Guide to OCR for Arabic Scripts (eBook, PDF)

Redaktion: Märgner, Volker; El Abed, Haikal

• Format: PDF

Produktbeschreibung

Optical Character Recognition (OCR) is a key technology enabling access to digital text data. This technique is especially valuable for Arabic scripts, for which there has been very little digital access.

Arabic script is widely used today. It is estimated that approximately 200 million people use Arabic as a first language, and the Arabic script is shared by an additional 13 languages, making it the second most widespread script in the world. However, Arabic scripts pose unique challenges for OCR systems that cannot be simply adapted from existing Latin character-based processing techniques.

This comprehensive Guide to OCR for Arabic Scripts is the first book of its kind, specifically devoted to this emerging field. Presenting state-of-the-art research from an international selection of pre-eminent authorities, the book reviews techniques and algorithms for the recognition of both handwritten and printed Arabic scripts. Many of these techniques can also be applied to other scripts, serving as an inspiration to all groups working in the area of OCR.

Topics and features:

• Contains contributions from the leading researchers in the field
• With a Foreword by Professor Bente Maegaard of the University of Copenhagen
• Presents a detailed overview of Arabic character recognition technology, covering a range of different aspects of pre-processing and feature extraction
• Reviews a broad selection of varying approaches, including HMM-based methods and a recognition system based on multidimensional recurrent neural networks
• Examines the evaluation of Arabic script recognition systems, discussing data collection and annotation, benchmarking strategies, and handwriting recognition competitions
• Describes numerous applications of Arabic script recognition technology, from historical Arabic manuscripts to online Arabic recognition

This authoritative work is an essential reference for all researchers and graduate students interested in OCR technology and methodology in general, and in Arabic scripts in particular.

---

Dieser Download kann aus rechtlichen Gründen nur mit Rechnungsadresse in A, B, BG, CY, CZ, D, DK, EW, E, FIN, F, GR, HR, H, IRL, I, LT, L, LR, M, NL, PL, P, R, S, SLO, SK ausgeliefert werden.

Produktdetails

• Verlag: Springer-Verlag GmbH
• Seitenzahl: 592
• Erscheinungstermin: 3. Juli 2012
• Englisch
• ISBN-13: 9781447140726
• Artikelnr.: 37669572

Autorenporträt

Volker Märgner is Academic Director of the Institute for Communications Technology (IfN) at Technische Universität Braunschweig, Germany. He has over 30 years research experience in image processing, pattern recognition, and handwriting recognition. He developed the IfN/ENIT-database of Arabic handwritten names which is the reference for Arabic handwritten word recognition systems and organized competitions both together with Haikal El Abed. Haikal El Abed is a Senior Research Engineer at the Institute for Communications Technology (IfN) at Technische Universität Braunschweig, Germany. He has more than 10 years research experience in pattern recognition and Arabic text recognition, on-line and off-line. He organizes competitions and works on the collection of databases.

Inhaltsangabe

Part I: Pre-Processing

An Assessment of Arabic Handwriting Recognition Technology
Sargur N. Srihari and Gregory Ball

Layout Analysis of Arabic Script Documents
Syed Saqib Bukhari, Faisal Shafait and Thomas M. Breuel

A Multi-Stage Approach to Arabic Document Analysis
Eugene Borovikov and Ilya Zavorin

Pre-Processing Issues in Arabic OCR
Zhixin Shi, Srirangaraj Setlur and Venu Govindaraju

Segmentation of Ancient Arabic Documents
Abdel Belaïd and Nazih Ouwayed

Features for HMM-Based Arabic Handwritten Word Recognition Systems
Laurence Likforman-Sulem, Ramy Al Hajj Mohammad, Chafic Mokbel, Fares Menasri, Anne-Laure Bianne-Bernard and Christopher Kermorvant

Part II: Recognition

Printed Arabic Text Recognition
Irfan Ahmed, Sabri A. Mahmoud and Mohammed Tanvir Parvez

Handwritten Arabic Word Recognition Using the IFN/ENIT-Database
Mario Pechwitz, Haikal El Abed and Volker Märgner

RWTH OCR: A Large Vocabulary Optical Character Recognition System for Arabic Scripts
Philippe Dreuw, David Rybach, Georg Heigold and Hermann Ney

Arabic Handwriting Recognition using Bernoulli HMMs
Ihab Alkhoury, Adrià Giménez and Alfons Juan

Handwritten Farsi Words Recognition Using Hidden Markov Models
Puntis Jifroodian and Ching Y. Suen

Offline Arabic Handwriting Recognition with Multidimensional Recurrent Neural Networks
Alex Graves

Application of Fractal Theory in Farsi/Arabic Document Analysis
Saeed Mozaffari

Multi-Stream Markov Models for Arabic Handwriting Recognition
Yousri Kessentini, Thierry Paquet and AbdelMajid Ben Hamadou

Towards Distributed Cursive Writing OCR Systems based on the Combination of Complementary Approaches
Maher Khemakhem and Abdelfettah Belghith

Part III: Evaluation

Data Collection and Annotation for Arabic Document Analysis
Ilya Zavorin and Eugene Borovikov

Arabic Handwriting Recognition Competitions
Volker Märgner and Haikal El Abed

Benchmarking Strategy for Arabic Screen Rendered Word Recognition
Fouad Slimane, Slim Kanoun, Jean Hennebert, Rolf Ingold, Adel M. Alimi and Jean Hennebert

Part IV: Applications

A Robust Word Spotting System for Historical Arabic Manuscripts
Mohamed Cheriet and Reza Farrahi Moghaddam

Arabic Text recognition using a Script-Independent Methodology: A Unified HMM-based Approach for Machine-print and Handwritten Text
Premkumar Natarajan, Rohit Prasad, Huaigu Cao, Krishna Subramanian, Shirin Saleem, David Belanger, Shiv Vitaladevuni, Matin Kamali and Ehry MacRostie

Arabic Handwriting Recognition Using VDHMM and Over-Segmentation
Amlan Kundu and Tom Hines

Online Arabic Databases and Applications
Houcine Boubaker, Abdelkarim Elbaati, Najiba Tagougui, Haikal El Abed, Monji Kherallah and Adel M. Alimi

Online Arabic Handwritten Words Recognition Based on HMM and Combination of Online and Offline Features
Sherif Abdelazeem, Hesham M. Eraqi and Hany Ahmed