2011 International Conference

on Document Analysisand Recognition

(ICDAR 2011)

Beijing, China

18 - 21 September 2011

Pages 759-1525

#IEEE IEEE Catalog Number: CFP11227-PRT

ISBN: 978-1-4577-1350-7

Improving Scene Text Detection by Scale-Adaptive Segmentation

and Weighted CRF Verification 759

Yi-Feng Pan, Yuanping Zhu, Jun Sun, and Satoshi Naoi

Progressive Alignment and Discriminative Error Correction for Multiple OCR

Engines •. 764

William B. Lund, Daniel D. Walker, and Eric K. Ringger

Offline Writer Identification Using K-Adjacent Segments 769

Rajiv Jain and David Doermann

Binarizing the Courtesy Amount Field on Color Chinese Bank Check Images 774

Dong Liu and Youbin Chen

A Table Detection Method for Multipage PDF Documents via Visual

Seperators and Tabular Structures 779

Jing Fang, Liangcai Gao, Kun 6a/, Ruiheng Qiu, Xin Tao, and Zhi Tang

Look Inside the World of Parts of Handwritten Characters 784

Wang Song, Seiichi Uchida, and Marcus Liwicki

Chinese Keyword Spotting Using Knowledge-Based Clustering 789

Yong Xia, Kuanquan Wang, and Mingwei Li

Text Segmentation of Consumer Magazines in PDF Format 794

Jian Fan

On-line Chinese Character Recognition System for Overlapping Samples 799

Xiang Wan, Changsong Liu, and Yanming Zou

On-line Signature Verification Using Segment-to-Segment Graph Matching 804

Kaiyue Wang, Yunhong Wang, and Zhaoxiang Zhang

Snap and Translate Using Windows Phone : 809

Jun Du, Qiang Huo, Lei Sun, and Jian Sun

Comparative Study of Part-Based Handwritten Character RecognitionMethods '. 814

Wang Song, Seiichi Uchida, and Marcus Liwicki

A Keypoint-Based Approach toward Scenery Character Detection 819

Seiichi Uchida, Yuki Shigeyoshi, Yasuhiro Kunishige, and Feng Yaokai

Three Dimensional Rotation-Free Recognition of Characters 824

Ryo Narita, Wataru Ohyama, Tetsushi Wakabayashi, and Fumitaka Kimura

A Novel Approach for Graphics Recognition Based on Galois Lattice and Bag

of Words Representation 829

Amani Boumaiza and Salvatore Tabbone

Effects of Line Densities on Nonlinear Normalization for Online Handwritten

Japanese Character Recognition , 834

Truyen Van Phan, JinFeng Gao, Bilan Zhu, and Masaki Nakagawa

Super-Resolved Binarization of Text Based on the FAIR Algorithm 839

Thibault Lelore and Frederic Bouchara

Writer Identification Using TF-IDF for Cursive Handwritten Word Recognition 844

Quang Ann Bui, Muriel Visani, Sophea Prum, and Jean-Marc Ogier

Creation and Analysis of a Corpus of Text Rich Indian TV Videos 849

T, Chattopadhyay, Soumik Sengupta, Aniruddha Sinha, and Nisha Rampuria

Text Classification and Document Layout Analysis of Paper Fragments 854

Markus Diem, Florian Kleber, and Robert Sablatnig

Touching Character Separation in Chinese Handwriting Using Visibility-Based

Foreground Analysis 859

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

Improved Automatic Analysis of Architectural Floor Plans 864

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

Subgraph Spotting through Explicit Graph Embedding: An Application

to Content Spotting in Graphic Document Images 870

Muhammad Muzzamil Luqman, Jean-Yves Ramel, Josep Llados,

and Thierry Brouard

Exploiting Collection Level for Improving Assisted Handwritten Word

Transcription of Historical Documents 875

