The Eighth IAPR International Workshop on Document Analysis Systems (DAS2008)

September 16-19, 2008
Nara Prefectural New Public Hall, Nara, Japan


Registration Desk

The registration desk will be open during the following hours:

Tuesday, September 16 12:00—19:00
Wednesday, September 17 8:30—17:30
Thursday, September 18 8:30—14:30
Friday, September 19 8:30—16:00


Tuesday, September 16
13:00—15:00 Tutorial 1
Prof. Dr. Thomas Breuel:
"Statistical and Adaptive OCR—a Hands-On Tutorial with OCRopus"
Room Yuri
("Hotel Nikko Nara" 5F)
15:00—15:30 Break
15:30—17:30 Tutorial 2
Prof. Apostolos Antonacopoulos:
"Unlocking the World's Knowledge: The Analysis of Historical Documents"
Room Yuri
("Hotel Nikko Nara" 5F)
17:30—18:00 Break
18:00—19:30 Welcome Reception Room Hiten
("Hotel Nikko Nara" 4F)

Wednesday, September 17
9:00—9:10 Opening Noh Theater
9:10—10:10 Keynote 1
Prof. Rangachar Kasturi:
"Extraction of Text Objects in Video Documents: Recent Progress"
Noh Theater
10:10—10:30 Break Noh Theater
10:30—11:50 Oral 1: Character Detection and Recognition Noh Theater
11:50—12:50 Lunch
12:50—14:10 Poster & Demo 1 Conference Room 1 & 2
14:10—14:40 Break
14:40—16:00 Oral 2: Layout Analysis and Super-Resolution Noh Theater
16:00—16:20 Break
16:20—17:40 Oral 3: Document Categorization and Indexing Noh Theater

Thursday, September 18
9:00—10:00 Keynote 2
Prof. Toshiro Kamiuchi:
"Digital Renaissance—Making Archives, Sharing Wisdoms and Creating Values"
Noh Theater
10:00—10:30 Break
10:30—11:50 Oral 4: Historical and Handwriting Documents Noh Theater
11:50—12:00 Grouping Noh Theater
12:00—13:00 Lunch
13:00—14:30 Discussion
Prof. Henry Baird
Meeting Room 1 & 2, Conference Room 4
14:30—15:20 Bus Transportation
15:20—17:00 Excursion Horyu-ji
17:00—17:40 Bus Transportation
17:40—19:00 Shower Break
19:00—21:30 Banquet Room Hiten
("Hotel Nikko Nara" 4F)

Friday, September 19
9:00—10:20 Oral 5: Document Analysis Systems Noh Theater
10:20—10:50 Break
10:50—12:10 Poster & Demo 2 Conference Room 1 & 2
12:10—13:10 Lunch
13:10—14:30 Oral 6: Document Image Processing and Enhancement Noh Theater
14:30—15:00 Break
15:00—15:50 Reports of Discussion Groups Noh Theater
15:50—16:00 Concluding Remarks Noh Theater

