11th IAPR International workshop on Document Analysis System

Mon. 07

Tue. 08

Wed. 09

Thu. 10

08:00

09:00

10:00

11:00

12:00

13:00

14:00

15:00

16:00

17:00

18:00

19:00

20:00

21:00

22:00

23:00

Tutorial 1 : Everything you always wanted to know about Tesseract.

8:30 - 12:30 (4h)

Tutorial 1 : Everything you always wanted to know about Tesseract.

Turing Amphitheater - PolytechTours

Ray Smith - Google USA

https://das2014.sciencesconf.org/data/program/DAS2014_tutorial1.html

Lunch (on your own)

12:30 - 14:00 (1h30)

Lunch (on your own)

Tutorial 2: Building Scalable Solutions for Document Retrieval and Recognition.

14:00 - 18:00 (4h)

Tutorial 2: Building Scalable Solutions for Document Retrieval and Recognition.

Turing Amphitheater - PolytechTours

C. V. Jawahar, IIIT Hyderabad, India - Pramod Kompalli, Xerox Research Centre, India

https://das2014.sciencesconf.org/data/program/DAS2014_tutorial2.html

Welcome Reception (at the city House of Tours)

19:15 - 22:30 (3h15)

Welcome Reception (at the city House of Tours)

Opening Ceremony

8:30 - 9:00 (30min)

Opening Ceremony

Room Courteline - Vinci

Document Evolution drives Document Analysis

9:00 - 10:00 (1h)

Document Evolution drives Document Analysis

Room Courteline - Vinci

Prof Andreas DENGEL - DFKI Kaiserslautern - Germany - Chairman: Jean-Marc Ogier

Coffee break

10:00 - 10:30 (30min)

Coffee break

Salon Agnes Sorel - Vinci

Oral-1 Document Classification and Retrieval (3x20')

10:30 - 11:30 (1h)

Oral-1 Document Classification and Retrieval (3x20')

Room Courteline - Vinci

Chairman: Dave Doermann

› #14 - Plane Geometry Figure Retrieval with Bag of Shapes - Lu Liu and Xiaoqing Lu 10:30-10:50 (20min)

› #144 - Multiscale Stroke-Based Page Segmentation Approach - Mehdi Felhi, Salvatore Tabbone and Maria V. Ortiz Segovia 10:50-11:10 (20min)

› #95 - Business Forms Classification using Earth Mover's Distance - Syed Saqib Bukhari, Markus Ebbecke and Michael Gillmann 11:10-11:30 (20min)

Oral-2 Writer Identification and Verification (3x20')

11:30 - 12:30 (1h)

Oral-2 Writer Identification and Verification (3x20')

Room Courteline - Vinci

Chairman:

› #133 - Multiclass Learning for Writer Identification using Error-Correcting Codes - Utkarsh Porwal, Chetan Ramaiah, Ashish Kumar and Venu Govindaraju 11:30-11:50 (20min)

› #72 - A Hierarchical Framework for Accent Based Writer Identification - Chetan Ramaiah and Venu Govindaraju 11:50-12:10 (20min)

› #59 - Feasibility study of visualizing diversity of Japanese Hiragana handwritings by multidimensional scaling of Earth Mover's Distance toward assisting forensic experts in writer verification - Yoshinori Akao, Atsushi Yamamoto and Yoshiyasu Higashikawa 12:10-12:30 (20min)

Lunch

12:30 - 14:00 (1h30)

Lunch

Salon Agnes Sorel - Vinci

Oral-3 Text detection and Correction (4x20')

14:00 - 15:30 (1h30)

Oral-3 Text detection and Correction (4x20')

Room Courteline - Vinci

Chairman: Vincent Poulain d'Andecy

› #91 - Flexible noisy text correction - Andrey Sariev, Vladislav Nenchev, Stefan Gerdjikov, Petar Mitankin, Hristo Ganchev, Stoyan Mihov and Tinko Tinchev 14:00-14:20 (20min)

› #129 - Planting, Growing, and Pruning Trees: Connected Filters Applied to Document Image Analysis - Guillaume Lazzara, Thierry Géraud and Roland Levillain 14:20-14:40 (20min)

› #33 - Text Detection using Delaunay Triangulation in Video Sequence - Liang Wu, Palaiahnakote Shivakumara, Tong Lu and Chew Lim Tan 14:40-15:00 (20min)

› #42 - A typed and handwritten text block segmentation system for heterogeneous and complex documents - Philippine Barlas, Sébastien Adam, Clément Chatelain and Thierry Paquet 15:00-15:20 (20min)

