DIVANSHU SAXENA DECLARATION BY TEACHER INCHARGE This is to certify that the project titled “NEURO - MARKETING” done by DIVANSHU SAXENA is a part of his/her academic curriculum for the degree of B.Com (H). It has no commercial implication and is done only for academic purpose. Ms.Vartika Khandelwal Ms. Aruna Jha (Mentor) (Teacher in charge) ACKNOWLEDGEMENT I express my deep sense of gratitude to my mentor Ms. Vartika Khandelwal for encouraging me to take the literature review on the topic of Neuro-Marketing as a part of my Bachelor of Commerce’s curriculum for semester VI. I am very much thankful to her for valuable guidance, keen interest and encouragement at various stages of my literature review work. I would further like to thank my Marketing teacher Ms. Monika Bansal whose guidance and suggestion contributed immensely to the evolution of my ideas on the project. I would also like to thank my friends and family without whom the project would have been a distant reality. Divanshu......

Words: 4787 - Pages: 20

Ebusiness-Process-Personalization Using Neuro-Fuzzy Adaptive Control for Interactive Systems

...International Review of Business Research Papers Vol.2. No.4. December 2006, Pp. 39-50 eBusiness-Process-Personalization using Neuro-Fuzzy Adaptive Control for Interactive Systems Zunaira Munir1 , Nie Gui Hua2 , Adeel Talib3 and Mudassir Ilyas4 ‘Personalization’, which was earlier recognized as the 5th ‘P’ of e-marketing , is now becoming a strategic success factor in the present customer-centric e-business environment. This paper proposes two changes in the current structure of personalization efforts in ebusinesses. Firstly, a move towards business-process personalization instead of only website-content personalization and secondly use of an interactive adaptive scheme instead of the commonly employed algorithmic filtering approaches. These can be achieved by applying a neuro-intelligence model to web based real time interactive systems and by integrating it with converging internal and external e-business processes. This paper presents a framework, showing how it is possible to personalize e-business processes by adapting the interactive system to customer preferences. The proposed model applies Neuro-Fuzzy Adaptive Control for Interactive Systems (NFACIS) model to converging business processes to get the desired results. Field of Research: Marketing, e-business 1. Introduction: As Kasanoff (2001) mentioned, the ability to treat different people differently is the most fundamental form of human intelligence. "You talk differently to your boss than......

Words: 4114 - Pages: 17

Neuro Marketing

...appeal, using the insights into sales results and the management of repeated orders. But what is Neuro-Marketing? To understand this, we shall look at the following research, which in a way formed the framework for Neuro-Marketing concepts and Techniques. Montague carried out an interesting research based on the fact that the Pepsi and Coca-Cola drinks have an almost identical chemical composition. They examined the influence of perception on the preferences of consumers with regard to aforementioned products. They ran a few tests. We find two of them particularly interesting. During the first testing, the respondents drank Coca-Cola and Pepsi not knowing which beverage they drank (the so- called "blind test"), whereas on another occasion they drank form the brand-marked glasses. The researchers found out that the results differed a lot. In the first test the respondents equally favoured Pepsi and Coca-Cola; however, when they knew which drink they had, the domination of Coca-Cola was significant. Furthermore, the researchers established that the brain activity was higher when drinking the "marked" Coca-Cola than when drinking "marked" Pepsi. This research, as well as many other studies, clearly showed the influence of emotions, motives, perception – in short, the inner consumers' world on their purchase decisions and opinions on the quality of a product/brand. And from here coined the term Neuro-marketing. Neuro-marketing can be defined as a marketing branch using......

Words: 3438 - Pages: 14

Using Pertinent Information from the Case Text

...1. Using pertinent information from the case text, prepare a capital budgeting analysis of the wind turbine project using the payback and net present value or internal rate of return models. a. 2. Identify and evaluate the environmental advantages of the wind turbine project. b. Wind energy is friendly to the surrounding environment, as no fossil fuels are burnt to generate electricity from wind energy. c. Wind turbines take up less space than the average power station. Windmills only have to occupy a few square meters for the base, this allows the land around the turbine to be used for many purposes, for example agriculture. d. Newer technologies are making the extraction of wind energy much more efficient. The wind is free, and we are able to cash in on this free source of energy. e. Wind turbines are a great resource to generate energy in remote locations, such as mountain communities and remote countryside. Wind turbines can be a range of different sizes in order to support varying population levels. f. Another advantage of wind energy is that when combined with solar electricity, this energy source is great for developed and developing countries to provide a steady, reliable supply of electricity. g. 3. Identify and evaluate the environmental disadvantages of the wind turbine project. h. The strength of the wind is not constant and it varies from zero to storm force. This means that wind turbines do not...

