Guide to OCR for Indic Scripts: Document Recognition and Retrieval

ISBN-13: 9781447125181 / Angielski / Miękka / 2012 / 325 str.

Govindaraju, Venu

Opis

Theoriginalmotivationsfordevelopingopticalcharacterrecognitiontechnologies weremodesttoconvertprintedtexton?atphysicalmediatodigitalform, prod- ingmachine-readabledigitalcontent. Bydoingthis, wordsthathadbeeninertand bound to physical material would be brought into the digital realm and thus gain newandpowerfulfunctionalitiesandanalyticalpossibilities. First-generation digital OCR researchers in the 1970s quickly realized that by limiting their ambitions primarily to contemporary documents printed in st- dard font type from the modern Roman alphabet (and of these, mostly English language materials), they were constraining the possibilities for future research andtechnologiesconsiderably. Domainresearchersalsosawthatthetrajectoryof OCR technologies if left unchanged would exclude a large portion of the human record. Digitalconversionofdocumentsandmanuscriptsinotheralphabets, scripts, and cursive styles was of critical importance. Embedded in non-Roman alp- bet source documents, including ancient manuscripts, papyri scrolls, clay tablets, and other inscribed artifacts was not only a wealth of scholarly information but alsonewopportunitiesandchallengesforadvancingOCR, imagingsciences, and othercomputationalresearchareas. Thelimitingcircumstancesatthetimeincluded the rudimentary capability (and high cost) of computational resources and lack of network-accessible digital content. Since then computational technology has advancedataveryrapidpaceandnetworkinginfrastructurehasproliferated. Over time, thisexponential decrease inthecost of computation, memory, and com- nicationsbandwidthcombinedwiththeexponentialincreaseinInternet-accessible digitalcontenthastransformededucation, scholarship, andresearch. Largenumbers ofresearchers, scholars, andstudentsuseanddependuponInternet-basedcontent andcomputationalresources. Thechaptersinthisbookdescribeacriticallyimportantareaofinvestigation- addressingconversionofIndicscriptintomachine-readableform. Roughestimates haveitthatcurrentlymorethanabillionpeopleuseIndicscripts. Collectively, Indic historic and cultural documents contain a vast richness of human knowledge and experience. The state-of-the-art research described in this book demonstrates the multiple values associated with these activities. Technically, the problems associated with Indicscriptrecognitionareverydif?cultandwillcontributetoandinformrelated v vi Foreword scriptrecognitionefforts. Theworkalsohasenormousconsequenceforenriching andenablingthestudyofIndicculturalheritagematerialsandthehistoricrecord of its people. This in turn broadens the intellectual context for domain scholars focusingonothersocieties, ancientandmodern. Digital character recognition has brought about another milestone in coll- tivecommunicationbybringinginert, ?xed-in-place, textintoaninteractivedi- talrealm. Indoingso, theinformationhasgainedadditionalfunctionalitieswhich expandourabilitiestoconnect, combine, contextualize, share, andcollaboratively pursue knowledge making. High-quality Internet content continues to grow in an explosivefashion. Inthenewglobalcyberenvironment, thefunctionalitiesandapp- cationsofdigitalinformationcontinuetotransformknowledgeintonewundersta- ingsofhumanexperienceandtheworldinwhichwelive. Thepossibilitiesforthe futurearelimitedonlybyavailableresearchresourcesandcapabilitiesandtheim- inationandcreativityofthosewhousethem. Arlington, Virginia StephenM.

This unique guide/reference is the very first comprehensive book on the subject of OCR (Optical Character Recognition) for Indic scripts. Features: contains contributions from the leading researchers in the field; discusses data set creation for OCR development; describes OCR systems that cover 8 different scripts Bangla, Devanagari, Gurmukhi, Gujarati, Kannada, Malayalam, Tamil, and Urdu (Perso-Arabic); explores the challenges of Indic script handwriting recognition in the online domain; examines the development of handwriting-based text input systems; describes ongoing work to increase access to Indian cultural heritage materials; provides a section on the enhancement of text and images obtained from historical Indic palm leaf manuscripts; investigates different techniques for word spotting in Indic scripts; reviews mono-lingual and cross-lingual information retrieval in Indic languages. This is an excellent reference for researchers and graduate students studying OCR technology and methodologies.

