1. Home
  2. Proceedings
  3. DAS
  4. DAS 2018
Default Cover Image

2018 13th IAPR International Workshop on Document Analysis Systems (DAS)

April 24 2018 to April 27 2018

Vienna, Austria

Table of Contents

Title Page iFreely available from IEEE.pp. i-i
Title Page iiiFreely available from IEEE.pp. iii-iii
Copyright PageFreely available from IEEE.pp. iv-iv
Table of ContentsFreely available from IEEE.pp. v-xi
Message from General Chairs and Program ChairsFreely available from IEEE.pp. xii-xiii
Workshop OrganizationFreely available from IEEE.pp. xiv-xiv
Program CommitteeFreely available from IEEE.pp. xv-xv
SponsorsFreely available from IEEE.pp. xvi-xvi
Word Spotting and Recognition Using Deep EmbeddingFull-text access may be available. Sign in or learn about subscription options.pp. 1-6
by Praveen Krishnan, Kartik Dutta, C.V. Jawahar
Learning Deep Representations for Word Spotting under Weak SupervisionFull-text access may be available. Sign in or learn about subscription options.pp. 7-12
by Neha Gurjar, Sebastian Sudholt, Gernot A. Fink
Exploring Critical Aspects of CNN-based Keyword Spotting. A PHOCNet StudyFull-text access may be available. Sign in or learn about subscription options.pp. 13-18
by George Retsinas, Giorgos Sfikas, Nikolaos Stamatopoulos, Georgios Louloudis, Basilis Gatos
CNN Training with Graph-Based Sample Preselection: Application to Handwritten Character RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 19-24
by Frédéric Rayar, Masanori Goto, Seiichi Uchida
Offline Handwriting Recognition on Devanagari Using a New Benchmark DatasetFull-text access may be available. Sign in or learn about subscription options.pp. 25-30
by Kartik Dutta, Praveen Krishnan, Minesh Mathew, C.V. Jawahar
Offline Arabic Handwriting Recognition Using BLSTMs CombinationFull-text access may be available. Sign in or learn about subscription options.pp. 31-36
by Sana Khamekhem Jemni, Yousri Kessentini, Slim Kanoun, Jean-Marc Ogier
Baseline Detection in Historical Documents Using Convolutional U-NetsFull-text access may be available. Sign in or learn about subscription options.pp. 37-42
by Michael Fink, Thomas Layer, Georg Mackenbrock, Michael Sprinzl
Handwriting Recognition of Historical Documents with Few Labeled DataFull-text access may be available. Sign in or learn about subscription options.pp. 43-48
by Edgard Chammas, Chafic Mokbel, Laurence Likforman-Sulem
Graph-Based Keyword Spotting in Historical Documents Using Context-Aware Hausdorff Edit DistanceFull-text access may be available. Sign in or learn about subscription options.pp. 49-54
by Michael Stauffer, Andreas Fischer, Kaspar Riesen
Non-destructive Digitization of Soiled Historical Chinese Bamboo ScrollsFull-text access may be available. Sign in or learn about subscription options.pp. 55-60
by Daniel Stromer, Vincent Christlein, Andreas Maier, Patrick Zippert, Eric Helmecke, Tino Hausotte, Xiaolin Huang
The Robust Reading Competition Annotation and Evaluation PlatformFull-text access may be available. Sign in or learn about subscription options.pp. 61-66
by Dimosthenis Karatzas, Luís Gómez, Anguelos Nicolaou, Marçal Rusiñol
Learning Surrogate Models of Document Image Quality Metrics for Automated Document Image ProcessingFull-text access may be available. Sign in or learn about subscription options.pp. 67-72
by Prashant Singh, Ekta Vats, Anders Hast
Ontology and Framework for Semantic Labelling of Document Data and Software MethodsFull-text access may be available. Sign in or learn about subscription options.pp. 73-78
by Christian Clausner, Apostolos Antonacopoulos
Learning Text Component Features via Convolutional Neural Networks for Scene Text DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 79-84
by Wafa Khlif, Nibal Nayef, Jean-Christophe Burie, Jean-Marc Ogier, Adel Alimi
Text Line Extraction Based on Integrated K-Shortest Paths OptimizationFull-text access may be available. Sign in or learn about subscription options.pp. 85-90
by Liuan Wang, Jun Sun, Seiichi Uchida
A Bidirectional Information Aggregation Architecture for Scene Text DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 91-96
by Xiaoyu Li, Yonghong Song, Yuanlin Zhang
Cutting Sayre's Knot: Reading Scene Text without Segmentation. Application to Utility MetersFull-text access may be available. Sign in or learn about subscription options.pp. 97-102
by Luís Gómez, Marçal Rusiñol, Dimosthenis Karatzas
