2011 International Conference

on Document Analysisand Recognition

(ICDAR2011)

Beijing, China

18 - 21 September 2011

Pages 1-758

IEEE IEEE Catalog Number: CFPl1227-PRT

ISBN: 978-1-4577-1350-7

11th international Conference

on Document Analysisand Recognition

ICDAR 2011

Table of Contents

Welcome from the General Chairs xxvii

Welcome from the Program Chairs xxviii

Conference Committees xxix

Reviewers xxxii

Sponsors xxxv

Document Image ProcessingA Tool for Tuning Binarization Techniques 1

Vavilis Sokratis and Ergina Kavallieratou

A Laplacian Energy for Document Binarization 6

Nicholas R. Howe

An MRF Model for Binarization of Natural Scene Text 11

AnandMishra, KarteekAlahari, and C.V. Jawahar

Stroke-Like Pattern Noise Removal in Binary Document Images 17

Mudit Agrawal and David Doermann

Combination of Document Image Binarization Techniques 22

Bolan Su, Shijian Lu, and Chew Lim Tan

Determining Document Skew Using Inter-line Spaces 27

Boris Epshtein

Datasets and Performance Evaluation

When is a Problem Solved?, 32

Daniel Lopresti and George Nagy

CASIA Online and Offline Chinese Handwriting Databases 37

Cheng-Lin Liu, Fei Yin, Da-Han Wang, and Qiu-Feng Wang

An Open Architecture for End-to-End Document Analysis Benchmarking 42

Bart Lamiroy and Daniel Lopresti

Aletheia - An Advanced Document Layout and Text Ground-Truthing System

for Production Environments 48

C. Clausner, S. Pletschacher, and A. Antonacopoulos

HMM-Based Alignment of Inaccurate Transcriptions for Historical Documents 53

Andreas Fischer, Emanuel Indermuhle, Volkmar Frinken, and Horst Bunke

Transcript Mapping for Handwritten Text Lines Using Conditional Random

Fields 58

Xiang-Dong Zhou, Fei Yin, Da-Han Wang, Qiu-Feng Wang, Masaki Nakagawa,

and Cheng-Lin Liu

Document Retrieval (1)

