10th IAPR International Workshop on Document Analysis Systems

March 27th - 29th, 2012

Gold Coast, Queensland, Australia

Workshop Program details




Time March 26 March 27 March 28 March 29
9.00 - 10.20 Tutorial 1
(With Coffee break)
Opening Ceremony
(9.00 - 9.20)
Session 3:
Video Text Processing
Session 6:
Keynote Lecture
(9.20 - 10.20)
10.20 - 10.40
Coffee Break Coffee Break Coffee Break
10.40 - 12.40 Session 1:
Systems and Intelligence
Session 4:
Session 7:
12.40 - 13.40 Lunch
(On Own)
Lunch Lunch Lunch
13.40 - 15.10 Tutorial 2
(With Coffee break)
Poster 1 Discussion Poster 2
15.10 - 15.30 Coffee Break Coffee Break Coffee Break
15.30 - 17.10 Session 2:
Document Classification and Recognition
Session 5:
Text Recognition
Reports of Discussion Group
(15.30 - 16.30)
Concluding Remarks & Awards
(16.30 - 17.00)
18.00 - 22.00 Welcome Reception
(18.00 - 22.00)
DAS-2012 PC Dinner
(19.00 - 21.30)
(18.00 - 21.30)

Tutorial Session 1

Chair: Robert Sablatnig

Title: Markov Models for Handwriting Recognition
Speaker: Dr.Gernot A. Fink

Goto Top

Tutorial Session 2

Chair: Palaiahnakote Shivakumara

Title: Large-Scale Document Image Retrieval and Character Recognition with Approximate Nearest Neighbor Techniques
Speaker: Dr.Koichi Kise

Goto Top

Keynote Lecture

Chair: Michael Blumenstein

Title: Learning A Semantic Space: From Image Annotation to Music Similarity
Speaker: Dr.Samy Bengio

Goto Top

Session-1: Systems and Intelligence

Chair: Umapada Pal
  1. Adapting the Turing Test for Declaring Document Analysis Problems Solved
    Daniel Lopresti and George Nagy.
  2. Towards Understandable Explanations for Document Analysis Systems
    Bjorn Forcher, Stefan Agne, Andreas Dengel, Michael Gillmann and Thomas Roth-Berghofer.
  3. A Modular Metadata Extraction System for Born-Digital Articles
    Dominika Tkaczyk, Lukasz Bolikowski, Artur Czeczko and Krzysztof Rusek.
  4. Koios++: A Query-Answering System for Handwritten Input
    Marcus Liwicki, Bjorn Forcher, Philipp Jaeger and Andreas Dengel.
  5. Attentive Tasks: Process-Driven Document Analysis for Multichannel Documents
    Kristin Stamm and Andreas Dengel.
  6. The Non-geek's guide to the DAE Platform
    Bart Lamiroy and Daniel Lopresti.

Goto Top

Session-2: Document Classification and Recognition

Chair: Seiichi Uchida
  1. Document Classification Using Multiple Views
    Albert Gordo, Florent Perronnin and Ernest Valveny.
  2. New Spatial-Gradient-Features for Video Script Identification
    Danni Zhao, Palaiahnakote Shivakumara, Shijian Lu and Chew Lim Tan.
  3. Multiple Feature-Classifier Combination in Automated Text Classification
    Lazaro S.P. Busagala, Wataru Ohyama, Tetsushi Wakabayashi and Fumitaka Kimura.
  4. An Efficient Framework for Searching Text in Noisy Document Images
    Ismet Zeki Yalniz and R. Manmatha.
  5. A Prototype System of Courtesy Amount Recognition for Chinese Bank Checks
    Dong Liu and Youbin Chen.

Goto Top

Session-3: Video Text Processing

Chair: David Doermann
  1. Adaptive Graph Cuts Based Binarization of Video Text Images
    Cunzhao Shi, Chunheng Wang, Baihua Xiao and Yang Zhang.
  2. Recent Advances in Video Based Document Processing: A Review
    Nabin Sharma, Umapada Pal and Michael Blumenstein.
  3. A Fast Stroke-Based Method for Text Detection in Video
    Bo Bai, Fei Yin and Cheng-Lin Liu.
  4. A New Method for Arbitrarily-Oriented Text Detection in Video
    Nabin Sharma, Palaiahnakote Shivakumara, Umapada Pal, Michael Blumenstein and Chew Lim Tan.