Oral Sessions

Oral 1: Character Detection and Recognition
10:30—11:50 / Wednesday, September 17
Chairs: Horst Bunke and Masayuki Okamoto
10:30—10:50 A Hilbert Warping Algorithm for Recognizing Characters from Moving Camera
Hiroyuki Ishida, Ichiro Ide, Hiroshi Murase, and Tomokazu Takahashi
10:50—11:10 Writer Verification of Arabic Handwriting
Sargur N. Srihari and Gregory R. Ball
11:10—11:30 A Robust System to Detect and Localize Texts in Natural Scene Images
Yi-Feng Pan, Xinwen Hou, and Cheng-Lin Liu
11:30—11:50 An Image Based Watermark String Detection System for Document Security Checking
Jun Sun, Yusaka Fujii, Hiroaki Takebe, Katsuhito Fujimoto, and Satoshi Naoi
Oral 2: Layout Analysis and Super-Resolution
14:40—16:00 / Wednesday, September 17
Chairs: Abdel Belaïd and Masakazu Iwamura
14:40—15:00 Feature Extraction for Document Image Segmentation by pLSA Model
Takuma Yamaguchi and Minoru Maruyama
15:00—15:20 Grouping Text Lines in Online Handwritten Japanese Documents by Combining Temporal and Spatial Information
Xiang-Dong Zhou, Da-Han Wang, and Cheng-Lin Liu
15:20—15:40 Accurate Alignment of Double-Sided Manuscripts for Bleed-Through Removal
Jie Wang, Michael S. Brown, and Chew Lim Tan
15:40—16:00 Super-Resolution of Text Images Using Edge-Directed Tangent Field
Jyotirmoy Banerjee and C.V. Jawahar
Oral 3: Document Categorization and Indexing
16:20—17:40 / Wednesday, September 17
Chairs: Daniel Lopresti and Seiichi Uchida
16:20—16:40 Attention-Based Document Classifier Learning
Georg Buscher and Andreas Dengel
16:40—17:00 Categorization of On-Line Handwritten Documents
Sebastián Peña Saldarriaga, Emmanuel Morin, and Christian Viard-Gaudin
17:00—17:20 Combining Multiple Methods for Book Indexing
Hervé Déjean and Jean-Luc Meunier
17:20—17:40 Automated OCR Ground Truth Generation
Joost van Beusekom, Faisal Shafait, and Thomas M. Breuel
Oral 4: Historical and Handwriting Documents
10:30—11:50 / Thursday, September 18
Chairs: Venugopal Govindaraju and Shinichiro Omachi
10:30—10:50 STATE: A Multimodal Assisted Text-Transcription System for Ancient Documents
Albert Gordo, David Llorens, Andrés Marzal, Federico Prat, and Juan Miguel Vilar
10:50—11:10 Authorship Identification of Ukiyoe by Using Rakkan Image
Shun Hirose, Mitsu Yoshimura, Kozaburo Hachimura, and Ryo Akama
11:10—11:30 Writer-Dependent Recognition of Handwritten Whiteboard Notes in Smart Meeting Room Environments
Marcus Liwicki, Andreas Schlapbach, and Horst Bunke
11:30—11:50 Shape Code Based Lexicon Reduction for Offline Handwritten Word Recognition
Roman Bertolami, Christoph Gutmann, Horst Bunke, and A. Lawrence Spitz
Oral 5: Document Analysis Systems
9:00—10:20 / Friday, September 19
Chairs: Andreas Dengel and Hisashi Ikeda
9:00—9:20 A Document Analysis System for Supporting Electronic Voting Research
Daniel Lopresti, George Nagy, and Elisa Barney Smith
9:20—9:40 An End-to-End Administrative Document Analysis System
Hatem Hamza, Yolande Belaïd, Abdel Belaïd, and Bidyut B.Chaudhuri
9:40—10:00 Re-Targetable OCR with Intelligent Character Segmentation
Mudit Agrawal and David Doermann
10:00—10:20 Symbol Descriptor Based on Shape Context and Vector Model of Information Retrieval
T.-O. Nguyen, S. Tabbone, O. Ramos Terrades
Oral 6: Document Image Processing and Enhancement
13:10—14:30 / Friday, September 19
Chairs: Simone Marinai and Shuji Senda
13:10—13:30 Skew Estimation by Instances
Seiichi Uchida, Megumi Sakai, Masakazu Iwamura, Shinichiro Omachi, and Koichi Kise
13:30—13:50 A Two-Step Dewarping of Camera Document Images
Nikolaos Stamatopoulos, Basilis Gatos, Ioannis Pratikakis, and Stavros J. Perantonis
13:50—14:10 An Objective Evaluation Methodology for Document Image Binarization Techniques
Konstantinos Ntirogiannis, Basilis Gatos, and Ioannis Pratikakis
14:10—14:30 Contrast Enhancement in Multispectral Images by Emphasizing Text Regions
Martin Lettner, Florian Kleber, Robert Sablatnig, and Heinz Miklas

