A Dataset of Amazigh Printed Words Images
|
|
- August Carroll
- 7 years ago
- Views:
Transcription
1 A Dataset of Amazigh Printed Words Images N. AHARRANE 1, A. DAHMOUNI 2, K. EL MOUTAOUAKIL 3, K.SATORI 4 Abstarct. 1 Student PhD, University Sidi Mohammed Ben AbedAllah aharranenabil@gmail.com 2 Student PhD, University Sidi Mohammed Ben AbedAllah abdellatifdahmouni@gmail.com 3 PA, National school of applied sciences Al-Hoceima yassirkarimimane@gmail.com 4 PES, University Sidi Mohamed Ben AbedAllah khalidsatori@gmail.com In the absence of a public database for a wide-scale benchmarking of Amazigh Optical Character Recognition (OCR) systems, this paper aims to provide a new Amazigh Printed Word Images database (APWID). This database contains 1795 different Amazigh words rendered with an automated procedure using different Amazigh fonts, sizes and styles to generate word images with their ground truth xml files. The database can be used as a source of training and testing sets to evaluate Amazigh OCR systems and also in other applications such as text classification systems and Amazigh characters segmentation. 1. Introduction and motivations In recent years, the OCR remains one of the most popular research subjects due to its diverse applications such as indexing archives, documents analysis, robotics, address classification system, processing of bank check, etc. Therefore, much work has been achieved for many languages, an excellent and recent survey can be found in [Peng et al., 2013]. Recently, due to the introduction of new technologies in communication and after the official introduction of the Amazigh language s teaching in the Moroccan educational system in 2003, researchers have begun to give attention to the Amazigh language trying to provide OCR systems able to achieve better performance. Rachidi et al present an overview of some released works [Rachidi et al., 2014]. Unfortunately, there is no common public database that makes significant the comparison of the elaborated OCR systems.
2 N. AHARRANE, A. DAHMOUNI, K. EL MOUTAOUAKIL, K. SATORI This work has as objective to present a new Amazigh Printed Word Images database (APWID). This database will serve in our research and it is publicly available (see the link in section 3) for the scientific community to enable them to evaluate and compare their OCR systems. The variability present in the data of the APWID database allow a large-scale benchmarking of multifonts, multi-sizes and multi-styles recognition systems of Amazigh words The Amazigh language has existed since the earliest antiquity. It has an original writing system, Tifinagh, used and preserved to this day. In recent decades, all Amazigh groups have reclaimed this ancestral writing. Currently, the Amazigh language is spoken by about 30 million speakers in North Africa (from the oasis of Siwa in Egypt to Morocco passing through Libya, Tunisia, Algeria, Niger, Mali, Burkina Faso and Mauritania). In Morocco, where nearly 50% of people are amazigh, the Amazigh language is divided into three regional varieties with Tarifit in the North, Tamazight in Central Morocco and South-East and Tachelhit in South-West and the High [Ameur et al., 2004]. Figure 1 : Tifinagh characters adopted by the IRCAM. The official introduction of the Amazigh language s teaching in the Moroccan educational system in 2003 involves the selection of a standard common language to teach. This task was accomplished by Royal Institute of the Amazigh Culture (IRCAM) created in 2001 [Sadiqi, 2011]. Actually, the Tifinagh-IRCAM alphabet is based on 33 characters [IRCAM, 2003] as seen in Figure 1. In the Amazigh OCR field, the characters ⴳⴳand ⴳⴳdo not have Unicode codes, so we obtain them by a combination of characters ⴳ, ⴳ with the sign of labialization ⵯ that have Unicode codes. The IRCAM institute has produced a number of Unicode-encoded Tifinagh fonts which are available for free download for all platforms. This variety in fonts allows a large variability in the rendered word images. The rest of this paper is organized as follows: Section 2 delineates all Necessary steps (data collection, rendering procedure, images description) to build the APWID database. In section 3, we present the corresponding statistics of the database and information about storage and usefulness. Finally, we conclude the paper with Section The APWID database This section describes the generation procedure of the APWID database and its specifications.
3 2.1. Data collection A NEW AMAZIGH PRINTED WORD IMAGES DATABASE 3 The database contains 1795 Amazigh words created from decomposable and non-decomposable words. Decomposable words are those generated from Amazigh verbs while non-decomposable ones are formed by Amazigh proper names, days, months, animals, etc. The Amazigh words were extracted from some books such as a French-Amazigh-Arabic dictionary and a Media dictionary published by the IRCAM institute. The collected words were grouped in a text file containing one Amazigh word in each line Sources of variability The images of the APWID database were generated using the 16 different Amazigh fonts proposed by the IRCAM institute (Table 1). We use all these fonts to cover different complexity of shapes of Amazigh printed characters, going from simple fonts with no or few overlaps (Tifinaghe IRCAM STANDARD) to more complex fonts rich in overlaps (Tifinaghe Tazirit UNICODE). We used also different sizes for each font: 8, 9, 10, 11, 12, 14, 16, 18, 20 and 24 points. And for each font and size combination we used different styles: Plain, Bold, Italic and Bold-Italic combination. Table 1: Different Amazigh fonts proposed by IRCAM The used fonts, sizes and styles guaranty a wide variability of the image database.