Goto Top

Session 4: Preprocessing

Chair: Venu Govindaraju
  1. A Robust Approach for Local Interest Point Detection in Line-Drawing Images
    The Anh Pham, Mathieu Delalandre, Sabine Barrat and Jean-Yves Ramel.
  2. Document Preprocessing System -- Automatic Selection of Binarization
    Ines Ben Messaoud, Haikal El Abed, Hamid Amiri and Volker Maergner.
  3. Local Consistency Constrained Adaptive Neighbor Embedding for Text Image Super-Resolution
    Wei Fan, Jun Sun, Satoshi Naoi, Akihiro Minagawa and Yoshinobu Hotta.
  4. Binarization-Free Text Line Segmentation for Historical Documents Based on Interest Point Clustering
    Angelika Garz, Andreas Fischer, Robert Sablatnig and Horst Bunke.
  5. Arabic Handwritten Text Line Extraction by Applying an Adaptive Mask to Morphological Dilation
    Muna Khayyat, Louisa Lam, Ching Suen, Fei Yin and Cheng-Lin Liu.
  6. Scanning Neural Network for Text Line Recognition
    Sheikh Faisal Rashid, Faisal Shafait and Thomas Breuel.

Goto Top

Session 5: Text Recognition

Chair:Andreas Dengel
  1. Improving Handwritten Chinese Text Recognition by Unsupervised Language Model Adaptation
    Qiu-Feng Wang, Fei Yin and Cheng-Lin Liu.
  2. Improving Book OCR by Adaptive Language and Image Models
    Dar-Shyang Lee and Ray Smith.
  3. Combining Multi-Scale Character Recognition and Linguistic Knowledge for Natural Scene Text OCR
    Khaoula Elagouni, Christophe Garcia, Franck Mamalet and Pascale Se'billot.
  4. Offline Handwritten English Character Recognition Based on Convolutional Neural Networks
    Aiquan Yuan, Gang Bai, Lijing Jiao and Yajie Liu.
  5. Robust Recognition of Degraded Documents Using Character N-Grams
    Shrey Dutta, Naveen Sankaran, Pramod Kompalli and Jawahar C.V.

Goto Top

Session 6: Retrieval

Chair:Daniel Lopresti
  1. Logo Retrieval in Document Images
    Rajiv Jain and David Doermann.
  2. Similar Fragment Retrieval of Animations by a Bag-of-feature Approach
    Weihan Sun, Koichi Kise and Yoann Champeil.
  3. Writer Retrieval and Writer Identification using Local Features
    Stefan Fiel and Robert Sablatnig.
  4. An Efficient Coarse-to-Fine Indexing Technique for Fast Text Retrieval in Historical Documents
    Partha Roy, Fre'de'ric Rayar and Jean-Yves Ramel.

Goto Top

Session 7: Applications

Chair:Graham Leedham
  1. ExpressMatch: A System for Creating Ground-Truthed Datasets of Online Mathematical Expressions
    Frank Julca and Nina Hirata.
  2. An Effective Staff Detection and Removal Technique for Musical Documents
    Bolan Su, Shijian Lu, Umapada Pal and Chew Lim Tan.
  3. Symbol Recognition Using a Galois Lattice of Frequent Graphical Patterns
    Ameni Boumaiza and Salvatore Tabbone.
  4. Quality Evaluation of Facsimiles of Hebrew First Temple Period Inscriptions
    Arie Shaus, Eli Turkel and Eli Piasetzky.
  5. Is It Possible to Automatically Identify Who Has Forged My Signature?: Approaching to the Identification of a Static Signature Forger
    Miguel Ferrer, Aythami Morales, Jesus Francisco Vargas, Ivan Lemos and Monica Quintero.
  6. Towards Semi-Supervised Transcription of Handwritten Historical Weather Reports
    Jan Richarz, Szila'rd Vajda and Gernot Fink.