Poster Sessions

Character Recognition
♠P1 Affine Invariant Recognition of Characters by Progressive Pruning
Akira Horimatsu, Ryo Niwa, Masakazu Iwamura, Koichi Kise, Seiichi Uchida, and Shinichiro Omachi
♥P2 Detecting Gradients in Text Images Using the Hough Transform
Dimosthenis Karatzas
♠P3 Multi-Font Rotated Character Recognition Using Periodicity
Hiroyuki Hase, Kohei Tanabe, Thi Hong Ha Tran, and Shogo Tokai
Character and Text Segmentation and Extraction
♥P4 Difference of Boxes Filters Revisited: Shadow Suppression and Efficient Character Segmentation
Erik Rodner, Herbert Süsse, Wolfgang Ortmann, and Joachim Denzler
♠P5 Segmentation of Curled Textlines Using Active Contours
Syed Saqib Bukhari, Faisal Shafait, and Thomas M. Breuel
♥P6 Kanji Character Detection from Complex Real Scene Images Based on Character Properties
Lianli Xu, Hiroto Nagayoshi, and Hiroshi Sako
♠P7 A Hybrid System for Text Detection in Video Frames
Marios Anthimopoulos, Basilis Gatos, and Ioannis Pratikakis
♥P8 A Study for High Performance Character Extraction from Color Scene Images
Keiichiro Shirai, Masanori Wakabayashi, Masayuki Okamoto, and Hiroaki Yamamoto
♠P9 Word Extraction Method by Generating Multiple Character Hypotheses
Hiroaki Takebe and Katsuhito Fujimoto
♥P10 An Efficient Edge Based Technique for Text Detection in Video Frames
Palaiahnakote Shivakumara, Weihua Huang, and Chew Lim Tan
♠P11 Multi-Oriented English Text Line Extraction Using Background and Foreground Information
Partha Pratim Roy, Umapada Pal, Josep Lladós, and Fumitaka Kimura
♥P12 Text String Extraction from Scene Image Based on Edge Feature and Morphology
Yuming Wang and Naoki Tanaka
♠P13 Accuracy Improvement and Objective Evaluation of Annotation Extraction from Printed Documents
Tomohiro Nakai, Kazumasa Iwata, and Koichi Kise
♥P14 Multi-Oriented Text Line Extraction from Handwritten Arabic Documents
Nazih Ouwayed and Abdel Belaid
♠P15 Writer Identification in Old Handwritten Music Scores
Alicia Fornés, Josep Lladós, Gemma Sánchez, and Horst Bunke
♥P16 An Expansion Method for Off-Line Hand-Printed Character Recognition Using On-Line Character Writing Features
Hiromitsu Nishimura and Kazuhisa Yanaka
♠P17 A Model-Based Field Frame Detection for Handwritten Filled-in Forms
Juan-Carlos Perez-Cortes, Luis Andreu, and Joaquim Arlandis
♠P18 Lexicon Reduction in Handwriting Recognition Using Topic Categorization
Faisal Farooq, Gaurav Chandalia, and Venu Govindaraju
Layout Analysis
♠P19 Truthing for Pixel-Accurate Segmentation
Michael A. Moll, Henry S. Baird, and Chang An
♥P20 On the Reading of Tables of Contents
Prateek Sarkar and Eric Saund
♠P21 Unsupervised Decomposition of Color Document Images by Projecting Colors to A Spherical Surface
Yuan He, Jun Sun, Satoshi Naoi, Yusaku Fujii, and Katsuhito Fujimoto
♥P22 Fast and Accurate Skew Estimation Based on Distance Transform
Itay Bar-Yosef, Nate Hagbi, Klara Kedem, and Itshak Dinstein
♠P23 Physical Layout Segmentation of Mail, Application Dedicated to Automatic Postal Sorting System
Djamel Gaceb, Véronique Eglin, Frank Lebourgeois, and Hubert Emptoz