Browsing Heterogeneous Document Collections by a Segmentation-Free

Word Spotting Method 63

Margal Rusihol, David Aldavert, Ricardo Toledo, and Josep Llados

Fast Key-Word Searching via Embedding and Active-DTW 68

Raid Saabni and Alex Bronstein

Keyword Spotting in Online Handwritten Documents Containing Text

and Non-text Using BLSTM Neural Networks 73

Emanuel Indermuhle, Volkmar Frinken, Andreas Fischer, and Horst Bunke

Keyword Spotting in Offline Chinese Handwritten Documents Using

a Statistical Model 78

Liang Huang, Fei Yin, Qing-Hu Chen, and Cheng-Lin Liu

BLSTM Neural Network Based Word Retrieval for Hindi Documents 83

Raman Jain, Volkmar Frinken, C. V. Jawahar, and R. Manmatha

A Method for Removing Inflectional Suffixes in Word Spotting of Mongolian

Kanjur 88

Hongxi Wei, Guanglai Gao, and Yulai Bao

Poster Session 1

A Handwritten Character Extraction Algorithm for Multi-language Document

Image 93

Yonghong Song, Guilin Xiao, Yuanlin Zhang, Lei Yang, and Liuliu Zhao

Retrieval of Envelope Images Using Graph Matching 99

Li Liu, Yue Lu, and Ching Y. Suen

Automatic Estimation of the Legibility of Binarised Historic Documents

for Unsupervised Parameter Tuning 104

M. Stommei and G. Frieder

Segmentation of Handwritten Textlines in Presence of Touching Components 109

Jayant Kumar, Le Kang, David Doermann, and Wael Abd-Almageed

Ternary Entropy-Based Binarization of Degraded Document Images Using

Morphological Operators 114

T. Hoang Ngan Le, Tien D. Bui, and Ching Y. Suen

Large Scale Page-Based Book Similarity Clustering 119

Nemanja Spasojevic and Guillaume Poncin

A New Gradient Based Character Segmentation Method for Video Text

Recognition 126

Palaiahnakote Shivakumara, Souvik Bhowmick, Bolan Su, Chew Lim Tan,

and Umapada Pal

Video Character Recognition through Hierarchical Classification 131

Palaiahnakote Shivakumara, Trung Quy Phan, Shijian Lu, and Chew Lim Tan

Robust Vanishing Point Detection for MobileCam-Based Documents 136

Xu-Cheng Yin, Hong-Wei Hao, Jun Sun, and Satoshi Naoi

A Benchmark Kannada Handwritten Document Dataset and Its Segmentation 141

Alireza Alaei, P. Nagabhushan, and Umapada Pal

A Digital Ink Recogntion Server for Handwritten Japanese Text 146

Daqing Wang, Bilan Zhu, and Masaki Nakagawa

A Novel Method for Embedded Text Segmentation Based on Stroke and Color 151

Xiufei Wang, Lei Huang, and Changping Liu

Using Ontologies to Reduce the Semantic Gap between Historians and Image

Processing Algorithms 156

Mickal Coustaty, Alain Bouju, Karell Bertet, and Georges Louis

Probabilistic Mathematical Formula Recognition Using a 2D Context-Free

Graph Grammar 161

Mehmet Celik and Berrin Yanikoglu

Chromatic / Achromatic Separation in Noisy Document Images 167

,4sma Ouji, Yann Leydier, and Frank Lebourgeois

Novel Data Representation for Text Extraction from Multispectral Historical

Document Images 172

Rachid Hedjam and Mohamed Cheriet

Text Detection in Natural Scene Images by Stroke Gabor Words : 177

Chucai Yi and Yingli Tian

A Shape Descriptor Combining Logarithmic-Scale Histogram of Radon

Transform and Phase-Only Correlation Function 182

Makoto Hasegawa and Salvatore Tabbone

Segmentation of Graphical Objects as Maximally Stable Salient Regions 187

Su Yang and Yuanyuan Wang

An Optimized Multi-stream Decoding Algorithm for Handwritten Word

Recognition 192

Yousri Kessentini, Thierry Paquet, and Ahmed Guermazi

Indexing On-line Handwritten Texts Using Word Confusion Networks 197

Sebastian Pena Saldarriaga and Mohamed Cheriet

Circle Text Expansion as Low-Rank Textures 202

Xin Zhang and Fuchun Sun

MRG-OHTC Database for Online Handwritten Tibetan Character Recognition 207

Long-long Ma, Hui-dan Liu, and Jian Wu

Using Readers' Highlighting on Monochromatic Documents for Automatic Text

Transcription and Summarization 212

Ricardo da Silva Barboza, Rafael Dueire Lins, and Victor Matheus de S. Pereira

Color-Mixing Correction of Overlapped Colors in Scanner Images 217

Misako Suwa

Enhanced Active Contour Method for Locating Text 222

Yaakov Navon, Vladimir Kluzner, and Boaz Ophir

Updating Knowledge in Feedback-Based Multi-classifier Systems 227

D. Impedovo and G. Pirlo

A New Feature Optimization Method Based on Two-Directional 2DLDA

for Handwritten Chinese Character Recognition 232

Xue Gao, Wenhuan Wen, and Lianwen Jin

Development of Template-Free Form Recognition System 237

Junichi Hirayama, Hiroshi Shinjo, Toshikazu Takahashi, and Takeshi Nagasaki

Data Extraction from Web Tables: The Devil is in the Details 242

George Nagy, Sharad Seth, Dongpu Jin, David W. Embley, Spencer Machado,

and Mukkai Krishnamoorthy

A Method of Evaluating Table Segmentation Results Based on a Table Image

Ground Truther 247

Yanhui Liang, Yizhou Wang, and Eric Saund

The SCRIBO Module of the Olena Platform: A Free Software Framework

for Document Image Analysis 252

Guillaume Lazzara, Roland Levillain, Thierry Geraud, Yann Jacquelet,

Julien Marquegnies, and Arthur Crepin-Leblond

A Semi-supervised Ensemble Learning Approach for Character Labelingwith Minimal Human Effort 259