4 N. AHARRANE, A. DAHMOUNI, K. EL MOUTAOUAKIL, K. SATORI 2.3. Rendering procedure The word images were generated automatically by rendering the word text in images using a java program, so, noise and artifacts present in scanned images are not present in the image database. For each word text, we used different combinations of fonts, sizes and styles and the word image was rendered with the text anti-aliasing filtering implemented in the java standard library by RenderingHints class. The algorithm presented in the Figure 2 describes the followed rendering procedure to generate the APWID database. Figure 2: Algorithm to generate the APWID database 2.4. Ground truth description A detailed description for each image word of the APWID is attached by an XML file reporting ground truth information about the word sequence of characters, as well as information about the image and the rendering settings. Figure 3 illustrates an image word and its attached XML file. Figure 3: Example of the ground truth XML file
5 A NEW AMAZIGH PRINTED WORD IMAGES DATABASE 5 This file is composed of 4 markups to provide all necessary information about the word image such as content, font, image specifications and the generation procedure: Content: this element provides the transcription of the Amazigh word, the number of pieces of Amazigh word (npaws), that are characters, and subelements for each Paw giving its correspondent utf-8 code and its appearance frequency in the word. Font: in this element, we have information about the font used (name, size and style) to generate the word image. Specs: this element indicates the encoding of image, its width and its height. Generation: in this element, we give some additional information about the rendering procedure. 3. Database statistics and utilization This section is devoted to present the APWID statistics and its corresponding information about storage and usefulness Statistics The APWID database contains 1795 words composed from characters and rendered in different combinations of 16 fonts, 10 sizes and 4 styles. Table 2 reports the APWID statistics. Table 2: The APWID statistics Number of words Number of characters fonts * 10 sizes * 4 styles Total As shown in Table 2 the APWID database is composed of word images files, each word image is described by a ground truth xml file. The database contains in total characters, their appearance frequencies in the database are distributed as seen in Table 3.
6 N. AHARRANE, A. DAHMOUNI, K. EL MOUTAOUAKIL, K. SATORI Table 3: Characters appearance frequencies in the APWID database 3.2. Storage The database takes about 900 Mo of disk space and is publicly available for free download via the following link: As shown in Figure 4, the database files are organized in 16 directories representing the 16 Amazigh fonts, each font directory contains 10 other ones for the 10 font sizes and each size directory contains 4 directories for the 4 different font styles. Figure 4: APWID Database structure in disk
7 3.3. Utilization A NEW AMAZIGH PRINTED WORD IMAGES DATABASE 7 The APWID database can be used as training/testing sets in many applications as OCR systems, text classification systems and characters segmentation algorithms. We proposed some protocols as summarized in Table 4 to test the impact of the variability of the data in the database on the tested systems. Table 4: Database testing protocols Protocol Training Set Train (font, size, style) Testing Set Test (font, size, style) APWID1 Train (F01, 14, P) Test (F01, 14, P) APWID2 Train ([F01,F03,F05,F06], [12,14], [P, I]) Test ([F02,F04,F08,F09], [12,14], [P,I]) APWID3 Train([F01,F02], [14,16], [P,I]) Test ([F01,F02], [14,16], [B,BI]) APWID4 Train ([F11-F15], [9,13,20], P) Test ([F11-F15], [9,13,20], P) APWID5 Train (All, All, All) Test (All, All, All) APWID6 Train ([F01, F05, F08, F09], [20,24], All) Test ([F01, F05, F08, F09], [20,24], All) These protocols use the notations Train (font, size, style) and Test (font, size, style) to define the training and testing conditions where: Font: the font ids as indicated in Table 1; Size : defines the sizes used in points ; Style: the style used where P, B, I and BI are for Plain, Bold, Italic and Bold & Italic. The defined protocols have well-defined objectives and are as follow: APTWID1: This is the basic one given that there are no mismatched between the training and testing sets conditions. The performance of the OCR systems should be the highest possible; APTWID2: This one is to test the ability of systems to recognize unseen fonts. APTWID3: This protocol aims to evaluate the capability of systems to treat unseen styles. APTWID4: in this protocol, we measure the systems capability to recognize unseen sizes;
8 N. AHARRANE, A. DAHMOUNI, K. EL MOUTAOUAKIL, K. SATORI APTWID5: This protocol is a global one where all data is used for experimentation; APTWID6: The last protocol is destined to the text classification systems to identify Amazigh text. The database can be used also to test different characters segmentation algorithms in overlapped fonts such as Tifinaghe-IRCAMtaromit2_unicode where the segmentation algorithm using the vertical projection histogram (Figure 5) cannot deal. Figure 5: Characters segmentation by histogram projection [ES Saady et al., 2011] The APWID database users are free to create their own combinations of training and testing sets according to their own needs by benefiting from the variability of the data. 4. Conclusion In this work, we have presented a new Amazigh Printed Word Images Database consisting of different word images and their attached ground truth XML files to provide a common database for a large-scale benchmarking of the OCR systems. The database can be used to create multiple combinations of training and testing sets while benefiting from the wide variability of the database data in term of fonts, sizes and styles. The APWID database is publicly available via Internet. Références Ameur M., Bouhjar A., Boukhris F., Boukouss A., Boumalk A., Elmedlaoui M., Iazzi E. and Souifi H. (2004): Initiation à la langue amazighe, Publications de l'institut Royal de la Culture Amazighe, Manuels N.1, pp. 9. Es Saady Y., Rachidi A., El Yassa M. and Mammass D. (2011): Amazigh Handwritten Character Recognition based on Horizontal and Vertical Centerline of Character, International Journal of Advanced Science and Technology, Vol. 33, pp