Laurent Guichard, Joseph Chazalon, and Bertrand Couasnon

Embedding a Mathematical OCR Module into OCRopus 880

Shinpei Yamazaki, Fumihiro Furukori, Qinzheng Zhao, Keiichiro Shirai,

and Masayuki Okamoto

Handwriting Character Recognition as a Service: A New Handwriting

Recognition System Based on Cloud Computing 885

Yan Gao, Lanwen Jin, Cong He, and Guibin Zhou

Page Curling Correction for Scanned Books Using Local Distortion Information 890

Vladimir Kluzner and Asaf Tzadok

Image Enhancement for Degraded Binary Document Images 895

Zhixin Shi, Srirangaraj Setlur, and Venu Govindaraju

Hybrid Approach to Adaptive OCR for Historical Books 900

Vladimir Kluzner, Asaf Tzadok, Dan Chevion, and Eugene Walach

Restoration of Arbitrarily Warped Historical Document Images Using Flow

Lines 905

Maryam Rahnemoonfar and Apostolos Antonacopoulos

Towards Improving the Accuracy of Telugu OCR Systems 910

P. Pavan Kumar, Chakravarthy Bhagvati, Atul Negi, Arun Agarwal,and B. L. Deekshatulu

Correcting Specular Noise in Multiple Images of Photographed Documents 915

Ednardo Mariano, Rafael Dueire Lins, Gabriel de Franga Pereira e Silva,

Jian Fan, Peter Majewicz, and Marcelo Thielo

A Study on Automatic Chinese Text Classification 920

XI Luo, Wataru Ohyama, Tetsushi Wakabayashi, and Fumitaka Kimura

A New System for Recognition of Handwritten Persian Bank Checks 925

Javad Sadri, Younes Akbari, Mohammad J. Jalili, Ahmad Farahi,

and Maliheh Habibi

Dynamic Text Line Segmentation for Real-Time Recognition of Chinese

Handwritten Sentences 931

Da-Han Wang and Cheng-Lin Liu

Character Enhancement for Historical Newspapers Printed Using Hot Metal

Typesetting 936

luliu Konya, Stefan Eickeler, and Christoph Seibert

Character n-Gram Spotting in Document Images 941

M. Sudha Praveen, K. Pramod Sankar, and C. V. Jawahar

Use of Semantic and Physical Constraints in Bayesian Networks for Form

Recognition 946

Phiiippot Emilie, Bela'id Yolande, and Belaid Abdel

Keynote Speech 2

Chinese Paleography, Calligraphy, and Pattern Recognition: Styles

and Scripts in Excavated Ancient Chinese Documents 951

Xing Wen

Applications (2)MCS for Online Mode Detection: Evaluation on Pen-Enabled Multi-touch

Interfaces 957

Markus Weber, Marcus Liwicki, Yannik T. H. Schelske, Christopher Schoelzel,

Florian StrauR, and Andreas Dengel

Discovering Legible Chinese Typefaces for Reading Digital Documents 962

Bing Zhang, Ying Li, Ching Y, Suen, and Xuemin Zhang

Detecting Figure-Panel Labels in Medical Journal Articles Using MRF 967

Daekeun You, SameerAntani, Dina Demner-Fushman, Venu Govindaraju,

and George R. Thoma

A New Method on the Segmentation and Recognition of Chinese Characters

for Automatic Chinese Seal Imprint Retrieval 972

Chao Ren, Dong Liu, and Youbin Chen

Graphics Recognition

CalliGUI: Interactive Labeling of Calligraphic Character Images 977

George Nagy and Xiafen Zhang

Symbol Spotting in Line Drawings through Graph Paths Hashing 982

Anjan Dutta, Josep Lladds, and Umapada Pal

A Non-rigid Feature Extraction Method for Shape Recognition 987

Jon Almazan, Alicia Fornes, and Ernest Valveny

Low Resolution QR-Code Recognition by Applying Super-Resolution Using

the Property of QR-Codes 992

Yuji Kato, Daisuke Deguchi, Tomokazu Takahashi, Ichiro Ide, and Hiroshi Murase

Character Recognition (2)