Szilard Vajda, Akmal Junaidi, and Gemot A. Fink

Character Recognition Based on DTW-Radon 264

K.C. Santosh

A Mixed Approach for Handwritten Documents Structural Analysis 269

Vincent Malleron and Ve~ronique Eglin

Binarization of Color Character Strings in Scene Images Using /("-Means

Clustering and Support Vector Machines 274

Toru Wakahara and Kohei Kita

Efficient Cut-Off Threshold Estimation for Word Spotting Applications 279

A. L. Kesidis and B. Gatos

Improvement of On-line Recognition Systems Using a RBF-Neural Network

Based Writer Adaptation Module 284

Lobna Haddad, Tarek M. Hamdani, Monji Kherallah, and Adel M. Alimi

Distortion Measurement for Automatic Document Verification 289

Joost van Beusekom and Faisal Shafait

Composite Script Identification and Orientation Detection for Indian Text

Images 294

Shamita Ghosh and Bidyut B. Chaudhuri

A Painting Based Technique for Skew Estimation of Scanned Documents 299

Alireza Alaei, Umapada Pal, P. Nagabhushan, and Fumitaka Kimura

Database Development and Recognition of Handwritten Devanagari Legal

Amount Words 304

R. Jayadevan, S. R. Kolhe, P. M. Patil, and Umapada Pal

Sample-Dependent Feature Selection for Faster Document Image

Categorization 309

Jerome Louradour and Christopher Kermorvant

Co-training for Handwritten Word Recognition 314

Volkmar Frinken, Andreas Fischer, Horst Bunke, and Alicia Foornes

Web Multimedia Object Clustering via Information Fusion 319

Wenting Lu, Lei Li, Tao Li, Honggang Zhang, and Jun Guo

A New Text-Line Alignment Approach Based on Piece-Wise Painting

Algorithm for Handwritten Documents 324

Alireza Alaei, P. Nagabhushan, and Umapada Pal

Baseline Dependent Percentile Features for Offline Arabic Handwriting

Recognition 329

Pradeep Natarajan, David Belanger, Rohit Prasad, Matin Kamali,

Krishna Subramanian, and Prem Natarajan

Stroke-Based Performance Metrics for Handwritten Mathematical Expressions 334

Richard Zanibbi, Amit Pillay, Harold Mouchere, Christian Viard-Gaudin,

and Dorothea Blostein

An Application of the 2D Gaussian Filter for Enhancing Feature Extraction

in Off-line Signature Verification 339

Vu Nguyen and Michael Blumenstein

alpha-Shape Based Classification with Applications to Optical Character

Recognition 344

Eli Packer, Asaf Tzadok, and Vladimir Kluzner

Bags of Strokes Based Approach for Classification and Indexing of Drop Caps 349

Thi Thuong Huyen Nguyen, Mickael Coustaty, and Jean-Marc Ogier

Robust Cell Extraction Method for Form Documents Based on Intersection

Searching and Global Optimization 354

Hiroshi Tanaka, Hiroaki Takebe, and Yoshinobu Hotta

Hypothesis Preservation Approach to Scene Text Recognition with Weighted

Finite-State Transducer 359

Takafumi Yamazoe, Minoru Etoh, Takeshi Yoshimura, and Kousuke Tsujino

Statistical Grouping for Segmenting Symbols Parts from Line Drawings,

with Application to Symbol Spotting 364

Nibal Nayefand Thomas M. Breuel

Overlapped Handwriting Input on Mobile Phones 369

Yanming Zou, Yingfei Liu, Ying Liu, and Kongqiao Wang

A Robust Color-independent Text Detection Method from Complex Videos 374

Yan Zhao, Tong Lu, and Wujun Liao

Handwritten and Audio Information Fusion for Mathematical Symbol

Recognition 379

Sofiane Medjkoune, Harold Mouchere, Simon Petitrenaud,

and Christian Viard-Gaudin

