The Community for Technology Leaders
Document Image Analysis for Libraries, International Workshop on (2006)
Lyon, France
Apr. 27, 2006 to Apr. 28, 2006
ISBN: 0-7695-2531-8
TABLE OF CONTENTS

Preface (PDF)

pp. viii
Introduction Paper

Interactive Document Processing and Digital Libraries (Abstract)

Daniel Lopresti , Lehigh University, Bethlehem, PA
George Nagy , Rensselaer Polytechnic Institute, Troy, NY
pp. 2-11
Chapter 1. Handwritten Documents Segmentation and Recognition

Separating Lines of Text in Free-Form Handwritten Historical Documents (Abstract)

Douglas J. Kennard , Brigham Young University
William A. Barrett , Brigham Young University
pp. 12-23

Multi-Queue Merging Scheme And Its Application in Arabic Script Segmentation (Abstract)

Pingping Xiu , Tsinghua University, China
Liangrui Peng , Tsinghua University, China
Xiaoqing Ding , Tsinghua University, China
pp. 24-29

Exploring the Use of Conditional Random Field Models and HMMs for Historical Handwritten Document Recognition (Abstract)

Andrew McCallum , University of Massachusetts
Shaolei Feng , University of Massachusetts
R. Manmatha , University of Massachusetts
pp. 30-37

Text Line Extraction in Handwritten Document with Kalman Filter Applied on Low Resolution Image (Abstract)

Aurelie Lemaitre , IRISA / INSA, Rennes Cedex, France
Jean Camillerapp , IRISA / INSA, Rennes Cedex, France
pp. 38-45

Complex Handwritten Page Segmentation Using Contextual Models (Abstract)

Thierry Paquet , Universite de Rouen UFR des Sciences et Techniques, Cedex, France
Laurent Heutte , Universite de Rouen UFR des Sciences et Techniques, Cedex, France
Stephane Nicolas , Universite de Rouen UFR des Sciences et Techniques, Cedex, France
pp. 46-59
Chapter 2. OCR and Layout Analysis for Multilingual Printed Documents

Dedicated Texture Based Tools for Characterisation of Old Books (Abstract)

R. Mullot , La Rochelle Cedex 1 - FRANCE
V. Eglin , LIRIS INSA de Lyon, Villeurbanne cedex - FRANCE
N. Jourmet , La Rochelle Cedex 1 - FRANCE
J.Y Ramel , LI-RFAI Jean Portalis TOURS - FRANCE
pp. 60-69

Detection and Segmentation of Table of Contents and Index Pages from Document Images (Abstract)

S. P. Chowdhury , CST Dept., B. E. & Science University, India
A. K. Das , CST Dept., B. E. & Science University, India
S. Mandal , CST Dept., B. E. & Science University, India
Bhabatosh Chanda , ECS Unit, Indian Statistical Unit Calcutta, India
pp. 70-81

Improving OCR Text Categorization Accuracy with Electronic Abstracts (Abstract)

Chew Lim Tan , National University of Singapore, Kent Ridge, Singapore
Linlin Li , National University of Singapore, Kent Ridge, Singapore
pp. 82-87

Character templates learning for textual images recognition as an example of learning in structural recognition (Abstract)

Bogdan Savchynskyy , International Research and Training Center of Information Technologies and Systems, Kiev, Ukraine
Olexander Kamotskyy , International Research and Training Center of Information Technologies and Systems, Kiev, Ukraine
pp. 88-95

Design and Comparison of Segmentation Driven and Recognition Driven Devanagari OCR (Abstract)

Venu Govindaraju , CEDAR, University at Buffalo, Amherst, NY
Srirangaraj Setlur , CEDAR, University at Buffalo, Amherst, NY
Suryaprakash Kompalli , CEDAR, University at Buffalo, Amherst, NY
pp. 96-102

Combining a hybrid Approach for Features Selection and Hidden Markov Models in Multifont Arabic Characters Recognition (Abstract)

Najoua Essoukri Ben Amara , National Engineering School of Sousse (ENISo) Tunisia
Nadia Ben Amor , National Engineering School of Tunis (ENIT) Tunisia
pp. 103-107

OCR Voting Methods for Recognizing Low Contrast Printed Documents (Abstract)

Laszlo Toth , Scansoft-Recognita, Inc.
Istvan Marosi , Scansoft-Recognita, Inc.
pp. 108-115
Chapter 3. DIA Applications for Digital Libraries

The Case of the Digitized Works at a National Digital Library (Abstract)

Joao Gil , INESC-ID - Instituto de Engenharia de Sistemas e Computadores, Lisboa, Portugal
Joao Penas , INESC-ID - Instituto de Engenharia de Sistemas e Computadores, Lisboa, Portugal
Jose Borbinha , INESC-ID - Instituto de Engenharia de Sistemas e Computadores, Lisboa, Portugal
Gilberto Pedrosa , INESC-ID - Instituto de Engenharia de Sistemas e Computadores, Lisboa, Portugal
pp. 116-125