Goto Top

Poster 1

Chair:Abdel Belaid
(R# : Regular Papers, S# : Short Papers)
  • R1. A Part-Based Skew Estimation Method
    Soma Shiraishi, Yaokai Feng and Seiichi Uchida.

  • R3. Removal Of Background Patterns And Signatures For Magnetic Ink Character Recognition Of Checks
    Keiichiro Shirai, Masashi Akita, Masayuki Okamoto, Kazuya Tanikawa, Takaaki Akiyama and Tetsuji Sakaguchi.

  • R5. Lexicon Reduction Technique For Bangla Handwritten Word Recognition
    Tapan Kumar Bhowmik, Utpal Roy and Swapan K. Parui.

  • R7. Recognition Of Similar Shaped Handwritten Characters Using Logistic Regression
    Kinjal Basu, Radhika Nangia and Umapada Pal.

  • R9. Capture and Dewarping of Page Spreads with a Handheld Compact 3D Camera
    Michael Cutter and Patrick Chiu.

  • R11. Graph-Based Background Suppression For Scene Text Detection
    Cunzhao Shi, Chunheng Wang, Baihua Xiao and Yang Zhang.

  • R13. Writer Identification Of Bangla Handwritings By Radon Transform Projection Profile
    Samit Biswas and Amit Kumar Das.

  • R15. Voronoi-Based Zoning Design By Multi-Objective Genetic Optimization
    Giuseppe Pirlo and Donato Impedovo.

  • R17. Real-Time Document Image Retrieval On A Smartphone
    Kazutaka Takeda, Koichi Kise and Masakazu Iwamura.

  • R19. Effect Of Text/Non-Text Classification For Ink Search Employing String Recognition
    Tomohisa Matsushita, Cheng Cheng, Yujiro Murata, Bilan Zhu and Masaki Nakagawa.

  • R21. On The Enhancement And Binarization Of Mobile Captured Vehicle Identification Number For An Embedded Solution
    Tanushyam Chattopadhyay, Ujjwal Bhattacharya and Bidyut B Chaudhuri.

  • R23. Optimization Analysis Based On A Breadth-First Exploration For A Structural Approach Of Sketches Interpretation
    Achraf Ghorbel, Eric Anquetil and Aure'lie Lemaitre.

  • R25. OCD Dolores - Recovering Logical Structures For Dummies
    Jean-Luc Bloechle, Maurizio Rigamonti and Rolf Ingold.

  • R27. Effect Of Ground Truth On Image Binarization
    Elisa H. Barney Smith and Chang An.

  • R29. How Important Is Global Structure For Characters?
    Minoru Mori, Seiichi Uchida and Hitoshi Sakano.

  • R31. A Compact Size Feature Set For The Off-Line Signature Verification Problem
    Vu Nguyen and Michael Blumenstein.

  • R33. Toward Part-Based Document Image Decoding
    Wang Song, Marcus Liwicki and Seiichi Uchida.

  • R35. Impact Of Word Segmentation Errors On Automatic Chinese Text Classification
    Xi Luo, Wataru Ohyama, Tetsushi Wakabayashi and Fumitaka Kimura.

  • R37. Crf-Based Bibliography Extraction From Reference Strings Focusing On Various Token Granularities
    Manabu Ohta, Daiki Arauchi, Atsuhiro Takasu and Jun Adachi.

  • R39. Off-Line Bangla Signature Verification
    Srikanta Pal, Vu Nguyen, Michael Blumenstein and Umapada Pal.

  • R41. Performance Evaluation Of Mathematical Formula Identification
    Xiaoyan Lin, Liangcai Gao, Zhi Tang, Xiaofan Lin and Xuan Hu.

  • R43. Skew Estimation Of Sparsely Inscribed Document Fragments
    Markus Diem, Florian Kleber and Robert Sablatnig.