Words: 1112 - Pages: 5

Implementing Portfolio Selection by Using Data Mining

...The Chinese University of Hong Kong Department of Computer Science and Engineering Final Year Project Trading Strategy and Portfolio Management (LWC 1301) Implementing Portfolio Selection By Using Data mining Tseng Ling Chun (1155005610) Supervisor: Professor Chan Lai Wan Marker: Professor Xu Lei 1 Table of Contents Table of Contents………………………………………….…………………………………………………2 1. Introduction………………………………………….…………………………………………................4 1.1 Financial Portfolios.......................................................................................................4 1.2 Data Mining and Decision Trees………………………………………..................….4 1.3 Flow of Report……………………………………….....................................................….5 2. Classification and Regression Trees (CART) …………………………………..........……….6 2.1 Detailed description of CART……………………………………................................6 2.2 Tree Construction………………………………………..............................................….8 2.2.1 Application of Impurity Function in CART……………………...…...9 2.3 Splitting Rules…………........……………...………….………………………….......……11 3. Optimizing Size of Tree……………………………....………..................................................….12 3.1 Parameterization of Trees…………………………………...........................……….13 3.2 Cost – Complexity Function……………………………………....….........................14 3.3 V – Fold Cross – Validation……………………………………..........................…….15 4. Iterative Dichotomiser 3 (ID3)......

Words: 10967 - Pages: 44

Offiline Arabic Handwritten Character Recognizer Based on Feature Extraction and Support Vector Machine

...Offline handwritten Arabic character recognizer based on Feature extraction and Support vector machine Thahira banu, Assistant professor in MCA department Sankara College of Science and comerce, Coimbatore-35. thahirshanth@gmail.com. ABSTRACT: Since the problem of Arabic text recognition is a large and complex one, it makes sense to try a simple method to see what performance can be achieved. The characters are written by many people using a great variety of sizes, writing styles, instruments, and with a widely varying amount of care. Some of the characters or words are poorly formed and are hard to classify, even for a human. Of the 280 sample characters used for training, 280 have been used for test purposes. The captured image of a character is normalized and set to eight feature values as parameter values of a vector. Training has given for a character by SVM (Support Vector machine) algorithm. It attempts to work with a subset of the features in a character that a human would typically see for the identification of Arabic characters. 1. Introduction One of the most classical applications of the Artificial Neural Network is the Character Recognition System. Cost effective and less time consuming, businesses, post offices, banks, security systems, and even the field of robotics employ this system as the base of their operations. Handwriting recognition can be defined as the task of transforming text represented in the spatial......

Words: 1773 - Pages: 8

Rough Set Approach for Feature Reduction in Pattern Recognition Through Unsupervised Artificial Neural Network

...International Conference on Emerging Trends in Engineering and Technology Rough Set Approach for Feature Reduction in Pattern Recognition through Unsupervised Artificial Neural Network A. G. Kothari A.G. Keskar A.P. Gokhale Rucha Pranjali Lecturer Professor Professor Deshpande Deshmukh agkothari72@re B.Tech Student B.Tech Student diffmail.com Department of Electronics & Computer Science Engineering, VNIT, Nagpur Abstract The Rough Set approach can be applied in pattern recognition at three different stages: pre-processing stage, training stage and in the architecture. This paper proposes the application of the Rough-Neuro Hybrid Approach in the pre-processing stage of pattern recognition. In this project, a training algorithm has been first developed based on Kohonen network. This is used as a benchmark to compare the results of the pure neural approach with the RoughNeuro hybrid approach and to prove that the efficiency of the latter is higher. Structural and statistical features have been extracted from the images for the training process. The number of attributes is reduced by calculating reducts and core from the original attribute set, which results into reduction in convergence time. Also, the above removal in redundancy increases speed of the process reduces hardware complexity and thus enhances the overall efficiency of the pattern recognition algorithm Keywords: core, dimensionality reduction, feature extraction, rough sets, reducts, unsupervised ANN as any type......

Words: 2369 - Pages: 10

Intimate Lingerie | Download | VA - I (Love) 80s (2CD) (2013) {Sony Music}