A Novel Skew Detection Technique Based on Vertical Projections 384

A. Papandreou and B. Gatos

Discrimination of Old Document Images Using Their Style 389

Mickael Coustaty and Jean-Marc Ogier

Performance Evaluation of Algorithms for Newspaper Article Identification 394

Roberto Beretta and Luigi Laura

Table Detection in Noisy Off-line Handwritten Documents 399

Jin Chen and Daniel Lopresti

A Model-Based Ruling Line Detection Algorithm for Noisy Handwritten

Documents 404

Jin Chen and Daniel Lopresti

An On-line Arabic Handwriting Recognition System: Based on a New On-line

Graphemes Segmentation Technique 409

Hesham M. Eraqi and Sherif Abdel Azeem

Keynote Speech 1

Document Recognition without Strong Models 414

Henry S. Baird

Text Extraction (1)Detection and Segmentation of Antialiased Text in Screen Images 424

Sivan Gleichman, Boaz Ophir, Amir Geva, Mattias Marder, Ella Barkan,

and Eli Packer

AdaBoost for Text Detection in Natural Scene 429

Jung-Jin Lee, Pyoung-Hean Lee, Seong-Whan Lee, Alan Yuille, and Christof Koch

Dot Text Detection Based on FAST Points 435

Yuning Du, Haizhou Ai, and Shihong Lao

Text Detection and Character Recognition in Scene Images with Unsupervised

Feature Learning 440

Adam Coates, Blake Carpenter, Carl Case, Sanjeev Satheesh, Bipin Surest),

Tao Wang, David J. Wu, and Andrew Y. Ng

Mathematics Recognition

Math Spotting: Retrieving Math in Technical Documents Using Handwritten

Query Images 446

Richard Zanibbi and Li Yu

HAMEX - A Handwritten and Audio Dataset of Mathematical Expressions 452

Solen Quiniou, Harold Mouchere, Sebastian Pen Saldarriaga,

Christian Viard-Gaudin, Emmanuel Morin, Simon Petitrenaud,

and Sofiane Medjkoune

HMM-Based Recognition of Online Handwritten Mathematical Symbols Using

Segmental K-Means Initialization and a Modified Pen-Up/Down Feature 457

Lei Hu and Richard Zanibbi

Comparing Approaches to Mathematical Document Analysis from PDF 463

Josef B. Baker, Alan P. Sexton, Volker Sorge, and Masakazu Suzuki

Applications (1)

Preservative License Plate De-identification for Privacy Protection 468

Liang Du and Haibin Ling

Evaluation of Voting with Form Dropout Techniques for Ballot Vote Counting 473

Elisa H. Barney Smith, Shatakshi Goyal, Robbie Scott, and Daniel Lopresti

Conversion of PDF Books in ePub Format 478

Simone Marinai, Emanuele Marino, and Giovanni Soda

Handwritten Street Name Recognition for Indian Postal Automation 483

Umapada Pal, Ramit Kumar Roy, and Fumitaka Kimura

Layout Analysis

Table Content Understanding in SmartFIX 488

Florian Deckert, Benjamin Seidler, Markus Ebbecke, and Michael Gillmann

Continuous CRF with Multi-scale Quantization Feature Functions Application

to Structure Extraction in Old Newspaper 493

David Hebert, Thierry Paquet, and Stephane Nicolas

Classifying Textual Components of Bilingual Documents with Decision-Tree

Support Vector Machines 498

Xiao-Rong Lin, Chien-Yang Guo, and Fu Chang

Iterative Analysis of Pages in Document Collections for Efficient User

Interaction 503

Joseph Chazalon, Bertrand Couasnon, and Aurelie Lemaitre

Layout Analysis for Historical Manuscripts Using Sift Features 508

Angelika Garz, Robert Sablatnig, and Markus Diem

Handwritten Text RecognitionJoint Optimization of Hidden Conditional Random Fields and Non Linear