  • R45. Word Image Retrieval Using Bag Of Visual Words
    Ravi Shekhar and C. V. Jawahar.

  • R47. A Fast Caption Detection Method For Low Quality Video Images
    Tianyi Gui, Jun Sun, Satoshi Naoi, Yutaka Katsuyama, Minagawa Akihiro and Hotta Yoshinobu.

  • R49. Word Slant Estimation Using Non-Horizontal Character Parts And Core-Region Information
    Alexandros Papandreou and Basilis Gatos.

  • R51. Accent Detection In Handwriting Based On Writing Styles
    Chetan Ramaiah, Utkarsh Porwal and Venu Govindaraju.

  • R53. How Salient Is Scene Text?
    Asif Shahab, Faisal Shafait, Andreas Dengel and Seiichi Uchida.
  • R55. Ensemble of Biased Learners for Offline Arabic Handwriting Recognition
    Utkarsh Porwal, Arti Shivram, Chetan Ramaiah and Venu Govindaraju.

  • S1. Wearable Reading Assistant Device with Scene Text Locator for the Blind
    Takahiro Sasaki, Akira Saito, Hideaki Goto

  • S3. Semi-supervised Learning Approach for Automatic Emotional Expression Extraction from eBook Text
    Kosei Fume, Masaru Suzuki and Morita Masahiro

  • S5. Document perceptual quality ground-truth creation
    Vincent Rabeux, Nicholas Journet, Anne Vialard, Jean-Philippe Domenger

  • S7. A Binarization Approach for Ukiyo-e Rakkan Extraction
    Liang Li, Chulapon Panichkriangkrai, Chihiro Tsunoda and Kozaburo Hachimura

  • S9. A New Method of Character Strings Extraction based on Blanket Binarization
    Hiromi Yoshida, Naoki Tanaka, Takashi Nagamatsu

  • S11. A Framework for Intelligent Navigation of Scanned Documents
    Akash Dutta, Amit Kumar Das, Manas Hira