♥P24 Structural Mixtures for Statistical Layout Analysis
Faisal Shafait, Joost van Beusekom, Daniel Keysers, and Thomas M. Breuel
♠P25 A Study on Document Structure Recognition of Discharge Summaries for Analogous Case Search System
Hiroharu Kawanaka, Yujiro Shiroyama, Shinji Tsuruoka, Tsuyoshi Shinogi, and Koji Yamamoto
♥P26 A Fast Preprocessing Method for Table Boundary Detection: Narrowing Down the Sparse Lines Using Solely Coordinate Information
Ying Liu, Prasenjit Mitra, and C. Lee Giles
♠P27 Pre-Printed and Hand-Filled Table-Form Analysis Aiming Cell Extraction
Rafaela Dandolini Felipe and Luiz Antonio Pereira Neves
Image Processing
♥P28 Efficient Binarization of Historical and Degraded Document Images
B. Gatos, I. Pratikakis, and S.J. Perantonis
♠P29 A Graphics Image Processing System
Linlin Li and Chew Lim Tan
♥P30 A Proposal of Evaluation Method for Balance of White Space in Calligraphy by Using Horizon View Camera
Kensuke Tobitani, Nobuyasu Okabe, Kazuhiko Yamamoto, and Kunihito Kato
Document Image Enhancement
♠P31 Anisotropic Total Variation Method for Text Image Super-Resolution
Battulga Bayarsaikhan, Younghee Kwon, and Jin Hyung Kim
♥P32 CCD: Connected Component Descriptor for Robust Mosaicing of Camera-Captured Document Images
T. Kasar and A. G. Ramakrishnan
Object Extraction and Recognition
♠P33 Word and Symbol Spotting Using Spatial Organization of Local Descriptors
Marçal Rusiñol and Josep Lladós
♥P34 Performance Evaluation of Symbol Recognition and Spotting Systems: An Overview
Mathieu Delalandre, Ernest Valveny and Josep Lladós
♠P35 Object Extraction from Colour Cadastral Maps
Romain Raveaux, Jean-Christophe Burie, and Jean-Marc Ogier
Historical Documents
♥P36 HistoSketch: A Semi-Automatic Annotation Tool for Archival Documents
Joan Mas, José A. Rodríguez, Dimosthenis Karatzas, Gemma Sánchez, and Josep Lladós
♠P37 A Complete Optical Character Recognition Methodology for Historical Documents
G.Vamvakas, B.Gatos, N. Stamatopoulos, and S.J.Perantonis
♥P38 Document Image Retrieval to Support Reading Mokkans
Akihito Kitadai, Jun Takakura, Masatoshi Ishikawa, Masaki Nakagawa, Hajime Baba, and Akihiro Watanabe
♠P39 Keyword Matching in Historical Machine-Printed Documents Using Synthetic Data, Word Portions and Dynamic Time Warping
T. Konidaris, B. Gatos, S. J. Perantonis, and A. Kesidis
Mathematical Documents
♥P40 A Large-Scale Analysis of Mathematical Expressions for an Accurate Understanding of Their Structure
Walaa Aly, Seiichi Uchida, and Masakazu Suzuki
♠P41 An Empirical Measure on the Set of Symbols Occurring in Engineering Mathematics Texts
Stephen M. Watt
Text Processing
♥P42 Named Entity Recognition by Neural Sliding Window
Ignazio Gallo, Elisabetta Binaghi, Moreno Carullo, and Nicola Lamberti
♠P43 Exploring Evolutionary Technical Trends from Academic Research Papers
Teng-Kai Fan and Chia-Hui Chang
Document Analysis Systems
♥P44 PaperDiff: A Script Independent Automatic Method for Finding The Text Differences Between Two Document Images
Sitaram Ramachandrula, Gopal Datt Joshi, Noushath.S, Pulkit Parikh, and Vishal Gupta
♠P45 The HCI Paradigm of HyperPrinting