Online Video Text Detection with Markov Decision ProcessFull-text access may be available. Sign in or learn about subscription options.pp. 103-108
by Xue-Hang Yang, Fei Yin, Cheng-Lin Liu
Vocabulometer: A Web Platform for Document and Reader Mutual AnalysisFull-text access may be available. Sign in or learn about subscription options.pp. 109-114
by Olivier Augereau, Clément Jacquet, Koichi Kise, Nicholas Journet
Comparing Different Feedback Modalities in Assisted Transcription of ManuscriptsFull-text access may be available. Sign in or learn about subscription options.pp. 115-120
by Carlos-D. Martínez-Hinarejos, Emilio Granell-Romero, Verónica Romero-Gómez
Automatic Recovery of Corrupted Font Encoding in PDF Documents Using CNN-based Symbol Recognition with Language ModelFull-text access may be available. Sign in or learn about subscription options.pp. 121-126
by Mark Vol, Andrey Krutko, Nicolas Stefanovitch, Denis Postanogov
Green Interaction for Extracting Family Information from OCR'd BooksFull-text access may be available. Sign in or learn about subscription options.pp. 127-132
by David W. Embley, George Nagy
Comparing Machine Learning Approaches for Table Recognition in Historical Register BooksFull-text access may be available. Sign in or learn about subscription options.pp. 133-138
by Stéphane Clinchant, Hervé Déjean, Jean-Luc Meunier, Eva Maria Lang, Florian Kleber
Table Recognition in Spreadsheets via a Graph RepresentationFull-text access may be available. Sign in or learn about subscription options.pp. 139-144
by Elvis Koci, Maik Thiele, Wolfgang Lehner, Oscar Romero
Printed/Handwritten Texts and Graphics Separation in Complex Documents Using Conditional Random FieldsFull-text access may be available. Sign in or learn about subscription options.pp. 145-150
by Xiao-Hui Li, Fei Yin, Cheng-Lin Liu
Symbol Detection in Online Handwritten Graphics Using Faster R-CNNFull-text access may be available. Sign in or learn about subscription options.pp. 151-156
by Frank D. Julca-Aguilar, Nina S. T. Hirata
A Free-Sketch Recognition Method for Chemical Structural FormulaFull-text access may be available. Sign in or learn about subscription options.pp. 157-162
by Penghui Sun, Yan Chen, Xiaoqing Lyu, Bei Wang, Jingwei Qu, Zhi Tang
Handwritten Music Object Detection: Open Issues and Baseline ResultsFull-text access may be available. Sign in or learn about subscription options.pp. 163-168
by Alexander Pacha, Kwon-Young Choi, Bertrand Coüasnon, Yann Ricquebourg, Richard Zanibbi, Horst Eidenberger
Encoding CNN Activations for Writer RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 169-174
by Vincent Christlein, Andreas Maier
Gaussian Process Classification as Metric Learning for Forensic Writer IdentificationFull-text access may be available. Sign in or learn about subscription options.pp. 175-180
by Fredrik Wahlberg
Stable Regions and Object Fill-Based Approach for Document Images WatermarkingFull-text access may be available. Sign in or learn about subscription options.pp. 181-186
by Cu Vinh Loc, Jean-Christophe Burie, Jean-Marc Ogier
Towards Detection of Morphed Face Images in Electronic Travel DocumentsFull-text access may be available. Sign in or learn about subscription options.pp. 187-192
by Ulrich Scherhag, Christian Rathgeb, Christoph Busch
Feature Fusion for Scene Text DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 193-198
by Zhen Zhu, Minghui Liao, Baoguang Shi, Xiang Bai
From Extraction to Spotting for Cuneiform Script AnalysisFull-text access may be available. Sign in or learn about subscription options.pp. 199-204
by Bartosz Bogacz, Hubert Mara
Handwriting Identification of Short Historical ManuscriptsFull-text access may be available. Sign in or learn about subscription options.pp. 205-210
by Piercarlo Dondi, Alessandro Danani, Luca Lombardi, Marco Malagodi, Maurizio Licchelli
A Multi-faceted OCR Framework for Artificial Urdu News Ticker Text RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 211-216
by Sami-Ur-Rehman, Burhan Ul Tayyab, Muhammad Ferjad Naeem, Adnan Ul-Hasan, Faisal Shafait
Deep Learning for Classification and as Tapped-Feature Generator in Medieval Word-Image RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 217-222
by Sukalpa Chanda, Emmanuel Okafor, Sebastien Hamel, Dominique Stutzmann, Lambert Schomaker
Synthetically Generated Semantic Codebook for Bag-of-Visual-Words Based Word SpottingFull-text access may be available. Sign in or learn about subscription options.pp. 223-228