Feature Extraction 513

Antoine Vinel, Trinh Minh Tri Do, and Thierry Artieres

Improving Handwritten Chinese Text Recognition by Confidence

Transformation 518

Qiu-Feng Wang, Fei Yin, and Cheng-Lin Liu

Concurrent Optimization of Context Clustering and GMM for Offline

Handwritten Word Recognition Using HMM 523

Tomoyuki Hamamura, Bunpei trie, Takuya Nishimoto, Nobutaka Ono,

and Shigeki Sagayama

Dempster-Shafer Based Rejection Strategy for Handwritten Word Recognition 528

Thomas Burger, Yousri Kessentini, and Thierry Paquet

Handwritten Text Recognition for Marriage Register Books 533

Veronica Romero, Joan Andreu Sanchez, Nicolas Serrano, and Enrique Vidal

Character Recognition (1)Limits on the Application of Frequency-Based Language Models to OCR 538

Ray Smith

An Impact of OCR Errors on Automated Classification of OCR Japanese Texts

with Parts-of-Speech Analysis •543

Akihiro Kokawa, Lazaro S.P. Busagala, Wataru Ohyama,

Tetsushi Wakabayashi, and Fumitaka Kimura

Recognizing Characters with Severe Perspective Distortion Using Hash

Tables and Perspective Invariants 548

Pan Pan, Yuanping Zhu, Jun Sun, and Satoshi Naoi

An Automatic Method for Enhancing Character Recognition in DegradedHistorical Documents 553

Gabriel Pereira e Silva and Rafael Dueire Lins

Discriminative Bernoulli Mixture Models for Handwritten Digit Recognition 558

Adria Gimenez, J. Andres-Ferrer, Alfons Juan, and Nicolas Serrano

Document Segmentation

Language-Independent Text Lines Extraction Using Seam Carving 563

Raid Saabni and Jihad El-Sana

Template Based Segmentation of Touching Components in Handwritten Text

Lines 569

Le Kang and David Doermann

Graph Clustering-Based Ensemble Method for Handwritten Text Line

Segmentation 574

Vasant Manohar, Shiv N. Vitaladevuni, Huaigu Cao, Rohit Prasad,

and Prem Natarajan

Text-Line Extraction Using a Convolution of Isotropic Gaussian Filter with

a Set of Line Filters 579

Syed Saqib Bukhari, Faisal Shafait, and Thomas M. Breuel

Fast Rule-Line Removal Using Integral Images and Support Vector Machines 584

Jayant Kumar and David Doermann

Online Handwriting RecognitionA Generative Model for Handwritings Based on Enhanced Feature