  • S13. Digital Image Library Data Design Criteria
    Anthony J. Maeder

Goto Top

Poster 2

Chair:Cheng-Lin Liu
(R# : Regular Papers, S# : Short Papers)
  • R2. Expanding Recognizable Distorted Characters Using Self-Corrective Recognition
    Masaki Tsukada, Masakazu Iwamura and Koichi Kise.
  • R4. Recognizing Words In Scenes With A Head-Mounted Eye-Tracker
    Takuya Kobayashi, Takumi Toyama, Faisal Shafait, Masakazu Iwamura, Koichi Kise and Andreas Dengel.
  • R6. Automatic Room Detection And Room Labeling From Architectural Floor Plans
    Sheraz Ahmed, Marcus Liwicki, Markus Weber and Andreas Dengel.
  • R8. Collecting Handwritten Nom Character Patterns From Historical Document Pages
    Truyen Van Phan, Bilan Zhu and Masaki Nakagawa.
  • R10. Extraction of Text Touching Graphics using SURF
    Sheraz Ahmed, Marcus Liwicki and Andreas Dengel.
  • R12. Web Document Analysis Based On Visual Segmentation And Page Rendering
    Cong Kinh Nguyen, Laurence Likforman-Sulem, Jean-Claude Moissinac, Claudie Faure and Je're'my Lardon.
  • R14. Similarity Evaluation And Shape Feature Extraction For Character Pattern Retrieval To Support Reading Historical Documents
    Akihito Kitadai, Masaki Nakagawa, Hajime Baba and Akihiro Watanabe.
  • R16. Seamless Integration Of Handwriting Recognition Into Pen-Enabled Displays For Fast User Interaction
    Marcus Liwicki, Markus Weber, Tobias Zimmermann and Andreas Dengel.
  • R18. Text Independent Writer Identification For Oriya Script
    Sukalpa Chanda, Katrin Franke and Umapada Pal.
  • R20. Use of PGM For Form Recognition
    Emilie Philippot, Abdel Belai d and Yolande Belai d.
  • R22. Efficient Word Retrieval Using A Multiple Ranking Combination Scheme
    Georgios Louloudis, Anastasios Kesidis and Basilis Gatos.
  • R24. Text Detection In Natural Scenes With Salient Region
    Quan Meng, Yonghong Song.
  • R26. OTCYMIST: Otsu-Canny Minimal Spanning Tree for Born-Digital Images
    Deepak Kumar and A G Ramakrishnan.
  • R28. Improvements To Uncalibrated Feature-Based Stereo Matching For Document Images By Using Text-Line Segmentation
    Muhammad Zeshan Afzal, Martin Kra mer, Syed Saqib Bukhari, Faisal Shafait and Thomas Breuel.
  • R30. A Simple And Uniform Way To Introduce Complimentary Asynchronous Interaction Models In An Existing Document Analysis System
    Joseph Chazalon, Bertrand Cou asnon and Aure'lie Lemaitre.
  • R32. OCR-Free Table of Contents Detection in Urdu Books
    Adnan Ul-Hasan, Syed Saqib Bukhari, Faisal Shafait and Thomas M. Breuel.
  • R34. Parsing Tables By Probabilistic Modeling Of Perceptual Cues
    Evgeniy Bart.
  • R36. Learning Domain-Specific Feature Descriptors For Document Images
    Kandan Ramakrishnan and Evgeniy Bart.
  • R38. A Signature Verification Framework for Digital Pen Applications
    Muhammad Imran Malik, Sheraz Ahmed, Andreas Dengel and Marcus Liwicki.
  • R40. Panel And Speech Balloon Extraction From Comics Books
    Anh Khoi Ngo Ho, Jean-Christophe Burie and Jean-Marc Ogier.
  • R42. Linear Compression of Digital Ink via Point Selection
    Vadim Mazalov and Stephen Watt.
  • R44. A Strategy for Automatically Extracting References from PDF Documents
    Neide Alves, Rafael Lins and Maria Lencastre.
  • R46. Evaluation of Features for Author Name Disambiguation Using Linear Support Vector Machines
    Piotr Jan Dendek, Lukasz Bolikowski and Michal Lukasik.
  • R48. Dataset, Ground-Truth And Performance Metrics For Table Detection Evaluation
    Jing Fang, Xin Tao, Zhi Tang Ruiheng Qiu and Ying Liu.
  • R50. A new Cursive Basic Word Database for Bank-check Processing Systems
    Sebastiano Impedovo, Giuseppe Facchini and Francesco Maurizio Mangini.
  • R52. An Empirical Evaluation on Online Chinese Handwriting Databases
    Shusen Zhou, Qingcai Chen, Xiaolong Wang, Zou Chen and Suqin Ao.
  • R54. Local Segmentation of Touching Characters using Contour based Shape Decomposition
    Le Kang, David Doermann, Huaigu Cao, Rohit Prasad and Prem Natarajan.
  • S2. Characters Extraction from Strings on a Document Image Using Handwriting Marks on Touch Screen
    Shinnosuke Hattori, Shinji Tsuruoka, Haruhiko Takase, Hiroharu Kawanaka

  • S4. A Proposal of Sheet Type Recognition Method and its Evaluation for Medical/Clinical Document Archiving Systems
    Shunta Nakamura, Hiroharu Kawanaka Hiroki Hayashi, Haruhiko Takase, Shinji Tsuruoka, Koji Yamamoto

  • S6. On-line cursive handwriting characterization using TF-IDF scores of graphemes
    Muriel Visani, Quang Anh Bui and Sophea Prum

  • S8. Character Segmentation for Japanese Woodblock Printed Historical Books
    Chulapong Panichkriangkrai, Liang Li, Kozaburo Hachimura

  • S10. A New Baseline Estimation Method Applied to Word Arabic Recognition
    Fouad Slimane, Slim Kanoun, Adel M. Alimi, Rolf Ingold, Jean Hennebert

  • S12. From MIT SketchML to InkML or There and Back Again
    Rui Hu, Stephen M. Watt

Goto Top