9 A NEW AMAZIGH PRINTED WORD IMAGES DATABASE 9 Institut Royal de la Culture Amazighe. (2003) : Proposition de codification des tifinaghes, Rabat, Morocco. Peng X., Cao H., Setlur S., Govindarju V. and Natarajan P. (2013): Multilingual OCR research and applications: An Overview, Proceedings of the 4th International Workshop on Multilingual OCR, ACM, New York, NY, USA. Article No.1. Rachidi A., Eddahibi M., Essaady Y. and Amrouch M. (2014): Amazigh Characters Automatic Recognition: Overview and Prospects, International Journal of Scientific & Engineering Research, Vol. 5, Issue 11, pp Sadiqi F. (2011): The Teaching of Tifinagh (Berber) in Morocco, Handbook of Language and Ethnic Identity: The Success-Failure Continuum in Language and Ethnic Identity Efforts, Vol. 2, Oxford University Press, pp:33-44.
Amazigh ConCorde: an appropriate concordance for Amazigh
SITACAM 09, Agadir, 12-13 December 2009 Amazigh ConCorde: an appropriate concordance for Amazigh Siham Boulaknadel Institut Royal de la Culture Amazighe Avenue Allal El Fassi, Madinat Al Irfane, Rabat
More informationHandwritten Character Recognition from Bank Cheque
International Journal of Computer Sciences and Engineering Open Access Research Paper Volume-4, Special Issue-1 E-ISSN: 2347-2693 Handwritten Character Recognition from Bank Cheque Siddhartha Banerjee*
More informationTibiscus University, Timişoara
PDF/A standard for long term archiving Ramona Vasilescu Tibiscus University, Timişoara ABSTRACT. PDF/A is defined by ISO 19005-1 as a file format based on PDF format. The standard provides a mechanism
More informationCourse Scheduling Support System
Course Scheduling Support System Roy Levow, Jawad Khan, and Sam Hsu Department of Computer Science and Engineering, Florida Atlantic University Boca Raton, FL 33431 {levow, jkhan, samh}@fau.edu Abstract
More informationSearch and Information Retrieval
Search and Information Retrieval Search on the Web 1 is a daily activity for many people throughout the world Search and communication are most popular uses of the computer Applications involving search
More informationAdaptation of Rapid Prototyping Model for Serious Games Development
Journal of Computer Science and Information Technology June 2014, Vol. 2, No. 2, pp. 173-183 ISSN: 2334-2366 (Print), 2334-2374 (Online) Copyright The Author(s). 2014. All Rights Reserved. Published by
More information2. Distributed Handwriting Recognition. Abstract. 1. Introduction
XPEN: An XML Based Format for Distributed Online Handwriting Recognition A.P.Lenaghan, R.R.Malyan, School of Computing and Information Systems, Kingston University, UK {a.lenaghan,r.malyan}@kingston.ac.uk
More informationThe Role of Size Normalization on the Recognition Rate of Handwritten Numerals
The Role of Size Normalization on the Recognition Rate of Handwritten Numerals Chun Lei He, Ping Zhang, Jianxiong Dong, Ching Y. Suen, Tien D. Bui Centre for Pattern Recognition and Machine Intelligence,
More informationImplementation of OCR Based on Template Matching and Integrating it in Android Application
International Journal of Computer Sciences and EngineeringOpen Access Technical Paper Volume-04, Issue-02 E-ISSN: 2347-2693 Implementation of OCR Based on Template Matching and Integrating it in Android
More informationCursive Handwriting Recognition for Document Archiving
International Digital Archives Project Cursive Handwriting Recognition for Document Archiving Trish Keaton Rod Goodman California Institute of Technology Motivation Numerous documents have been conserved
More informationTibetan For Windows - Software Development and Future Speculations. Marvin Moser, Tibetan for Windows & Lucent Technologies, USA
Tibetan For Windows - Software Development and Future Speculations Marvin Moser, Tibetan for Windows & Lucent Technologies, USA Introduction This paper presents the basic functions of the Tibetan for Windows
More informationHow To Segmentate In Ctv Video
Time and Date OCR in CCTV Video Ginés García-Mateos 1, Andrés García-Meroño 1, Cristina Vicente-Chicote 3, Alberto Ruiz 1, and Pedro E. López-de-Teruel 2 1 Dept. de Informática y Sistemas 2 Dept. de Ingeniería
More informationPageX: An Integrated Document Processing and Management Software for Digital Libraries
PageX: An Integrated Document Processing and Management Software for Digital Libraries Hanchuan Peng, Zheru Chi, Wanchi Siu, and David Dagan Feng Department of Electronic & Information Engineering The
More informationThe Unicode Standard Version 8.0 Core Specification
The Unicode Standard Version 8.0 Core Specification To learn about the latest version of the Unicode Standard, see http://www.unicode.org/versions/latest/. Many of the designations used by manufacturers
More informationDevelopment and Implementation of the OpenLR Map Interface for Shapefiles
Mohammed Alhessi Development and Implementation of the OpenLR Map Interface for Shapefiles Duration of the Thesis: 6 months Completion: May 2013 Tutor: Rainer Schützle, MSc Examiner: Prof. Dr.-Ing. Volker
More informationAutomatic License Plate Recognition using Python and OpenCV
Automatic License Plate Recognition using Python and OpenCV K.M. Sajjad Department of Computer Science and Engineering M.E.S. College of Engineering, Kuttippuram, Kerala me@sajjad.in Abstract Automatic
More informationAccuRead OCR. Administrator's Guide
AccuRead OCR Administrator's Guide July 2016 www.lexmark.com Contents 2 Contents Change history... 3 Overview... 4 System requirements...4 Supported applications... 4 Supported formats and languages...