Coffee break

15:30 - 16:00 (30min)

Coffee break

Salon Agnes Sorel - Vinci

Oral-4 Handwritten Text recognition and Graph Edit distances (3x20')

16:00 - 17:00 (1h)

Oral-4 Handwritten Text recognition and Graph Edit distances (3x20')

Room Courteline - Vinci

Chairman:

› #81 - A System for Recognizing Online Handwritten Mathematical Expressions and Improvement of Structure Analysis - Duc Anh Le, Van Truyen Phan and Masaki Nakagawa 16:00-16:20 (20min)

› #40 - Curriculum learning for handwritten text line recognition - Jérôme Louradour and Christopher Kermorvant 16:20-16:40 (20min)

› #6 - Iterative Bipartite Graph Edit Distance Approximation - Kaspar Riesen, Rolf Dornberger and Horst Bunke 16:40-17:00 (20min)

Teasers-1 (23x1')

17:00 - 17:30 (30min)

Teasers-1 (23x1')

Room Courteline - Vinci

Chairman: Marcal Rusiñol

Poster-1

17:30 - 19:00 (1h30)

Poster-1

Salon Agnes Sorel - Vinci

Chairman: Marcal Rusiñol

› #104 - A Combined System for Text Line Extraction and Handwriting Recognition in Historical Documents - Andreas Fischer 17:30-17:30 ()

› #115 - Multi-Oriented Text Recognition in Graphical Documents using HMM - Partha Pratim Roy 17:30-17:30 ()

› #125 - Spotting Symbol using Sparsity over Learned Dictionary of Local Descriptors - Thanh Ha Do 17:30-17:30 ()

› #126 - Sequential Word Spotting in Historical Handwritten Documents - David Fernández 17:30-17:30 ()

› #13 - NIST 2013 Open Handwriting Recognition and Translation (OpenHaRT'13) Evaluation - Audrey Tong 17:30-17:30 ()

› #134 - Towards a Robust OCR System for Indic Scripts - Praveen Krishnan, LI 17:30-17:30 ()

› #137 - Holistic Recognition of Online Handwritten Words Based on an Ensemble of SVM Classifiers - Avinaba Srimany 17:30-17:30 ()

› #148 - Word-Graph based Handwriting Key-word Spotting: Impact of Word-Graph Size on Performance - Alejandro Héctor Toselli 17:30-17:30 ()

› #154 - Text Classification via iVector Based Feature Representation - Shengxin Zha 17:30-17:30 ()

› #26 - A Context Based Text Summarization System - . Rafael Mello, Luciano Cabral, Rafael Dueire, Grabriel França and Frederico Freitas, das2014 17:30-17:30 ()

› #27 - Multilingual Off-line Handwriting Recognition in Real-world Images - Michal Kozielski 17:30-17:30 ()

› #36 - The infuence of language orthographic characteristics on digital word recognition - Ofer Biller 17:30-17:30 ()

› #51 - Multi-oriented handwritten annotations extraction from scanned documents - Mohamed Benjlaiel 17:30-17:30 ()

› #53 - Evaluation of Texture Features for Offline Arabic Writer Identification - Djeddi Chawki 17:30-17:30 ()

› #58 - Context-Dependent Confusions Rules for building Error Model using Weighted Finite State Transducers for OCR Post-Processing - Mayce Al-Azawi 17:30-17:30 ()

› #66 - A Cache Language Model for Whole Document Handwriting Recognition - Volkmar Frinken 17:30-17:30 ()

› #7 - The A2iA Arabic Handwritten Text Recognition System at the OpenHaRT2013 Evaluation - Théodore Bluche 17:30-17:30 ()

› #73 - Printer Identification using Supervised Learning for Document Forgery Detection - Sara Elkasrawi 17:30-17:30 ()

› #74 - Oriented Local Binary Patterns for Arabic Optical Font Recognition - Anguelos Nicolaou 17:30-17:30 ()

› #82 - Historical Chinese Character Recognition Method Based on Style Transfer Mapping - Bohan Li 17:30-17:30 ()

› #85 - The RWTH Large Vocabulary Arabic Handwriting Recognition System - Mahdi Hamdani 17:30-17:30 ()

› #88 - On-line Handwritten Mathematical Expression Recognition Method based on Statistical and Semantic Analysis - Yang Hu 17:30-17:30 ()

DAS 2014 PC Dinner

19:45 - 23:00 (3h15)