Multilingual document recognition research and its application in China (Abstract)

Liangrui Peng , Tsinghua University, China
Xiaoqing Ding , Tsinghua University, China
Changsong Liu , Tsinghua University, China
Hua Wang , Tsinghua University, China
pp. 126-132

Digital Bleaching and Content Extraction for the Digital Archive of Rare Books (Abstract)

Dominique Deuff , National Institute of Informatics, Tokyo, Japan
Sonoko Sato , National Institute of Informatics, Tokyo, Japan
Asanobu Kitamoto , National Institute of Informatics, Tokyo, Japan
Tomohiro Ikezaki , National Institute of Informatics, Tokyo, Japan
Takako Muramatsu , National Institute of Informatics, Tokyo, Japan
Takeo Yamamoto , National Institute of Informatics, Tokyo, Japan
Makiko Onishi , National Institute of Informatics, Tokyo, Japan
Ryo Kamida , National Institute of Informatics, Tokyo, Japan
Kinji Ono , National Institute of Informatics, Tokyo, Japan
Eka Meyer , National Institute of Informatics, Tokyo, Japan
pp. 133-144

AGORA: the Interactive Document Image Analysis Tool of the BVH Project (Abstract)

J.Y. Ramel , Ecole Polytechnique de l?Universite de Tours, France
S. Busson , CESR - UMR 6576 du CNRS Tours, France
M.L. Demonet , CESR - UMR 6576 du CNRS Tours, France
pp. 145-155

User centered image management system for digital libraries (Abstract)

Elod EGYED-ZSIGMOND , LIRIS INSA-Lyon, Villeurbanne Cedex, France
Zoltan ISZLAI , Sapientia EMTE, Romania
pp. 164-171

What can we learn from the processing of 165,000 forms from the 19th century? (Abstract)

Bertrand Couasnon , IRISA / INSA, Campus universitaire de Beaulieu, Rennes Cedex, France
pp. 172-179
Chapter 4. Documents Images Indexing and Retrieval

Use of Figures in Literature Mining for Biomedical Digital Libraries (Abstract)

Hagit Shatka , Queen's University, Kingston, Ontario, Canada
Nawei Chen , Queen's University, Kingston, Ontario, Canada
Dorothea Blostein , Queen's University, Kingston, Ontario, Canada
pp. 180-197

Document Image Retrieval using Signatures as Queries (Abstract)

Siyuan Chen , CEDAR, University at Buffalo(SUNY), NY
Shravya Shetty , CEDAR, University at Buffalo(SUNY), NY
Sargur N. Srihari , CEDAR, University at Buffalo(SUNY), NY
Harish Srinivasan , CEDAR, University at Buffalo(SUNY), NY
Gady Agam , Illinois Institute of Technology, Chicago
Chen Huang , CEDAR, University at Buffalo(SUNY), NY
Ophir Frieder , Illinois Institute of Technology, Chicago
pp. 198-203

Automatic Content-based Indexing of Digital Documents through Intelligent Processing Techniques (Abstract)

Nicola Di Mauro , University of Bari, Italy
Stefano Ferilli , University of Bari, Italy
Floriana Esposito , University of Bari, Italy
Teresa M.A. Basile , University of Bari, Italy
pp. 204-219

On defining signatures for the retrieval and the classification of graphical drop caps (Abstract)

Jean-Marc Ogier , Universite de la Rochelle, Avenue Michel Crepeau, La Rochelle CEDEX, France
Rudolf Pareti , Laboratoire CRIP5, Universite de Paris 5, France
Surapong Uttama , Universite de la Rochelle, Avenue Michel Crepeau, La Rochelle CEDEX, France
Laurent Wendling , LORIA, INRIA, CEDEX, France
Sebastien Adam , Laboratoire PSI, Universite de Rouen, UFR Sciences, CEDEX, France
Salvatore Tabbone , LORIA, INRIA, CEDEX, France
Jean-Pierre Salmon , LORIA, INRIA, CEDEX, France
Nicole Vincent , Laboratoire CRIP5, Universite de Paris 5, France
pp. 220-231

Distance Measures for Layout-Based Document Image Retrieval (Abstract)

Joost Van Beusekom , Technical University of Kaiserslautern, Germany
Faisal Shafait , Technical University of Kaiserslautern, Germany
Daniel Keysers , Technical University of Kaiserslautern, Germany
Thomas M. Breuel , Technical University of Kaiserslautern, Germany
pp. 232-242

Tree clustering for layout-based document image retrieval (Abstract)