More informationContents. Downloading the Data Files... 2. Centering Page Elements... 6
Creating a Web Page Using HTML Part 1: Creating the Basic Structure of the Web Site INFORMATION TECHNOLOGY SERVICES California State University, Los Angeles Version 2.0 Winter 2010 Contents Introduction...
More informationHow To Digitise Newspapers On A Computer At Nla.Com
Australian Newspapers Digitisation Program Development of the Newspapers Content Management System Rose Holley ANDP Manager ANPlan/ANDP Workshop, 28 November 2008 1 Requirements Manage, store and organise
More informationSIPAC. Signals and Data Identification, Processing, Analysis, and Classification
SIPAC Signals and Data Identification, Processing, Analysis, and Classification Framework for Mass Data Processing with Modules for Data Storage, Production and Configuration SIPAC key features SIPAC is
More informationIntroduction. 1. Name of your organisation: 2. Country (of your organisation): Page 2
Introduction 1. Name of your organisation: 2. Country (of your organisation): 6 Page 2 Policies and Procedures The following questions address the policies and procedures regarding data management (acquisition,
More informationSterling Web. Localization Guide. Release 9.0. March 2010
Sterling Web Localization Guide Release 9.0 March 2010 Copyright 2010 Sterling Commerce, Inc. All rights reserved. Additional copyright information is located on the Sterling Web Documentation Library:
More informationDetection and mitigation of Web Services Attacks using Markov Model
Detection and mitigation of Web Services Attacks using Markov Model Vivek Relan RELAN1@UMBC.EDU Bhushan Sonawane BHUSHAN1@UMBC.EDU Department of Computer Science and Engineering, University of Maryland,
More informationChapter 4: Computer Codes
Slide 1/30 Learning Objectives In this chapter you will learn about: Computer data Computer codes: representation of data in binary Most commonly used computer codes Collating sequence 36 Slide 2/30 Data
More informationSecure Semantic Web Service Using SAML
Secure Semantic Web Service Using SAML JOO-YOUNG LEE and KI-YOUNG MOON Information Security Department Electronics and Telecommunications Research Institute 161 Gajeong-dong, Yuseong-gu, Daejeon KOREA
More informationOptical Character Recognition. Joerg Schulenburg, LinuxTag 2005 GOCR
Optical Character Recognition GOCR, what can it do for you? converting images with printed text to text format making printed text accessible for text utils sources: scans, screenshots, photos?, pdf's,
More informationUnicode in Mobile Phones
Unicode in Mobile Phones Adil Allawi Technical Director adil@diwan.com Unicode in Mobile Phones Complex text in small devices Memory is very limited Processing speed is low yet time is critical Screen
More informationVisualizing Data: Scalable Interactivity
Visualizing Data: Scalable Interactivity The best data visualizations illustrate hidden information and structure contained in a data set. As access to large data sets has grown, so has the need for interactive
More informationEr is door mij gebruik gemaakt van dia s uit presentaties van o.a. Anastasios Kesidis, CIL, Athene Griekenland, en Asaf Tzadok, IBM Haifa Research Lab
IMPACT is supported by the European Community under the FP7 ICT Work Programme. The project is coordinated by the National Library of the Netherlands. Er is door mij gebruik gemaakt van dia s uit presentaties
More informationOntology and automatic code generation on modeling and simulation
Ontology and automatic code generation on modeling and simulation Youcef Gheraibia Computing Department University Md Messadia Souk Ahras, 41000, Algeria youcef.gheraibia@gmail.com Abdelhabib Bourouis
More informationBibliographic Standards
Bibliographic Standards The INFLIBNET Centre maintains this page as part of its commitment to collaboration with University, College, R & D and National institute libraries in the development, promotion
More informationHow To Filter Spam Image From A Picture By Color Or Color
Image Content-Based Email Spam Image Filtering Jianyi Wang and Kazuki Katagishi Abstract With the population of Internet around the world, email has become one of the main methods of communication among
More informationDigital media glossary
A Ad banner A graphic message or other media used as an advertisement. Ad impression An ad which is served to a user s browser. Ad impression ratio Click-throughs divided by ad impressions. B Banner A