by David Aldavert, Marçal Rusiñol
Word Spotting Using Convolutional Siamese NetworkFull-text access may be available. Sign in or learn about subscription options.pp. 229-234
by Berat Kurar Barakat, Reem Alasam, Jihad El-Sana
Compact Binary Feature for Open Set RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 235-238
by Han Xiao, Jun Sun, Xiaoyi Yu, Liuan Wang
InDUS: Incremental Document Understanding System Focus on Document ClassificationFull-text access may be available. Sign in or learn about subscription options.pp. 239-244
by Vincent Poulain d'Andecy, Aurélie Joseph, Jean-Marc Ogier
Feature Selection for Document Flow SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 245-250
by Ahmed Hamdi, Mickaël Coustaty, Aurélie Joseph, Vincent Poulain d'Andecy, Antoine Doucet, Jean-Marc Ogier
Field Extraction by Hybrid Incremental and A-Priori Structural TemplatesFull-text access may be available. Sign in or learn about subscription options.pp. 251-256
by Vincent Poulain d'Andecy, Emmanuel Hartmann, Marçal Rusiñol
Comics Story Representation System Based on GenreFull-text access may be available. Sign in or learn about subscription options.pp. 257-262
by Yuki Daiku, Motoi Iwata, Olivier Augereau, Koichi Kise
Document Image Binarization Using Recurrent Neural NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 263-268
by Florian Westphal, Niklas Lavesson, Håkan Grahn
Offset Neural Network for Document Orientation IdentificationFull-text access may be available. Sign in or learn about subscription options.pp. 269-274
by Ruochen Wang, Song Wang, Jun Sun
Predicting Mobile-Captured Document Images Sharpness QualityFull-text access may be available. Sign in or learn about subscription options.pp. 275-280
by Quang Anh Bui, David Molard, Salvatore Tabbone
Document Bleed-Through Removal Using Sparse Image InpaintingFull-text access may be available. Sign in or learn about subscription options.pp. 281-286
by Muhammad Hanif, Anna Tonazzini, Pasquale Savino, Emanuele Salerno, Gregory Tsagkatakis
Fully Convolutional Neural Networks for Page Segmentation of Historical Document ImagesFull-text access may be available. Sign in or learn about subscription options.pp. 287-292
by Christoph Wick, Frank Puppe
Manuscript Text Line Detection and Segmentation Using Second-Order DerivativesFull-text access may be available. Sign in or learn about subscription options.pp. 293-298
by David Aldavert, Marçal Rusiñol
Layout Error Correction Using Deep Neural NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 299-304
by Srie Raam Mohan, Syed Saqib Bukhari, Andreas Dengel
A Sequence Labeling Based Approach for Character Segmentation of Historical DocumentsFull-text access may be available. Sign in or learn about subscription options.pp. 305-310
by Liangcai Gao, Xiaode Zhang, Zhi Tang, Yaoxiong Huang, Lianwen Jin
On the Similarities of Fingerprints and Railroad Tracks: Using Minutiae Detection Algorithms to Digitize Track PlansFull-text access may be available. Sign in or learn about subscription options.pp. 311-316
by Maximilian Klockmann, Marco Filax, Frank Ortmeier, Martin Reiß
Contained Neural Style Transfer for Decorated Logo GenerationFull-text access may be available. Sign in or learn about subscription options.pp. 317-322
by Gantugs Atarsaikhan, Brian Kenji Iwana, Seiichi Uchida
anyAlign: An Intelligent and Interactive Text-Alignment Web-Application for Historical DocumentFull-text access may be available. Sign in or learn about subscription options.pp. 323-327
by Syed Saqib Bukhari, Manabendra Saha, Praveen Badimala, Manesh Kumar Lohano, Andreas Dengel
Automatic Alignment of Handwritten Images and Transcripts for Training Handwritten Text Recognition SystemsFull-text access may be available. Sign in or learn about subscription options.pp. 328-333
by Verónica Romero-Gómez, Alejandro H. Toselli, Vicente Bosch, Joan Andreu Sánchez, Enrique Vidal
Web Services in Document Image Analysis - Recent Developments on DIVAServices and the Importance of Building an EcosystemFull-text access may be available. Sign in or learn about subscription options.pp. 334-339
by Marcel Würsch, Marcus Liwicki, Rolf Ingold
A Semi-automatized Modular Annotation Tool for Ancient Manuscript AnnotationFull-text access may be available. Sign in or learn about subscription options.pp. 340-344