Desynchronization 589

Seiichi Uchida, Toru Sasaki, and Feng Yaokai

Objective Function Design for MCE-Based Combination of On-line and Off-line

Character Recognizers for On-line Handwritten Japanese Text Recognition 594

Bilan Zhu, JinFeng Gao, and Masaki Nakagawa

A Weighted Finite-State Transducer (WFST)-Based Language Model

for Online Indie Script Handwriting Recognition 599

Suhan Chowdhury, Utpal Garain, and Tanushyam Chattopadhyay

Handwritten Street Name Recognition for Indian Postal Automation 483

Umapada Pal, Ramit Kumar Roy, and Fumitaka Kimura

Layout Analysis

Table Content Understanding in SmartFIX 488

Florian Deckert, Benjamin Seidler, Markus Ebbecke, and Michael Gillmann

Continuous CRF with Multi-scale Quantization Feature Functions Application

to Structure Extraction in Old Newspaper 493

David Hebert, Thierry Paquet, and Stephane Nicolas

Classifying Textual Components of Bilingual Documents with Decision-Tree

Support Vector Machines 498

Xiao-Rong Lin, Chien-Yang Guo, and Fu Chang

Iterative Analysis of Pages in Document Collections for Efficient User

Interaction 503

Joseph Chazalon, Bertrand Coiiasnon, and Aurelie Lemaitre

Layout Analysis for Historical Manuscripts Using Sift Features 508

Angelika Garz, Robert Sablatnig, and Markus Diem

Handwritten Text Recognition

Joint Optimization of Hidden Conditional Random Fields and Non Linear

Feature Extraction 513

Antoine Vinel, Trinh Minh Tri Do, and Thierry Artieres

Improving Handwritten Chinese Text Recognition by Confidence

Transformation 518

Qiu-Feng Wang, Fei Yin, and Cheng-Lin Liu

Concurrent Optimization of Context Clustering and GMM for Offline

Handwritten Word Recognition Using HMM 523

Tomoyuki Hamamura, Bunpei trie, Takuya Nishimoto, Nobutaka Ono,

and Shigeki Sagayama

Dempster-Shafer Based Rejection Strategy for Handwritten Word Recognition 528

Thomas Burger, Yousri Kessentini, and Thierry Paquet

Handwritten Text Recognition for Marriage Register Books 533

Veronica Romero, Joan Andreu Sanchez, Nicolas Serrano, and Enrique Vidal

Character Recognition (1)

Limits on the Application of Frequency-Based Language Models to OCR 538

Ray Smith

An Impact of OCR Errors on Automated Classification of OCR Japanese Texts

with Parts-of-Speech Analysis 543

Akihiro Kokawa, Lazaro S.P. Busagala, Wataru Ohyama,Tetsushi Wakabayashi, and Fumitaka Kimura

Recognizing Characters with Severe Perspective Distortion Using Hash

Tables and Perspective Invariants 548

Pan Pan, Yuanping Zhu, Jun Sun, and Satoshi Naoi

An Automatic Method for Enhancing Character Recognition in DegradedHistorical Documents 553

Gabriel Pereira e Silva and Rafael Dueire Lins

Discriminative Bernoulli Mixture Models for Handwritten Digit Recognition 558

Adria Gimenez, J. Andres-Ferrer, Alfons Juan, and Nicolas Serrano

Document Segmentation

Language-Independent Text Lines Extraction Using Seam Carving 563

Raid Saabni and Jihad El-Sana

Template Based Segmentation of Touching Components in Handwritten Text

Lines 569

Le Kang and David Doermann

Graph Clustering-Based Ensemble Method for Handwritten Text Line

Segmentation 574

Vasant Manohar, Shiv N. Vitaladevuni, Huaigu Cao, Rohit Prasad,

and Prem Natarajan

Text-Line Extraction Using a Convolution of Isotropic Gaussian Filter with

a Set of Line Filters 579

Syed Saqib Bukhari, Faisal Shafait, and Thomas M. Breuel

Fast Rule-Line Removal Using Integral Images and Support Vector Machines 584

Jayant Kumar and David Doermann

Online Handwriting RecognitionA Generative Model for Handwritings Based on Enhanced Feature

