Document Analysis Systems: 14th IAPR International Workshop, DAS 2020, Wuhan, China, July 26–29, 2020, Proceedings (Lecture Notes in Computer Science Book 12116)

This book constitutes the refereed proceedings of the 14th IAPR International Workshop on Document Analysis Systems, DAS 2020, held in Wuhan, China, in July 2020. The 40 full papers presented in this book were carefully reviewed and selected from 57 submissions. The papers are grouped in the following topical sections: character and text recognition; document image processing; segmentation and layout analysis; word embedding and spotting; text detection; and font design and classification. Due to the Corona pandemic the conference was held as a virtual event . Front Matter ....Pages i-xiv Front Matter ....Pages 1-1 Maximum Entropy Regularization and Chinese Text Recognition (Changxu Cheng, Wuheng Xu, Xiang Bai, Bin Feng, Wenyu Liu)....Pages 3-17 An Improved Convolutional Block Attention Module for Chinese Character Recognition (Kai Zhou, Yongsheng Zhou, Rui Zhang, Xiaolin Wei)....Pages 18-29 Adapting OCR with Limited Supervision (Deepayan Das, C. V. Jawahar)....Pages 30-44 High Performance Offline Handwritten Chinese Text Recognition with a New Data Preprocessing and Augmentation Pipeline (Canyu Xie, Songxuan Lai, Qianying Liao, Lianwen Jin)....Pages 45-59 ALEC: An Accurate, Light and Efficient Network for CAPTCHA Recognition (Nan Li, Qianyi Jiang, Qi Song, Rui Zhang, Xiaolin Wei)....Pages 60-73 A Benchmark System for Indian Language Text Recognition (Krishna Tulsyan, Nimisha Srivastava, Ajoy Mondal, C. V. Jawahar)....Pages 74-88 Classification of Phonetic Characters by Space-Filling Curves (Valentin Owczarek, Jordan Drapeau, Jean-Christophe Burie, Patrick Franco, Mickaël Coustaty, Rémy Mullot et al.)....Pages 89-100 Front Matter ....Pages 101-101 Self-supervised Representation Learning on Document Images (Adrian Cosma, Mihai Ghidoveanu, Michael Panaitescu-Liess, Marius Popescu)....Pages 103-117 ACMU-Nets: Attention Cascading Modular U-Nets Incorporating Squeeze and Excitation Blocks (Seokjun Kang, Brian Kenji Iwana, Seiichi Uchida)....Pages 118-130 Dewarping Document Image by Displacement Flow Estimation with Fully Convolutional Network (Guo-Wang Xie, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu)....Pages 131-144 Building Super-Resolution Image Generator for OCR Accuracy Improvement (Xujun Peng, Chao Wang)....Pages 145-160 Faster Glare Detection on Document Images (Dmitry Rodin, Andrey Zharkov, Ivan Zagaynov)....Pages 161-167 Camera Captured DIQA with Linearity and Monotonicity Constraints (Xujun Peng, Chao Wang)....Pages 168-181 Background Removal of French University Diplomas (Tanmoy Mondal, Mickaël Coustaty, Petra Gomez-Krämer, Jean-Marc Ogier)....Pages 182-196 Front Matter ....Pages 197-197 The Benefits of Close-Domain Fine-Tuning for Table Detection in Document Images (Ángela Casado-García, César Domínguez, Jónathan Heras, Eloy Mata, Vico Pascual)....Pages 199-215 IIIT-AR-13K: A New Dataset for Graphical Object Detection in Documents (Ajoy Mondal, Peter Lipps, C. V. Jawahar)....Pages 216-230 Page Segmentation Using Convolutional Neural Network and Graphical Model (Xiao-Hui Li, Fei Yin, Cheng-Lin Liu)....Pages 231-245 The Notary in the Haystack – Countering Class Imbalance in Document Processing with CNNs (Martin Leipert, Georg Vogeler, Mathias Seuret, Andreas Maier, Vincent Christlein)....Pages 