DAS 2014 PC Dinner

Oral-5a OCR, Word Spotting and Recognition (4x20')

8:40 - 10:00 (1h20)

Oral-5a OCR, Word Spotting and Recognition (4x20')

Room Courteline - Vinci

Chairman: Faisal Shafait

› #28 - Combining Focus Measure Operators to Predict OCR Accuracy in Mobile-Captured Document Images - Marçal Rusiñol, Joseph Chazalon and Jean-Marc Ogier 08:30-08:50 (20min)

› #9 - End-to-End Text Recognition using Local Ternary Patterns, MSER and Deep Convolutional Nets - Michael Opitz, Markus Diem, Florian Kleber, Stefan Fiel and Robert Sablatnig 08:50-09:10 (20min)

› #89 - Adapting Tesseract for Complex Scripts: An Example for Urdu Nastalique - Qurat-Ul-Ain Akram, Sarmad Hussain, Aneeta Niazi, Umair Anjum and Faheem Irfan 09:10-09:30 (20min)

› #10 - Performance Improvement in Local Feature Based Camera-Captured Character Recognition - Takahiro Matsuda, Masakazu Iwamura and Koichi Kise 09:30-09:50 (20min)

Coffee break

10:00 - 10:30 (30min)

Coffee break

Salon Agnes Sorel - Vinci

Oral-5b OCR, Word Spotting and Recognition (3x20')

10:30 - 11:30 (1h)

Oral-5b OCR, Word Spotting and Recognition (3x20')

Room Courteline - Vinci

Chairman: Abdel Belaid

› #68 - OCR Performance Prediction using a Bag of Allographs and Support Vector Regression - Tapan Kumar Bhowmik, Thierry Paquet and Nicolas Ragot 10:30-10:50 (20min)

› #35 - A Novel Learning-free Word Spotting Approach Based On Graph Representation - Peng Wang, Véronique Eglin, Christine Largeron, Josep Lladós, Alicia Fornes and Christophe Garcia 10:50-11:10 (20min)

› #15 - Surgenerative Finite State Transducer n-gram for Out-Of-Vocabulary Word Recognition - Ronaldo Messina and Christopher Kermorvant 11:10-11:30 (20min)

Spotlight (10x1') Shortpaper poster+demo

11:30 - 12:30 (1h)

Spotlight (10x1') Shortpaper poster+demo

Salon Agnes Sorel - Vinci

Chairman: Andreas Fischer

› #175 - A Hybrid Algorithm for Automatic Language Detection on Web and Text Documents - . Luciano Cabral, Rinaldo Lima, Rafael Lins, Fred Freitas, Rafael Mello, Gabriel França and George D. C. Cavalcanti 11:30-11:30 ()

› #176 - A system for camera-based complex map image retrieval using a multi-layer approach - . Quoc Bao Dang, Muhammad Muzzamil Luqman, Mickael Coustaty, Nibal Nayef, Jean-Marc Ogier and Cao De Tran 11:30-11:30 ()

› #177 - Dehyphenation by Classification for OCR Results - . Mayce Al-Azawi and Thomas M Breuel 11:30-11:30 ()

› #178 - Efficient OCR Training Data Generation with Aletheia - . Christian Clausner, Stefan Pletschacher and Apostolos Antonacopoulos 11:30-11:30 ()

› #179 - PaRADIIT Project: Main Concepts and Outcomes - . Frédéric Rayar, Jean-Yves Ramel, Pascal Bourquin, Rémi Jimenes, Toshinori Uetani, Sandrine Breuil, Marie-Luce Demonet 11:30-11:30 ()

› #181 - An Android Application for Browsing and Searching in Historical Manuscripts - . Alicia Fornés, Pau Riba and Josep Lladós 11:30-11:30 ()

› #182 - Boosting-based approaches for Arabic text detection in news videos - . Sonia Yousfi, Sid-Ahmed Berrani and Christophe Garcia 11:30-11:30 ()

› #184 - A simple approach to distinguish between Maghrebi and Persian calligraphy in old manuscripts - . Insaf Setitra and Abdelkrim Meziane 11:30-11:30 ()

› #185 - Categorizing a New Collection for Document Recognition Research - . Barri Bruno and Daniel Lopresti 11:30-11:30 ()

› #187 - NOE-EDHI: A trans-disciplinary project to create a platform for demographic forms retro-conversion - . Mickaël Coustaty, Alain Bouju, Pascal Chareille, Jean-Marc Ogier, Arnaud Bringé, Isabelle Seguy and Pierre Darlu 11:30-11:30 ()