Tuning between Exponential Functions and Zones for Membership Functions

Selection in Voronoi-Based Zoning for Handwritten Character Recognition 997

S. Impedovo and G. Pirlo

Multiple Instance Learning Based Method for Similar Handwritten Chinese

Characters Discrimination 1002

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

Perceptron Learning of Modified Quadratic Discriminant Function 1007

Tong-Hua Su, Cheng-Lin Liu, and Xu-Yao Zhang

Similar Handwritten Chinese Character Recognition Using Discriminative

Locality Alignment Manifold Learning 1012

Dapeng Tao, Lingyu Liang, Lianwen Jin, and Yan Gao

Keynote Speech 3

The Four and a Half Challenges of Humanities Data 1017

Marc Wilhelm Kuster

Text Extraction (2)A Gradient Vector Flow-Based Method for Video Character Segmentation 1024

Trung Quy Phan, Palaiahnakote Shivakumara, Bolan Su, and Chew Lim Tan

Text Extraction from Video Using Conditional Random Fields 1029

Xujun Peng, Huaigu Cao, Rohit Prasad, and Premkumar Natarajan

Scene Text Extraction by Superpixel CRFs Combining Multiple Character

Features 1034

Min Su Cho, Jae-Hyun Seok, Seonghun Lee, and Jin Hyung Kim

Bayesian Approach to Photo Time-Stamp Recognition 1039

AsifShahab, Faisal Shafait, and Andreas Dengel

A Chinese Character Localization Method Based on Intergrating Structure

and CC-Clustering for Advertising Images 1044

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

Scenery Character Detection with Environmental Context 1049

Yasuhiro Kunishige, Feng Yaokai, and Seiichi Uchida

Document Retrieval (2)

Real-Time Document Image Retrieval for a 10 Million Pages Database with

a Memory Efficient and Stability Improved LLAH 1054

Kazutaka Takeda, Koichi Kise, and Masakazu Iwamura

Document Image Classification and Labeling Using Multiple Instance Learning 1059

Jayant Kumar, Jaishanker Pillai, and David Doermann

A Lattice-Based Method for Keyword Spotting in Online Chinese Handwriting 1064

Heng Zhang and Cheng-Lin Liu

A Graph Lattice Approach to Maintaining Dense Collections of Subgraphs

as Image Features 1069

Eric Saund

Similar Manga Retrieval Using Visual Vocabulary Based on Regions

of Interest 1075

Weihan Sun and Koichi Kise

Case Study in Hebrew Character Searching 1080

Irina Rabaev, OferBilier, Jihad El-Sana, Klara Kedem, and Itshak Dinstein

Character Recognition (3)Multiscale Histogram of Oriented Gradient Descriptors for Robust Character

Recognition 1085

Andrew J. Newell and Lewis D. Griffin

A Coarse Classifier Construction Method from a Large Number of Basic

Recognizers for On-line Recognition of Handwritten Japanese Characters 1090

Bilan Zhu and Masaki Nakagawa

Affine-lnvariant Recognition of Handwritten Characters via Accelerated KL

Divergence Minimization 1095

Torn Wakahara and Yukihiko Yamashita

MQDF Discriminative Learning Based Offline Handwritten Chinese Character

Recognition 1100

Yanwei Wang, Xiaoqing Ding, and Changsong Liu

A Semi-supervised SVM Framework for Character Recognition 1105

AmitArora and Anoop M. Namboodiri

Efficient Word Recognition Using a Pixel-Based Dissimilarity Measure 1110

Sebastian Colutto and Basilis Gatos

Poster Session 3

A Compression Scheme for Handwritten Patterns Based on Curve Fitting 1115

Kama! Gupta, Manish Bansal, and Santanu Chaudhury

Edge-Based Features for Localization of Artificial Urdu Text in Video Images 1120