More informationBook Builder Training Materials Using Book Builder September 2014
Book Builder Training Materials Using Book Builder September 2014 Prepared by WDI, Inc. Table of Contents Introduction --------------------------------------------------------------------------------------------------------------------
More informationDEVNAGARI DOCUMENT SEGMENTATION USING HISTOGRAM APPROACH
DEVNAGARI DOCUMENT SEGMENTATION USING HISTOGRAM APPROACH Vikas J Dongre 1 Vijay H Mankar 2 Department of Electronics & Telecommunication, Government Polytechnic, Nagpur, India 1 dongrevj@yahoo.co.in; 2
More informationThe Development of Multimedia-Multilingual Document Storage, Retrieval and Delivery System for E-Organization (STREDEO PROJECT)
The Development of Multimedia-Multilingual Storage, Retrieval and Delivery for E-Organization (STREDEO PROJECT) Asanee Kawtrakul, Kajornsak Julavittayanukool, Mukda Suktarachan, Patcharee Varasrai, Nathavit
More informationDAISY PRODUCER: AN INTEGRATED PRODUCTION MANAGEMENT SYSTEM FOR ACCESSIBLE MEDIA
42 DAISY2009 LEIPZIG Christian Egli DAISY PRODUCER: AN INTEGRATED PRODUCTION MANAGEMENT SYSTEM FOR ACCESSIBLE MEDIA Christian Egli Swiss Library for the Blind and Visually Impaired Zurich Grubenstrasse
More informationChapter 3. Application Software. Chapter 3 Objectives. Application Software
Chapter 3 Objectives Chapter 3 Application Software Identify the categories of application software Explain ways software is distributed Explain how to work with application software Identify the key features
More informationPreservation Handbook
Preservation Handbook Plain text Author Version 2 Date 17.08.05 Change History Martin Wynne and Stuart Yeates Written by MW 2004. Revised by SY May 2005. Revised by MW August 2005. Page 1 of 7 File: presplaintext_d2.doc
More informationPreserving the Spirit of the Epoch: Digital Conversion of Nordic Music Magazines Amalie Ørum Hansen Development Consultant Gentofte Centralbibliotek
Preserving the Spirit of the Epoch: Digital Conversion of Nordic Amalie Ørum Hansen Development Consultant Gentofte Centralbibliotek Sergey Borovoy CEO ATAPY Software Quick facts about Gentofte Central
More informationAdobe Acrobat 9 Pro Accessibility Guide: PDF Accessibility Overview
Adobe Acrobat 9 Pro Accessibility Guide: PDF Accessibility Overview Adobe, the Adobe logo, Acrobat, Acrobat Connect, the Adobe PDF logo, Creative Suite, LiveCycle, and Reader are either registered trademarks
More informationUsing CSI s Web Messaging Email System: Imail URL: mail.csi.cuny.edu
Using CSI s Web Messaging Email System: Imail URL: mail.csi.cuny.edu Preferences: General User Settings Full Name: The name in the box is the name that will appear in the recipients from field. Reply to:
More informationA Review of Anomaly Detection Techniques in Network Intrusion Detection System
A Review of Anomaly Detection Techniques in Network Intrusion Detection System Dr.D.V.S.S.Subrahmanyam Professor, Dept. of CSE, Sreyas Institute of Engineering & Technology, Hyderabad, India ABSTRACT:In
More informationDesigning forms for auto field detection in Adobe Acrobat
Adobe Acrobat 9 Technical White Paper Designing forms for auto field detection in Adobe Acrobat Create electronic forms more easily by using the right elements in your authoring program to take advantage
More informationPreservation Handbook
Preservation Handbook [Binary Text / Word Processor Documents] Author Rowan Wilson and Martin Wynne Version Draft V3 Date 22 / 08 / 05 Change History Revised by MW 22.8.05; 2.12.05; 7.3.06 Page 1 of 7
More informationCREATING EXCEL PIVOT TABLES AND PIVOT CHARTS FOR LIBRARY QUESTIONNAIRE RESULTS
CREATING EXCEL PIVOT TABLES AND PIVOT CHARTS FOR LIBRARY QUESTIONNAIRE RESULTS An Excel Pivot Table is an interactive table that summarizes large amounts of data. It allows the user to view and manipulate
More informationAutomated Medical Citation Records Creation for Web-Based On-Line Journals
Automated Medical Citation Records Creation for Web-Based On-Line Journals Daniel X. Le, Loc Q. Tran, Joseph Chow Jongwoo Kim, Susan E. Hauser, Chan W. Moon, George R. Thoma National Library of Medicine,
More informationTEXT-FILLED STACKED AREA GRAPHS Martin Kraus
Martin Kraus Text can add a significant amount of detail and value to an information visualization. In particular, it can integrate more of the data that a visualization is based on, and it can also integrate
More informationELECTRONIC LIBRARIES IN PARTNERSHIP: BEEP FOR AFRICA