Lunch

12:30 - 13:30 (1h)

Lunch

Salon Agnes Sorel - Vinci

Discussion groups

13:30 - 15:30 (2h)

Discussion groups

Room Courteline - Vinci

Marcus Liwicki

Coffee break

15:30 - 16:00 (30min)

Coffee break

Salon Agnes Sorel - Vinci

An Inside Look into ABBYY OCR Technology

16:00 - 16:40 (40min)

An Inside Look into ABBYY OCR Technology

Room Courteline - Vinci

Vladimir Rybkin and Konstantin Anisimovich - ABBYY Europe - Chairman: Koichi Kise

Social Event - Visit of the Amboise Castle

17:30 - 19:15 (1h45)

Social Event - Visit of the Amboise Castle

Banquet (at the Amboise Castle)

19:20 - 23:30 (4h10)

Banquet (at the Amboise Castle)

Oral-6 Super-resolution and born digital document processing (4x20')

8:40 - 10:00 (1h20)

Oral-6 Super-resolution and born digital document processing (4x20')

Room Courteline - Vinci

Chairman: Muhammad Muzzamil Luqman

› #96 - CERMINE - automatic extraction of metadata and references from scientific literature - Dominika Tkaczyk, Pawel Szostek, Piotr Jan Dendek, Mateusz Fedoryszak and Lukasz Bolikowski 08:30-08:50 (20min)

› #52 - End-to-End Conversion of HTML Tables for Populating a Relational Database - George Nagy, David W. Embley and Sharad Seth 08:50-09:10 (20min)

› #60 - Efficient Example-based Super-Resolution of Single Text Images Based on Selective Patch Processing - Nibal Nayef, Joseph Chazalon, Petra Gomez-Krämer and Jean-Marc Ogier 09:10-09:30 (20min)

› #21 - Real-time Document Image Super-Resolution by Fast Matting - Yun Zheng, Xudong Kang, Shutao Li, Yuan He and Jun Sun 09:30-09:50 (20min)

Coffee break

10:00 - 10:30 (30min)

Coffee break

Salon Agnes Sorel - Vinci

Oral-7 Ground truthing and performance evaluation (3x20')

10:30 - 11:30 (1h)

Oral-7 Ground truthing and performance evaluation (3x20')

Room Courteline - Vinci

Chairman: Daniel Lopresti

› #145 - Ground-Truth production in the tranScriptorium project - Basilis Gatos, Georgios Louloudis, Tim Causer, Kris Grint, Verónica Romero, Joan Andreu Sánchez, Alejandro Héctor Toselli and Enrique Vidal 10:30-10:50 (20min)

› #108 - An on-line platform for ground truthing and performance evaluation of text extraction systems - Dimosthenis Karatzas, Sergi Robles Mestre and Lluis Gómez 10:50-11:10 (20min)

› #20 - Ground-truth and Performance Evaluation for Page Layout Analysis of Born-digital Documents - Xin Tao, Zhi Tang and Canhui Xu 11:10-11:30 (20min)

From Academia to Industry, the knowledge transfert in Document Analysis

11:30 - 12:10 (40min)

From Academia to Industry, the knowledge transfert in Document Analysis

Room Courteline - Vinci

Vincent POULAIN D'ANDECY - ITESOFT France - Chairman: Ray Smith

Lunch

12:15 - 13:45 (1h30)

Lunch

Salon Agnes Sorel - Vinci

Teasers-2 (23x1')

13:45 - 14:15 (30min)

Teasers-2 (23x1')

Room Courteline - Vinci

Chairman: Christophe Kermorvant

Poster-2

14:15 - 15:30 (1h15)

Poster-2

Salon Agnes Sorel - Vinci

Chairman: Christophe Kermorvant

› #117 - A study to achieve manga character retrieval method for manga images - . Motoi Iwata, Atsushi Ito and Koichi Kise 14:30-14:30 ()

› #119 - Color descriptor for content-based drawing retrieval - . Christophe Rigaud, Jean-Christophe Burie, Dimosthenis Karatzas and Jean-Marc Ogier 14:30-14:30 ()

› #124 - A Note on Fast Binary Template Matching Application to Manga Copyright Protection - . Mathieu Delalandre, Motoi Iwata and Koichi Kise 14:30-14:30 ()