AkhtarJamil, Imran Siddiqi, FahimArif, andAhsen Raza

Stamp Detection in Color Document Images 1125

Barbora Micenkova and Joost van Beusekom

Trie-Lexicon-Driven Recognition for On-line Handwritten Japanese Disease

Names Using a Time-Synchronous Method 1130

Bilan Zhu and Masaki Nakagawa

Convolutional Neural Network Committees for Handwritten Character

Classification 1135

Dan Claudiu Cire§an, Ueli Meier, Luca Maria Gambardella,

and Jurgen Schmidhuber

Semantic Logging: Towards Explanation-Aware DAS 1140

Bjdrn Forcher, Stefan Agne, Andreas Dengel, Michael Gillmann,

and Thomas Roth-Berghofer

A Novel Preprocessing Method for Hectography Prints Based on Independent

Component Analysis 1145

Thomas Kurbiel, luliu Konya, and Stefan Eickeler

An Empirical Evaluation on HIT-OR3C Database 1150

Shusen Zhou, Qingcai Chen, Xiaolong Wang, Xinyi Guo, and Hui Li

Greek Poiytonic OCR Based on Efficient Character Class Number Reduction 1155

B. Gatos, G. Louloudis, and N. Stamatopoulos

Adaptive Zoning Features for Character and Word Recognition 1160

B. Gatos, A. L. Kesidis, and A. Papandreou

A New Fourier-Moments Based Video Word and Character Extraction Method

for Recognition 1165

Deepak Rajendran, Palaiahnakote Shivakumara, Bolan Su, Shijian Lu,

and Chew Lim Tan

Signature Segmentation from Machine Printed Documents Using Conditional

Random Field 1170

Ranju Mandal, Partha Pratim Roy, and Umapada Pal

Lexicon-Free, Novel Segmentation of Online Handwritten Indie Words 1175

Suresh Sundaram andA. G. Ramakrishan

Scale Space Binarization Using Edge Information Weighted by a Foreground

Estimation 1180

Florian Kleber, Markus Diem, and Robert Sablatnig

Multi Resolution Layout Analysis of Medieval Manuscripts Using Dynamic MLP 1185

Micheal Baechler and Rolflngold

Document Images Indexing with Relevance Feedback: An Application

to Industrial Context 1190

O. Augereau, N. Journet, and J.-P. Domenger

Interactive Competitive Breadth-First Exploration for Sketch Interpretation 1195

Achraf Ghorbel, Sebastien Mace, Aurelie Lemaitre, and Eric Anquetil

Document Image Indexing Using Edit Distance Based Hashing 1200

Ehtesham Hassan, Santanu Chaudhury, and M. Gopal

New Binarization Approach Based on Text Block Extraction 1205

Ines Ben Messaoud, Hamid Amiri, Haikal El Abed, and Volker Margner

Searching OCR'ed Text: An LDA Based Approach 1210

Ehtesham Hassan, Vikram Garg, S. K. Mirajul Haque, Santanu Chaudhury,

and M. Gopal

A CRF Based Scheme for Overlapping Multi-colored Text Graphics Separation 1215

Ritu Garg, Ehtesham Hassan, Santanu Chaudhury, and M. Gopal

Fuzzy Relative Positioning Templates for Symbol Recognition 1220

Adrien Delaye and Eric Anquetil

Recognition of Printed Mathematical Expressions Using Two-Dimensional

Stochastic Context-Free Grammars 1225

Francisco Alvaro, Joan-Andreu Sanchez, and Jose-Miguel Benedi

Document Recto-verso Registration Using a Dynamic Time Warping Algorithm 1230

Rabeux Vincent, Journet Nicholas, and Domenger Jean Philippe

Automatic Content Extraction on Semi-structured Documents 1235

Jose Eduardo Bastos dos Santos

Video Script Identification Based on Text Lines 1240

Trung Quy Phan, Palaiahnakote Shivakumara, Zhang Ding, Shijian Lu,

and Chew Lim Tan

Extending Page Segmentation Algorithms for Mixed-Layout Document

Processing 1245

Amy Winder, Tim Andersen, and Elisa H. Barney Smith

Better Digit Recognition with a Committee of Simple Neural Nets 1250