ELECTRONIC LIBRARIES IN PARTNERSHIP: BEEP FOR AFRICA By Pier Luigi Rossi IRD (Research Institute for Development), Bendy, France rossi@ird.fr Introduction Between September 2008 and September 2009, IRD
More informationREQUEST FOR EXPRESSIONS OF INTEREST
REQUEST FOR EXPRESSIONS OF INTEREST AFRICAN DEVELOPMENT BANK Regional Department North (ORNA) African Development Bank E-mail: t.triki@afdb.org Telephone: +216 71103009 Fax: +216 71 194523 Expressions
More informationElfring Fonts, Inc. PCL MICR Fonts
Elfring Fonts, Inc. PCL MICR Fonts This package contains five MICR fonts (also known as E-13B), to print magnetic encoding on checks, and six Secure Number fonts, to print check amounts. These fonts come
More informationVISUALIZATION APPROACH FOR SOFTWARE PROJECTS
Canadian Journal of Pure and Applied Sciences Vol. 9, No. 2, pp. 3431-3439, June 2015 Online ISSN: 1920-3853; Print ISSN: 1715-9997 Available online at www.cjpas.net VISUALIZATION APPROACH FOR SOFTWARE
More informationUser Guide. Printing Unicode characters from SAP to SATO GT4xxe Printers. www.satoworldwide.com. Version 061030-02
Printing Unicode characters from SAP to SATO GT4xxe Printers User Guide Version 061030-02 2006 SATO Corporation. All rights reserved. Table of Contents 1. Introduction... 3 2. Configuration at SAP environment...
More informationText Steganography in SMS
2007 International Conference on Convergence Information Technology Text Steganography in SMS Mohammad Shirali-Shahreza Computer Science Department Sharif University of Technology Tehran, Iran shirali@cs.sharif.edu
More informationGUIDEBOOK FOR TECHNOLOGY COMPETENCIES BOSTON COLLEGE LYNCH SCHOOL OF EDUCATION
GUIDEBOOK FOR TECHNOLOGY COMPETENCIES BOSTON COLLEGE LYNCH SCHOOL OF EDUCATION Contents Summary of Required Technology Competencies....2 Guidelines for Demonstration of Technology Competencies...3 Available
More informationIntroduction to <emma>
1 Educause Southeast Regional Conference June 20, 2006 Christy Desmet, Director of First-year Composition Ron Balthazor, Developer University of Georgia Introduction
More informationScript and Language Identification for Handwritten Document Images. Judith Hochberg Kevin Bowers * Michael Cannon Patrick Kelly
Script and Language Identification for Handwritten Document Images Judith Hochberg Kevin Bowers * Michael Cannon Patrick Kelly Computer Research and Applications Group (CIC-3) Mail Stop B265 Los Alamos
More informationFigure 1 - BI Publisher Enterprise Capabilities. OAUG Forum @ Collaborate 08 Page 2 Copyright 2008 by Lee Briggs
Oracle BI Publisher was originally developed to solve these reporting problems. It was first released with Oracle E- Business Suite 11.5.10 towards the end of 2005. The original release was called XML
More informationithenticate User Manual
ithenticate User Manual Updated November 20, 2009 Contents Introduction 4 New Users 4 Logging In 4 Resetting Your Password 5 Changing Your Password or Username 6 The ithenticate Account Homepage 7 Main
More informationChapter 3. Application Software. Chapter 3 Objectives. Application Software. Application Software. Application Software. What is application software?
Chapter 3 Objectives Chapter 3 Application Software Identify the the categories of of application software Explain ways software is is distributed Explain how to to work with application software Identify
More informationThe Hybrid Oriental Library and the Content Management System
The Hybrid Oriental Library and the Content Management System " #"$" The recent RSLP funded projects for Oriental Libraries and digitization projects funded by the New Opportunities Fund have accelerated
More informationLow-resolution Character Recognition by Video-based Super-resolution
2009 10th International Conference on Document Analysis and Recognition Low-resolution Character Recognition by Video-based Super-resolution Ataru Ohkura 1, Daisuke Deguchi 1, Tomokazu Takahashi 2, Ichiro
More informationithenticate User Manual
ithenticate User Manual Version: 2.0.8 Updated February 4, 2014 Contents Introduction 4 New Users 4 Logging In 4 Resetting Your Password 5 Changing Your Password or Username 6 The ithenticate Account Homepage
More informationWeb Development. Owen Sacco. ICS2205/ICS2230 Web Intelligence
Web Development Owen Sacco ICS2205/ICS2230 Web Intelligence Introduction Client-Side scripting involves using programming technologies to build web pages and applications that are run on the client (i.e.