Thomas Kieninger and Andreas Dengel
♥P46 MathBrush: A System for Doing Math on Pen-Based Devices
George Labahn, Edward Lank, Scott MacLean, Mirette Marzouk, and David Tausky
♠P47 End-to-End Trainable Thai OCR System Using Hidden Markov Models
Kriste Krstovski, Ehry MacRostie, Rohit Prasad, and Premkumar Natarajan
♥P48 Comprehensive Global Typography Extraction System for Electronic Book Documents
Liangcai Gao, Zhi Tang, Xiaofan Lin, and Ruiheng Qiu
♠P49 Digital Ink to Form Alignment for Electronic Clipboard Devices
Jagannadan Varadarajan and Sriganesh Madhvanath
♥P50 Towards Whole-Book Recognition
Pingping Xiu and Henry S. Baird
♠P51 Handling of Surface Modifications for Robust Image Based Mail Piece Comparison
Katja Worm and Beate Meffert
♥P52 Dolores: An Interactive and Class-Free Approach for Document Logical Restructuring
Jean-Luc Bloechle, Catherine Pugin, and Rolf Ingold
♥P54 The Convergence of Iterated Classification
Chang An and Henry S. Baird
♠P55 A Comparison of Clustering Methods for Word Image Indexing
Simone Marinai, Emanuele Marino, and Giovanni Soda
♥P56 New Oversampling Approaches Based on Polynomial Fitting for Imbalanced Data Sets
Sami Gazzah and Najoua Essoukri Ben Amara
Extended Abstracts
♠P57 Pen and Paper-Based Interaction with the Semantic Desktop
Marcus Liwicki, Kinga Schumacher, Andreas Dengel, Nadir Weibel, Beat Signer, and Moira C. Norrie
♥P58 Compound Document Image Compression with Unified Coder
Kenneth K. C. Lee and Y. K. Chan
♠P59 A Study on Signboard Image Identification with SIFT Features
Hiromi Yoshida and Naoki Tanaka
♥P60 An Identification Method for Printed European Address Images
Tatsuo Akiyama, Katsuhiko Kondoh, and Daisuke Nishiwaki
♠P61 Logical Structure Understanding of PDF Documents for Generating Business Document Templates
Masakazu Fujio, Katsumi Marukawa, Hiroshi Shinjo, Takeshi Nagasaki, Minenobu Seki, and Hisashi Ikeda
♥P62 A Manually Annotated HTML Corpus for a Novel Scientific Trend Analysis
Richárd Farkas, Róbert Ormándi, Márk Jelasity, and János Csirik
♠P63 Extracting Precise Data from PDF Documents for Mathematical Formula Recognition
Josef B. Baker, Alan P. Sexton, and Volker Sorge

Demo Sessions

♠D1 MathBrush: A System for Doing Math on Pen-Based Devices
George Labahn, Edward Lank, Scott MacLean, Mirette Marzouk, and David Tausky
♥D2 Real-Time Retrieval for Images of Documents in Various Languages
Tomohiro Nakai, Koichi Kise, and Masakazu Iwamura
♥D3 Semantic eInk — Pen and Paper-Based Interaction with the Semantic Desktop
Marcus Liwicki, Kinga Schumacher, Andreas Dengel, Nadir Weibel, Beat Signer, and Moira C. Norrie
♥D5 An On-Line Handwritten Japanese Text Recognition System Free from Line Direction and Writing Format Constraints
Bilan Zhu and Masaki Nakagawa
♠D6 An Image Based Watermark String Detection System for Document Security Checking
Jun Sun, Yusaka Fujii, Hiroaki Takebe, Katsuhito Fujimoto, and Satoshi Naoi
♥D7 A System to Help Archaeologists Read Mokkans
Jun Takakura, Somayeh Sherini, Akihito Kitadai, Masatoshi Ishikawa, Masaki Nakagawa, Hajime Baba, and Akihiro Watanabe