Ueli Meier, Dan Claudiu Ciresan, Luca Maria Gambardella,

and Jurgen Schmidhuber

Towards Improved Paper-Based Election Technology 1255

Elisa H. Barney Smith, Daniel Lopresti, George Nagy, and Ziyan Wu

An Evaluation of HMM-Based Techniques for the Recognition of Screen

Rendered Text 1260

Sheikh Faisal Rashid, Faisal Shafait, and Thomas M. Breuel

A System for an Automatic Reading of Student Information Sheets 1265

AfefKacem, Asma Sa'idani, and Abdel Belaid

Wall Patch-Based Segmentation in Architectural Floorplans 1270

Lluis-Pere de las Heras, Joan Mas, Gemma Sanchez, and Ernest Valveny

High Performance Layout Analysis of Arabic and Urdu Document Images 1275

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

Automatically Discriminating between Digital and Scanned Photographs 1280

Rafael Dueire Lins, Gabriel de Franga Pereira e Silva, and Steven J. Simske

A Discriminative Model for On-iine Handwritten Japanese Text Retrieval 1285

Cheng Cheng, Bilan Zhu, and Masaki Nakagawa

A Circular Grid-Based Rotation Invariant Feature Extraction Approachfor Off-line Signature Verification 1289

Marianela Parodi, Juan C. Gomez, and Abdel Bela'id

Fringe Map Based Text Line Segmentation of Printed Telugu Document

Images 1294

Vijaya Kumar Koppula and Atul Negi

Combining of Off-line and On-line Feature Extraction Approaches for Writer

Identification 1299

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

and Haikal El Abed

On-line Arabic Handwritten Personal Names Recognition System Based

on HMM 1304

Sherif Abdelazeem and Hesham M. Eraqi

Using Earth Mover's Distance in the Bag-of-Visual-Words Model

for Mathematical Symbol Retrieval 1309

Simone Marinai, Beatrice Miotti, and Giovanni Soda

Enhancing Handwritten Word Segmentation by Employing Local SpatialFeatures 1314

Fotini Simistira, Vassilis Papavassiliou, Themos Stafylakis, and Vassilis Katsouros

Symbol Recognition by Multiresolution Shape Context Matching 1319

Feng Su, Jong Lu, and Ruoyu Yang

On-line Arabic Handwriting Recognition System Based on HMM 1324

Hany Ahmed and SherifAbdel Azeem

Recognizing Text Elements for SVG Comic Compression and Its Novel

Applications 1329

Chung-Yuan Su, Ray-I Chang, and Jen-Chang Liu

Facilitating Understanding of Large Document Collections 1334

Jae Hyeon Bae, Weijia Xu, and Maria Esteva

Translation-Inspired OCR 1339

Dmitriy Genzel, Ashok C. Popat, Nemanja Spasojevic, Michael Jahr,

Andrew Senior, Eugene le, and Frank Yung-Fong Tang

Towards Searchable Digital Urdu Libraries - A Word Spotting Based Retrieval

Approach 1344

AHAbidi, Imran Siddiqi, and Khurram Khurshid

Word Warping for Offline Handwriting Recognition 1349

Douglas J. Kennard, William A. Barrett, and Thomas W. Sederberg

Script-Free Text Line Segmentation Using Interline Space Model for Printed

Document Images 1354

Minwoo Kim and ll-Seok Oh

Text Localization in Web Images Using Probabilistic Candidate Selection

Model 1359

Liangji Situ, Ruizhe Liu, and Chew Lim Tan

Functional-Based Table Category Identification in Digital Library 1364

Seongchan Kim and Ying Liu

Chinese Chess Character Recognition with Radial Harmonic Fourier Moments 1369

Wang Kejia, Zhang Honggang, Ping Ziliang, and Haiying

Non-rigid Registration and Restoration of Double-Sided Historical Manuscripts 1374

Jie Wang and Chew Lim Tan

A Fast Appearance-Based Full-Text Search Method for Historical NewspaperImages 1379