› #135 - Newspaper Article Extraction Using Hierarchical Fixed Point Model - Anukriti Bansal, Santanu Chaudhury, Sumantra Dutta Roy and J B Srivastava 14:30-14:30 ()

› #138 - A two level algorithm for text detection in natural scene images - . Rong Li, Suyu Wang and Zhixin Shi 14:30-14:30 ()

› #162 - Recognition of Handwritten Mathematical Characters on Whiteboards Using Colour Images - Behrang Sabeghi Saroui, LI 14:30-14:30 ()

› #166 - Forgery Detection Based on Intrinsic Document Contents - Amr Ahmed and Faisal Shafait 14:30-14:30 ()

› #169 - A Seed-Based Segmentation Method for Scene Text Extraction - . Bo Bai, Fei Yin and Cheng-Lin Liu 14:30-14:30 ()

› #19 - Logical Labeling of Fixed Layout PDF Documents Using Multiple Contexts - . Xin Tao, Zhi Tang and Canhui Xu 14:30-14:30 ()

› #30 - Robustness Assessment of Texture Features for the Segmentation of Ancient Documents - . Maroua Mehri, Van Cuong Kieu, Mohamed Mhiri, Pierre Héroux, Petra Gomez-Krämer, Mohamed Ali Mahjoub and Rémy Mullot 14:30-14:30 ()

› #39 - Improving classification of an industrial document image database by combining visual and textual features - . Olivier Augereau, Nicholas Journet, Anne Vialard and Jean Philippe Domenger 14:30-14:30 ()

› #41 - A New One-class Classification Method Based on Symbolic Representation: Application to Document Classification - . Fahimeh Alaei, Nathalie Girard, Sabine Barrat and Jean-Yves Ramel 14:30-14:30 ()

› #46 - The Robustness of a New 3D CAPTHCHA - . Qi Ye, Youbin Chen and Bin Zhu 14:30-14:30 ()

› #5 - Automatic Training Set Generation for Better Historic Document Transcription and Compression - . Gabriel Silva and Rafael Lins 14:30-14:30 ()

› #56 - A New Laplacian Method for Arbitrarily-Oriented Word Segmentation in Video - . Shivakumara Palaiahnakote, Mahamad Suhil, Devanur Guru and Chew Lim Tan 14:30-14:30 ()

› #57 - Separation of Graphics and Scene Text in Video Frames - . Shivakumara Palaiahnakote, N. Vinay Kumar, Devanur Guru and Chew Lim Tan 14:30-14:30 ()

› #67 - Design of Unsupervised Feature Extraction System for On-Line Handwriting Recognition - . Volkmar Frinken, Nilanjana Bhattacharya and Umapada Pal 14:30-14:30 ()

› #71 - AreCAPTCHA: Outsourcing Arabic Text Digitization to Native Speakers - . Menna Bakry, Mohamed Khamis and Slim Abdennadher 14:30-14:30 ()

› #77 - Text Line Segmentation Based on Matched Filtering and Top-down Grouping for Handwritten Documents - . Youbao Tang, Xiangqian Wu and Wei Bu 14:30-14:30 ()

› #80 - Land Map Images Binarization based on Distance Transform and Adaptive Threshold - . Samit Biswas, Sekhar Mandal, Amit Kumar Das and Bhabatosh Chanda 14:30-14:30 ()

› #83 - Graph Model Optimization based Historical Chinese Character Segmentation Method - . Jingning Ji, Liangrui Peng and Bohan Li 14:30-14:30 ()

› #84 - The Maurdor project - Improving automatic processing of digital documents - . Sylvie Brunessaux, Patrick Giroux, Bruno Grilheres, Mathieu Manta, Maylis Bodin, Khalid Choukri, Olivier Galibert and Juliette Kahn 14:30-14:30 ()

› #92 - Empirical Evaluation of CRF-Based Bibliography Extraction from Reference Strings - . Manabu Ohta, Daiki Arauchi, Atsuhiro Takasu and Jun Adachi 14:30-14:30 ()

› #97 - A Complete Logo Detection/Recognition System for Document Images - Alireza ALAEI, LI 14:30-14:30 ()

Coffee break

15:30 - 16:00 (30min)

Coffee break

Salon Agnes Sorel - Vinci

Reports of Discussion Groups

16:00 - 16:45 (45min)

Reports of Discussion Groups

Room Courteline - Vinci

Marcus Liwicki

Concluding Remarks & Awards

16:45 - 17:30 (45min)

Concluding Remarks & Awards

Room Courteline - Vinci