Spis treści

Part I: Recognition of Indic Scripts Building Data Sets for Indian Language OCR Research C. V. Jawahar, Anand Kumar, A. Phaneendra and K.J. Jinesh On OCR of major Indian scripts: Bangla and Devanagari B. B. Chaudhari A Complete Machine Printed Gurmukhi OCR System Gurpreet Singh Lehal Progress in Gujarati Document Processing and Character Recognition Jignesh Dholakia, Atul Negi and S. Rama Mohan Design of a bilingual Kannada-English OCR R. S. Umesh , P. B. Pati and A. G. Ramakrishnan Recognition of Malayalam Documents N. V. Neeba , Anoop Namboodiri, C. V. Jawahar and P. J. Narayanan A Complete OCR System for Tamil Magazine Documents K. H. Aparna and V. S. Chakravarthy Experiments on Urdu Text Recognition Omar Mukhtar, Srirangaraj Setlur and Venu Govindaraju The BBN Byblos Hindi OCR System Prem Natarajan, Ehry MacRostie, and Michael Decerbo Generalization of Hindi OCR using Adaptive Segmentation and Font Files Mudit Agrawal, Huanfeng Ma and David Doermann Online Handwriting Recognition for Indic Scripts A. Bharath and Sriganesh Madhvanath Part II: Retrieval of Indic Documents Enhancing Access to Primary Cultural Heritage Materials of India Peter M. Scharf and Malcolm Hyman Digital Image Enhancement of Indic Historical Manuscripts Zhixin Shi, Srirangaraj Setlur and Venu Govindaraju GFG based Compression and Retrieval of Document Images in Indian Scripts Gaurav Harit, Shantanu Chaudhary and Ritu Garg Word spotting for Indic documents to facilitate retrieval Anurag Bhardwaj, Srirangaraj Setlur, Venu Govindaraju Indian Language Information Retrieval Prasenjit Majumder and Mandar Mitra

Blurb

Optical Character Recognition (OCR) is a key enabling technology critical to creating indexed, digital library content, and it is especially valuable for Indic scripts, for which there has been very little digital access.

Indic scripts, the ancient Brahmi scripts prevalent in the Indian subcontinent, present some challenges for OCR that are different from those faced with Latin and Oriental scripts. But properly utilized, OCR will help to make Indic digital archives practically accessible to researchers and lay users alike by creating searchable indexes and machine-readable text repositories.

This unique guide/reference is the very first comprehensive book on the subject of OCR for Indic scripts, providing an overview of the state-of-the-art research in this field as well as other issues related to facilitating query and retrieval of Indic documents from digital libraries. All major research groups working in this area are represented in this book, which is divided into sections on recognition of Indic scripts and retrieval of Indic documents.

Topics and features:

• Contains contributions from the leading researchers in the field
• Discusses data set creation for OCR development
• Describes OCR systems that cover eight different scripts: Bangla, Devanagari, Gurmukhi, Gujarati, Kannada, Malayalam, Tamil, and Urdu (Perso-Arabic)
• Explores the challenges of Indic script handwriting recognition in the online domain
• Examines the development of handwriting-based text input systems
• Describes ongoing work to increase access to Indian cultural heritage materials
• Provides a section on the enhancement of text and images obtained from historical Indic palm leaf manuscripts
• Investigates different techniques for word spotting in Indic scripts
• Reviews mono-lingual and cross-lingual information retrieval in Indic languages

This is an excellent reference for researchers and graduate students studying OCR technology and methodologies. This volume will contribute to opening up the rich Indian cultural heritage embodied in millions of ancient and contemporary documents spanning topics such as science, literature, medicine, astronomy, mathematics and philosophy.

Venu Govindaraju FIEEE FIAPR, is a Distinguished Professor of Computer Science and Engineering at the University at Buffalo. He has over 20 years of research experience in pattern recognition, information retrieval and biometrics. His seminal work on handwriting recognition was at the core of the first handwritten address interpretation system used by the U.S. Postal Service.

Srirangaraj Setlur SMIEEE, is a Principal Research Scientist at the University at Buffalo. He has over 15 years of research experience in pattern recognition that includes NSF sponsored work on multilingual OCR technologies for digital libraries and other applications. His work on postal automation has led to technology adopted by the U.S. Postal Service, and Royal Mail in the U.K.