Kengo Terasawa, Takahiro Shima, and Toshio Kawashima

Reliable Online Stroke Recovery from Offline Data with the Data-EmbeddingPen

, 1384

Marcus Liwicki, Yoshida Akira, Seiichi Uchida, Masakazu Iwamura,

Shinichiro Omachi, and Koichi Kise

Online Handwriting Recognition of Tamil Script Using Fractal Geometry 1389

Rituraj Kunwar and A. G. Ramakrishnan

Connected Component Level Discrimination of Handwritten

and Machine-Printed Text Using Eigenfaces 1394

Samuel J. Pinson and William A. Barrett

Recognition of Multi-oriented, Multi-sized, and Curved Text 1399

Yao-Yi Chiang and Craig A. Knoblock

Scenario Driven In-depth Performance Evaluation of Document Layout

Analysis Methods 1404

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

Recognition of Multiple Characters in a Scene Image Using Arrangementof Local Features 1409

Masakazu Iwamura, Takuya Kobayashi, and Koichi Kise

Quality Evaluation of Character Image Database and Its Application 1414

Hiroyuki Hase

Mathematical Formula Identification in PDF Documents 1419

Xiaoyan Lin, Liangcai Gao, Zhi Tang, Xiaofan Lin, and Xuan Hu

Panel Discussion

Evaluation of Fonts for Digital Publishing and Display 1424

C. Y. Suen, N. Dumont, M. Dyson, Y.-C. Tai, andX. Lu

Competitions

International Conference on Document Analysis and Recognition (ICDAR

2011) - Competitions Overview 1437

Haikal El Abed, Liu Wenyin, and Volker Margner

ICDAR 2011 - Arabic Handwriting Recognition Competition 1444

Volker Margner and Haikal El Abed

ICDAR 2011 - Arabic Recognition Competition: Multi-font Multi-size Digitally

Represented Text 1449

Fouad Slimane, Slim Kanoun, Haikal El Abed, Adel M. Alimi, Rolf Ingold,

and Jean Hennebert

Online Arabic Handwriting Recognition Competition 1454

Monjl Kherallah, Najiba Tagougui, Adel M. Alimi, Haikal El Abed,

and Volker Margner

ICDAR 2011 - French Handwriting Recognition Competition 1459

Emmanuele Grosicki and Haikal El-Abed

ICDAR 2011 Chinese Handwriting Recognition Competition 1464

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

The ICDAR2011 Arabic Writer Identification Contest 1470

Abdelaali Hassa'fne, Somaya Al-Maadeed, Jihad Mohamad Alja'am, AH Jaoua,

and Ahmed Bouridane

ICDAR 2011 Writer Identification Contest 1475

G. Louloudis, N. Stamatopoulos, and B. Gatos

Signature Verification Competition for Online and Offline Skilled Forgeries

(SigComp2011) 1480

Marcus Liwicki, Muhammad /mran Malik, C. Eli'sa van den Heuvel,

Xiaohong Chen, Charles Berger, Reinoud Stoel, Michael Blumenstein,

and Bryan Found

ICDAR 2011 Robust Reading Competition - Challenge 1: Reading Text

in Born-Digital Images (Web and Email) 1485

D. Karatzas, S, Robles Mestre, J. Mas, F. Nourbakhsh, and P. Pratim Roy

ICDAR 2011 Robust Reading Competition Challenge 2: Reading Text

in Scene Images 1491

AsifShahab, Faisal Shafait, and Andreas Dengel

CROHME2011: Competition on Recognition of Online Handwritten

Mathematical Expressions 1497

Harold Mouchere, Christian Viard-Gaudin, Dae Hwan Kim, Jin Hyung Kim,

and Utpal Garain

ICDAR 2011 Book Structure Extraction Competition 1501

Antoine Doucet, Gabriella Kazai, and Jean-Luc Meunier

ICDAR 2011 Document Image Binarization Contest (DIBCO 2011) 1506

loannis Pratikakis, Basilis Gatos, and Konstantinos Ntirogiannis

The ICDAR 2011 Music Scores Competition: Staff Removal and Writer

Identification 1511

Alicia Fornes, Anjan Dutta, Albert Gordo, and Josep Llados

Historical Document Layout Analysis Competition 1516

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

Document Analysis Algorithm Contributions in End-to-End Applications:

Report on the ICDAR 2011 Contest 1521

Bart Lamiroy, Daniel Lopresti, and Tao Sun