More informationSupervised DNA barcodes species classification: analysis, comparisons and results. Tutorial. Citations
Supervised DNA barcodes species classification: analysis, comparisons and results Emanuel Weitschek, Giulia Fiscon, and Giovanni Felici Citations If you use this procedure please cite: Weitschek E, Fiscon
More informationIntroduction to Machine Learning Lecture 1. Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu
Introduction to Machine Learning Lecture 1 Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Introduction Logistics Prerequisites: basics concepts needed in probability and statistics
More informationithenticate User Manual
ithenticate User Manual Version: 2.0.2 Updated March 16, 2012 Contents Introduction 4 New Users 4 Logging In 4 Resetting Your Password 5 Changing Your Password or Username 6 The ithenticate Account Homepage
More informationOCRopus Addons. Internship Report. Submitted to:
OCRopus Addons Internship Report Submitted to: Image Understanding and Pattern Recognition Lab German Research Center for Artificial Intelligence Kaiserslautern, Germany Submitted by: Ambrish Dantrey,
More informationTable Of Contents. iii
PASSOLO Handbook Table Of Contents General... 1 Content Overview... 1 Typographic Conventions... 2 First Steps... 3 First steps... 3 The Welcome dialog... 3 User login... 4 PASSOLO Projects... 5 Overview...
More informationOCR-Based Electronic Documentation Management System
OCR-Based Electronic Documentation Management System Khalaf S. Alkhalaf, Abdulelah I. Almishal, Anas O. Almahmoud, and Majed S. Alotaibi Abstract Optical character recognition (OCR) is one of the latest
More informationAccuRead OCR. Administrator's Guide
AccuRead OCR Administrator's Guide April 2015 www.lexmark.com Contents 2 Contents Overview...3 Supported applications...3 Supported formats and languages...3 OCR performance...4 Sample documents...6 Configuring
More informationUSING ELECTRONIC RESUMES IN THE JOB SEARCH By Dr. Lillian H. Chaney and Dr. Catherine G. Green
USING ELECTRONIC RESUMES IN THE JOB SEARCH By Dr. Lillian H. Chaney and Dr. Catherine G. Green The widespread use of technology has changed recruiting practices of many businesses. One change is the increased
More informationThe Archiving Method for Records of Public Sector s Facebook Page
The Archiving Method for Records of Public Sector s Facebook Page Yun-Young Hwang 1, In-Ho Jang 2 and Kyu-Chul Lee 2 1 Korean Institute of Science and Technology Information 2 Dept. Computer Engineering,
More informationEUROMED JUSTICE III PROJECT PROJET EUROMED JUSTICE III
/ Final Conference/Conférence finale 11 March 2015 / 11 Mars 2015 Barcelona (ES) EUROMED JUSTICE III PROJECT Final Conference 11 March 2015 Conférence finale 11 Mars 2015 1 Final Regional Conference/Conférence
More informationThe Languages of Africa LIN 4930/6932. SSA 4930. Spring 2012. T 7 T 7-8. WEIM 1084
The Languages of Africa LIN 4930/6932. SSA 4930. Spring 2012. T 7 T 7-8. WEIM 1084 Dr. Frank Seidel Hours: Tuesday, 3:00-3:50 Office: 496 Grinter Hall & by appointment Phone: 850-339-6337 e-mail: fseidel@ufl.edu
More informationencoding compression encryption
encoding compression encryption ASCII utf-8 utf-16 zip mpeg jpeg AES RSA diffie-hellman Expressing characters... ASCII and Unicode, conventions of how characters are expressed in bits. ASCII (7 bits) -
More informationExtend Table Lens for High-Dimensional Data Visualization and Classification Mining
Extend Table Lens for High-Dimensional Data Visualization and Classification Mining CPSC 533c, Information Visualization Course Project, Term 2 2003 Fengdong Du fdu@cs.ubc.ca University of British Columbia
More informationPerfion Output Using Special Barcode fonts
Perfion Output Using Special Barcode fonts 1 Using Barcodes... 2 1.1 Perfion Barcodes... 2 1.2 Perfion Barcodes: when using other Design tools... 2 1.3 Barcode fonts... 2 2 Using Barcode fonts... 3 2.1
More informationMultimodal Biometric Recognition Security System
Multimodal Biometric Recognition Security System Anju.M.I, G.Sheeba, G.Sivakami, Monica.J, Savithri.M Department of ECE, New Prince Shri Bhavani College of Engg. & Tech., Chennai, India ABSTRACT: Security
More informationNetwork Scanner Tool R3.1. User s Guide Version 3.0.04
Network Scanner Tool R3.1 User s Guide Version 3.0.04 Copyright 2000-2004 by Sharp Corporation. All rights reserved. Reproduction, adaptation or translation without prior written permission is prohibited,
More informationVirtual Exhibit 5.0 requires that you have PastPerfect version 5.0 or higher with the MultiMedia and Virtual Exhibit Upgrades.