246-261 Evaluation of Neural Network Classification Systems on Document Stream (Joris Voerman, Aurélie Joseph, Mickael Coustaty, Vincent Poulain d’Andecy, Jean-Marc Ogier)....Pages 262-276 Computerized Counting of Individuals in Ottoman Population Registers with Deep Learning (Yekta Said Can, Mustafa Erdem Kabadayı)....Pages 277-290 Front Matter ....Pages 291-291 Annotation-Free Learning of Deep Representations for Word Spotting Using Synthetic Data and Self Labeling (Fabian Wolf, Gernot A. Fink)....Pages 293-308 Fused Text Recogniser and Deep Embeddings Improve Word Recognition and Retrieval (Siddhant Bansal, Praveen Krishnan, C. V. Jawahar)....Pages 309-323 A Named Entity Extraction System for Historical Financial Data (Wassim Swaileh, Thierry Paquet, Sébastien Adam, Andres Rojas Camacho)....Pages 324-340 Effect of Text Color on Word Embeddings (Masaya Ikoma, Brian Kenji Iwana, Seiichi Uchida)....Pages 341-355 Document Data Extraction System Based on Visual Words Codebook (Vasily Loginov, Aleksandr Valiukov, Stanislav Semenov, Ivan Zagaynov)....Pages 356-370 Automated Transcription for Pre-modern Japanese Kuzushiji Documents by Random Lines Erasure and Curriculum Training (Anh Duc Le)....Pages 371-382 Representative Image Selection for Data Efficient Word Spotting (Florian Westphal, Håkan Grahn, Niklas Lavesson)....Pages 383-397 Named Entity Recognition in Semi Structured Documents Using Neural Tensor Networks (Khurram Shehzad, Adnan Ul-Hasan, Muhammad Imran Malik, Faisal Shafait)....Pages 398-409 Front Matter ....Pages 411-411 SickZil-Machine: A Deep Learning Based Script Text Isolation System for Comics Translation (U-Ram Ko, Hwan-Gue Cho)....Pages 413-425 Lyric Video Analysis Using Text Detection and Tracking (Shota Sakaguchi, Jun Kato, Masataka Goto, Seiichi Uchida)....Pages 426-440 Fast and Lightweight Text Line Detection on Historical Documents (Aleksei Melnikov, Ivan Zagaynov)....Pages 441-450 From Automatic Keyword Detection to Ontology-Based Topic Modeling (Marc Beck, Syed Tahseen Raza Rizvi, Andreas Dengel, Sheraz Ahmed)....Pages 451-465 A New Context-Based Method for Restoring Occluded Text in Natural Scene Images (Ayush Mittal, Palaiahnakote Shivakumara, Umapada Pal, Tong Lu, Michael Blumenstein, Daniel Lopresti)....Pages 466-480 New Benchmarks for Barcode Detection Using Both Synthetic and Real Data (Andrey Zharkov, Andrey Vavilin, Ivan Zagaynov)....Pages 481-493 Front Matter ....Pages 495-495 Character-Independent Font Identification (Daichi Haraguchi, Shota Harada, Brian Kenji Iwana, Yuto Shinahara, Seiichi Uchida)....Pages 497-511 A New Common Points Detection Method for Classification of 2D and 3D Texts in Video/Scene Images (Lokesh Nandanwar, Palaiahnakote Shivakumara, Ahlad Kumar, Tong Lu, Umapada Pal, Daniel Lopresti)....Pages 512-528 Analysis of Typefaces Designed for Readers with Developmental Dyslexia (Xinru Zhu, Kyo Kageura, Shin’ichi Satoh)....Pages 529-543 Neural Style Difference Transfer and Its Application to Font Generation (Gantugs Atarsaikhan, Brian Kenji Iwana, Seiichi Uchida)....Pages 544-558 A Method for Scene Text Style Transfer (Gaojing Zhou, Lei Wang, Xi Liu, Yongsheng Zhou, Rui Zhang, Xiaolin Wei)....Pages 559-571 Re-Ranking for Writer Identification and Writer Retrieval (Simon Jordan, Mathias Seuret, Pavel Král, Ladislav Lenc, Jiří Martínek, Barbara Wiermann et al.)....Pages 572-586 Back Matter ....Pages 587-588