Desynchronization 589

Seiichi Uchida, Toru Sasaki, and Feng Yaokai

Objective Function Design for MCE-Based Combination of On-line and Off-line

Character Recognizers for On-line Handwritten Japanese Text Recognition 594

Bilan Zhu, JinFeng Gao, and Masaki Nakagawa

A Weighted Finite-State Transducer (WFST)-Based Language Model

for Online Indie Script Handwriting Recognition 599

Suhan Chowdhury, Utpal Garain, and Tanushyam Chattopadhyay

On-line Handwritten Japanese Characters Recognition Using a MRF Model

with Parameter Optimization by CRF 603

Bilan Zhu and Masaki Nakagawa

Symbol Knowledge Extraction from a Simple Graphical Language 608

Jinpeng Li, Harold Mouchere, and Christian Viard-Gaudin

Forensic Document Analysis

Segmentation and Normalisation in Grapheme Codebooks 613

Tara Gilliam, Richard C. Wilson, and John A. Clark

Evaluating the Rarity of Handwriting Formations 618

SargurN. Srihari

Multi-fractal Modeling for On-line Text-Independent Writer Identification 623

Aymen Chaabouni, Houcine Boubaker, Monji Kherallah, Adel M. Alimi,

and Haikal ElAbed

Writer Retrieval - Exploration of a Novel Biometric Scenario Using Perceptual

Features Derived from Script Orientation 628

Vlad Atanasiu, Laurence Likforman-Sulem, and Nicole Vincent

Quality Analysis of Dynamic Signature Based on the Sigma-Lognormal Model 633

Javier Galbally, Julian Fierrez, Marcos Martinez-Diaz, and Rejean Plamondon

Poster Session 2

An Improved Method Based on Weighted Grid Micro-structure Feature

for Text-Independent Writer Recognition 638

LuXu, Xiaoqing Ding, Liangrui Peng, and Xin Li

A Multi-scale Text Line Segmentation Method in Freestyle Handwritten

Documents 643

Yangdong Gao, Xiaoqing Ding, and Changsong Liu

Digit/Symbol Pruning and Verification for Arabic Handwritten Digit/Symbol

Spotting 648

Nicola Nobile, Chun Lei He, Malik Waqas Sagheer, Louisa Lam, and Ching Y. Suen

Modified Two-Class LDA Based Compound Distance for Similar Handwritten

Chinese Characters Discrimination 653

Yunxue Shao, Chunheng Wang, Baihua Xiao, Rongguo Zhang, and Linbo Zhang

Error Correction with !n-domain Training across Multiple OCR System Outputs 658

William B. Lund and Eric K. Ringger

Effects of Generating a Large Amount of Artificial Patterns for On-line

Handwritten Japanese Character Recognition 663

Bin Chen, Bilan Zhu, and Masaki Nakagawa

A Novel Short Merged Off-line Handwritten Chinese Character StringSegmentation Algorithm Using Hidden Markov Model 668

Zhiwei Jiang, Xiaoqing Ding, Changsong Liu, and Yanwei Wang

Binarization of Textual Content in Video Frames 673

Konstantinos Ntirogiannis, Basilis Gatos, and loannis Pratikakis

Word Retrieval in Historical Document Using Character-Primitives 678

Partha Pratim Roy, Jean-Yves Ramel, and Nicolas Ragot

An On-line Handwritten Text Search Method Based on Directional Feature

Matching 683

Pasitthideth Luangvilay, Bilan Zhu, and Masaki Nakagawa

Text Localization in Real-World Images Using Efficiently Pruned Exhaustive

Search 687

Lukas Neumann and Jifi Matas

Classical Mongolian Words Recognition in Historical Document 692

Guanglai Gao, Xiangdong Su, Hongxi Wei, and Yeyun Gong

A Novel Italic Detection and Rectification Method for Chinese Advertising

Images 698

Jie Liu, Heping Li, Shuwu Zhang, and Wei Liang

Minimizing User Annotations in the Generation of Layout Ground-Truthed Data 703

Karim Hadjar and Rolflngold

An Improved Scene Text Extraction Method Using Conditional Random Field

and Optical Character Recognition 708

Hongwei Zhang, Changsong Liu, Cheng Yang, Xiaoqing Ding, and KongQiao Wang

Identification of Indie Scripts on Tom-Documents 713

Sukalpa Chanda, Katrin Franke, and Umapada Pal

A Contour-Based Method for Logo Detection 718

The Anh Pham, Mathieu Delalandre, and Sabine Barrat

A Contour-Based Progressive Technique for Shape Recognition 723

Stefano Ferilli, Teresa M.A. Basile, Floriana Esposito, and Marenglen Biba

Localization of Digit Strings in Farsi/Arabic Document Images Using Structural

Features and Syntactical Analysis 728

Ali Abedi and Karim Faez

Text/Graphics Segmentation in Architectural Floor Plans 734

Sheraz Ahmed, Markus Weber, Marcus Liwicki, and Andreas Dengel

OCR-Driven Writer Identification and Adaptation in an HMM Handwriting

Recognition System 739

Huaigu Cao, Rohit Prasad, and Prem Natarajan

Handwritten and Typewritten Text Identification and Recognition Using Hidden

Markov Models 744

Huaigu Cao, Rohit Prasad, and Prem Natarajan

Metadata Extraction System for Chinese Books 749

Liangcai Gao, Yuan Zhong, Yingmin Tang, Zhi Tang, Xiaofan Lin, and Xuan Hu

A Fast Alignment Scheme for Automatic OCR Evaluation of Books 754

Ismet Zeki Yalniz and R. Manmatha