28 VIRTUAL EXHIBIT Virtual Exhibit (VE) is the instant Web exhibit creation tool for PastPerfect Museum Software. Virtual Exhibit converts selected collection records and images from PastPerfect to HTML
More informationUrban Tree Management System. Contact
U rban Tree Management System (UTMS) was developed and is distributed by Alan Wagar in Shoreline, Washingtion. Two versions of UTMS are available - UTMS 5000 and UTMS III. Both versions are identical except
More informationBangla Localization of OpenOffice.org. Asif Iqbal Sarkar Research Programmer BRAC University Bangladesh
Bangla Localization of OpenOffice.org Asif Iqbal Sarkar Research Programmer BRAC University Bangladesh Localization L10n is the process of adapting the text and applications of a product or service to
More informationThe LENA TM Language Environment Analysis System:
FOUNDATION The LENA TM Language Environment Analysis System: The Interpreted Time Segments (ITS) File Dongxin Xu, Umit Yapanel, Sharmi Gray, & Charles T. Baer LENA Foundation, Boulder, CO LTR-04-2 September
More informationImage Spam: The Email Epidemic of 2006
S e c u r i t y T r e n d s Overview Image Spam: The Email Epidemic of 2006 S E C U R I T Y T R E N D S O v e r v i e w End-users around the world are reporting an increase in spam. Much of this increase
More informationInternational Language Character Code
, pp.161-166 http://dx.doi.org/10.14257/astl.2015.81.33 International Language Character Code with DNA Molecules Wei Wang, Zhengxu Zhao, Qian Xu School of Information Science and Technology, Shijiazhuang
More informationSession 6: Element D: Reporting, monitoring and review
Session 6: Element D: Reporting, monitoring and review Connecting Element D with principles, approaches, methods and tools [REPSAHEL / MECCA-Africa] Sahara and Sahel Observatory - OSS [Nikola Rass] [Climate
More informationARGE Styrian Voip Business Park 4 8200 Gleisdorf Tel: 03112 38900 email: office@styrian-voip.at
USA _001201 0,06 USA _001313 0,06 USA _001202 0,06 USA _001314 0,06 USA _001203 0,06 USA _001315 0,06 Canada _001204 0,06 USA _001316 0,06 USA _001205 0,06 USA _001317 0,06 USA _001206 0,06 USA _001318
More informationThe Open University s repository of research publications and other research outputs
Open Research Online The Open University s repository of research publications and other research outputs Improving search in scanned documents: Looking for OCR mismatches Conference Item How to cite:
More informationTracking Moving Objects In Video Sequences Yiwei Wang, Robert E. Van Dyck, and John F. Doherty Department of Electrical Engineering The Pennsylvania State University University Park, PA16802 Abstract{Object
More informationDiscovering Computers 2008. Chapter 3 Application Software
Discovering Computers 2008 Chapter 3 Application Software Chapter 3 Objectives Identify the categories of application software Explain ways software is distributed Explain how to work with application
More informationSwivel Multi-factor Authentication
Swivel Multi-factor Authentication White Paper Abstract Swivel is a flexible authentication solution that offers a wide range of authentication models. The use of the Swivel patented one-time code extraction
More informationDigital Collections as Big Data. Leslie Johnston, Library of Congress Digital Preservation 2012
Digital Collections as Big Data Leslie Johnston, Library of Congress Digital Preservation 2012 Data is not just generated by satellites, identified during experiments, or collected during surveys. Datasets
More informationDetection and Restoration of Vertical Non-linear Scratches in Digitized Film Sequences
Detection and Restoration of Vertical Non-linear Scratches in Digitized Film Sequences Byoung-moon You 1, Kyung-tack Jung 2, Sang-kook Kim 2, and Doo-sung Hwang 3 1 L&Y Vision Technologies, Inc., Daejeon,
More informationComputer-Based Text- and Data Analysis Technologies and Applications. Mark Cieliebak 9.6.2015
Computer-Based Text- and Data Analysis Technologies and Applications Mark Cieliebak 9.6.2015 Data Scientist analyze Data Library use 2 About Me Mark Cieliebak + Software Engineer & Data Scientist + PhD
More informationModule 9 The CIS error profiling technology
Florian Fink Module 9 The CIS error profiling technology 2015-09-15 1 / 24 Module 9 The CIS error profiling technology Florian Fink Centrum für Informations- und Sprachverarbeitung (CIS) Ludwig-Maximilians-Universität
More informationThe Unicode Standard Version 8.0 Core Specification
The Unicode Standard Version 8.0 Core Specification To learn about the latest version of the Unicode Standard, see http://www.unicode.org/versions/latest/. Many of the designations used by manufacturers
More informationECE 533 Project Report Ashish Dhawan Aditi R. Ganesan
Handwritten Signature Verification ECE 533 Project Report by Ashish Dhawan Aditi R. Ganesan Contents 1. Abstract 3. 2. Introduction 4. 3. Approach 6. 4. Pre-processing 8. 5. Feature Extraction 9. 6. Verification
More informationecommerce Web-Site Trust Assessment Framework Based on Web Mining Approach
ecommerce Web-Site Trust Assessment Framework Based on Web Mining Approach ecommerce Web-Site Trust Assessment Framework Based on Web Mining Approach Banatus Soiraya Faculty of Technology King Mongkut's
More informationRIT American Museums Survey on Digital Imaging for Direct Capture of Artwork
RIT American Museums Survey on Digital Imaging for Direct Capture of Artwork Mitchell R. Rosen* and Franziska S. Frey *Munsell Color Science Laboratory School of Print Media Rochester Institute of Technology,
More information