by Mathias Seuret, Manuel Bouillon, Fotini Simistira, Marcel Würsch, Marcus Liwicki, Rolf Ingold
A First Step Toward a Fair Comparison of Evaluation Protocols for Text Detection AlgorithmsFull-text access may be available. Sign in or learn about subscription options.pp. 345-350
by Aliona Dangla, Elodie Puybareau, Guillaume Tochon, Jonathan Fabrizio
READ-BAD: A New Dataset and Evaluation Scheme for Baseline Detection in Archival DocumentsFull-text access may be available. Sign in or learn about subscription options.pp. 351-356
by Tobias Grüning, Roger Labahn, Markus Diem, Florian Kleber, Stefan Fiel
ZoneMapAlt: An Alternative to the ZoneMap Metric for Zone Segmentation and ClassificationFull-text access may be available. Sign in or learn about subscription options.pp. 357-362
by Romain Karpinski, Abdel Belaid
"Quality" vs. "Readability" in Document Images: Statistical Analysis of Human PerceptionFull-text access may be available. Sign in or learn about subscription options.pp. 363-368
by Alireza Alaei, Romain Raveaux, Donatello Conte, Bela Stantic
Evaluation of Gist Operator for Document Image RetrievalFull-text access may be available. Sign in or learn about subscription options.pp. 369-374
by Fahimeh Alaei, Alireza Alaei, Umapada Pal, Michael Blumenstein
A New Descriptor for Pattern Matching: Application to Identity Document VerificationFull-text access may be available. Sign in or learn about subscription options.pp. 375-380
by Nabil Ghanmi, Ahmad Montaser Awal
Offline Bengali Writer Verification by PDF-CNN and Siamese NetFull-text access may be available. Sign in or learn about subscription options.pp. 381-386
by Chandranath Adak, Simone Marinai, Bidyut B. Chaudhuri, Michael Blumenstein
Saliency-Based Detection of Identy Documents Captured by SmartphonesFull-text access may be available. Sign in or learn about subscription options.pp. 387-392
by Minh Ôn Vũ Ngoc, Jonathan Fabrizio, Thierry Géraud
Automated Forgery Detection in Multispectral Document Images Using Fuzzy ClusteringFull-text access may be available. Sign in or learn about subscription options.pp. 393-398
by Muhammad Jaleed Khan, Adeel Yousaf, Khurram Khurshid, Asad Abbas, Faisal Shafait
Joint Recognition of Handwritten Text and Named Entities with a Neural End-to-End ModelFull-text access may be available. Sign in or learn about subscription options.pp. 399-404
by Manuel Carbonell, Mauricio Villegas, Alicia Fornés, Josep Lladós
Multi-dimensional Connectionist Classification: Reading Text in One StepFull-text access may be available. Sign in or learn about subscription options.pp. 405-410
by Martin Schall, Marc-Peter Schambach, Matthias O. Franz
Does Deeper Network Lead to Better Accuracy: A Case Study on Handwritten Devanagari CharactersFull-text access may be available. Sign in or learn about subscription options.pp. 411-416
by Bappaditya Chakraborty, Bikash Shaw, Jayanta Aich, Ujjwal Bhattacharya, Swapan Kumar Parui
Hand Written Characters Recognition via Deep Metric LearningFull-text access may be available. Sign in or learn about subscription options.pp. 417-422
by Shah Nawaz, Alessandro Calefati, Nisar Ahmed, Ignazio Gallo
Improving OCR Accuracy on Early Printed Books by Utilizing Cross Fold Training and VotingFull-text access may be available. Sign in or learn about subscription options.pp. 423-428
by Christian Reul, Uwe Springmann, Christoph Wick, Frank Puppe
OCR Error Correction: State-of-the-Art vs an NMT-based ApproachFull-text access may be available. Sign in or learn about subscription options.pp. 429-434
by Kareem Mokhtar, Syed Saqib Bukhari, Andreas Dengel
An Efficient Feature Vector for Segmentation-Free Recognition of Online Cursive Handwriting Based on a Hybrid Deep Neural NetworkFull-text access may be available. Sign in or learn about subscription options.pp. 435-440
by Partha Sarathi Mukherjee, Ujjwal Bhattacharya, Swapan Kumar Parui
Knowledge Transfer Using Neural Network Based Approach for Handwritten Text RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 441-446
by Rathin Radhakrishnan Nair, Nishant Sankaran, Bharagava Urala Kota, Sergey Tulyakov, Srirangaraj Setlur, Venu Govindaraju
Optical Character Recognition for Sanskrit Using Convolution Neural NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 447-452
by Meduri Avadesh, Navneet Goyal
Author IndexFreely available from IEEE.pp. 453-455
[Publisher's information]Freely available from IEEE.pp. 456-456
Showing 86 out of 86