Simone Marinai , Universita di Firenze, Italy
Giovanni Soda , Universita di Firenze, Italy
Emanuele Marino , Universita di Firenze, Italy
pp. 243-253
Chapter 5. Other Trends in DIA

Ink recognition based on statistical classification methods (Abstract)

Vassilis Konstantinou , University of Westminster, Watford Road, UK
Vasiliki Kokla , University of Westminster, Watford Road, UK
Alexandra Psarrou , University of Westminster, Watford Road, UK
pp. 254-264

Computer assistance for Digital Libraries: Contributions to Middle-ages and Authors? Manuscripts exploitation and enrichment (Abstract)

S. BRES , LIRIS INSA de Lyon, Villeurbanne cedex - France
I. MOALLA , LIRIS INSA de Lyon, Villeurbanne cedex - France
F. LEBOURGEOIS , LIRIS INSA de Lyon, Villeurbanne cedex - France
H. EMPTOZ , LIRIS INSA de Lyon, Villeurbanne cedex - France
V. EGLIN , LIRIS INSA de Lyon, Villeurbanne cedex - France
F. DRIRA , LIRIS INSA de Lyon, Villeurbanne cedex - France
Y. LEYDIER , LIRIS INSA de Lyon, Villeurbanne cedex - France
pp. 265-280

Querying for silhouettes by qualitative feature schemes (Abstract)

Bjorn Gottfried , University of Bremen, Germany
pp. 281-290

A novel technique for the watermarking of symbolically compressed documents (Abstract)

Utpal Garain , Computer Vision & Pattern Recognition Unit
Sarbani Palit , Computer Vision & Pattern Recognition Unit
pp. 291-296

Refinement of digitized documents through recognition of mathematical formulae (Abstract)

Masakazu SUZUKI , Kyushu University, Fukuoka, Japan
Toshihiro KANAHORI , Tsukuba University of Technology,Ibaraki, Japan
pp. 297-302

Image Analysis for Palaeography Inspection (Abstract)

A. M. ALIMI , University of Sfax, ENIS, DGE, BP. W-3038 - Sfax, Tunisia
I. MOALLA , University of Sfax, ENIS, DGE, BP. W-3038 - Sfax, Tunisia
H. EMPTOZ , Laboratoire d'InfoRmatique en Images et Syst?mes d'information (LIRIS)
F. LEBOURGEOIS , Laboratoire d'InfoRmatique en Images et Syst?mes d'information (LIRIS)
pp. 303-311
Chapter 6. DIA Evaluation and Document Image Quality

Quality Assurance in High Volume Document Digitization: A Survey (Abstract)

Xiaofan Lin , Hewlett-Packard Laboratories, Palo Alto, CA
pp. 312-319

Performance Evaluation of a Mathematical Formula Recognition System with a large scale of printed formula images (Abstract)

Masayuki Okamoto , Shinshu University, Nagano, Japan
Hiroki Imai , Seiko Epson Corporation
Kazuki Ashida , Shinshu University, Matsumoto, Japan
Tsubasa Nakatsuka , Seiko Epson Corporation
pp. 320-331

Experimental Performance Study of a User Intensive and Large-scale Digital Library Framework (Abstract)

Bin Wang , Chinese Academy of Sciences Beijing, P.R.China
Xiangwen Liao , Graduate School of the Chinese Academy of Sciences, Beijing, P.R.China
Binxing Fang , Chinese Academy of Sciences Beijing, P.R.China
Weihua Luo , Chinese Academy of Sciences Beijing, P.R.China
pp. 332-339

Improving the Quality of Degraded Document Images (Abstract)

Ergina Kavallieratou , University of the Aegean, Karlovassi, Greece
Efstathios Stamatatos , University of the Aegean, Karlovassi, Greece
pp. 340-349

Towards Restoring Historic Documents Degraded Over Time (Abstract)

Fadoua DRIRA , UMR 5205 du CNRS- INSA de LYON, France
pp. 350-357

Image Interpolation using Mathematical Morphology (Abstract)

Valerie De Witte , Department of Applied Mathematics & Computer Science, Ghent University, Gent, Belgium
Wilfried Philips , Telin Department, Ghent University, Gent, Belgium
Alessandro Ledda , Telin Department, Ghent University, Gent, Belgium
Hiep Q. Luong , Telin Department, Ghent University, Gent, Belgium
Etienne E. Kerre , Department of Applied Mathematics & Computer Science, Ghent University, Gent, Belgium
pp. 358-367

An Image Inpainting Approach Based on the Poisson Equation (Abstract)

Houqiang Li , University of Science and Technology of China
Xiaowei Shao , University of Science and Technology of China
Zhengkai Liu , University of Science and Technology of China
pp. 368-372
Author Index

Author Index (Abstract)

pp. 373
98 ms
(Ver )