A Combined System for Text Line Extraction and Handwriting Recognition in Historical Documents

被引：11
|
作者：
Fischer, Andreas [1 ]
Baechler, Micheal [2 ]
Garz, Angelika [2 ]
Liwicki, Marcus [2 ]
Ingold, Rolf [2 ]
机构：
[1] Polytech Montreal, Dept Elect Engn, Montreal, PQ, Canada
[2] Univ Fribourg, Dept Informat, CH-1700 Fribourg, Switzerland
来源：
2014 11TH IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS (DAS 2014) | 2014年
关键词：
SEGMENTATION; WORDS;
D O I：
10.1109/DAS.2014.51
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Automated reading of historical handwriting is needed to search and browse ancient manuscripts in digital libraries based on their textual content. In this paper, we present a combined system for text localization and transcription in page images. It includes flexible learning-based methods for layout analysis and handwriting recognition, which were developed in the context of the Swiss research project HisDoc. A comprehensive experimental evaluation is provided for the medieval Parzival database, demonstrating a promising word recognition accuracy of 93.0% with closed vocabulary. In order to harmonize the evaluation of the two document analysis tasks, we introduce a novel evaluation measure for text line extraction that takes substitution, deletion, as well as insertion errors into account.
引用
收藏
页码：71 / 75
页数：5
相关论文
共 50 条
  • [1] Text Line Extraction in Handwritten Historical Documents
    Capobianco, Samuele
    Marinai, Simone
    DIGITAL LIBRARIES AND ARCHIVES, IRCDL 2017, 2017, 733 : 68 - 79
  • [2] Improving Handwriting Recognition for Historical Documents Using Synthetic Text Lines
    Spoto, Martin
    Wolf, Beat
    Fischer, Andreas
    Scius-Bertrand, Anna
    INTERTWINING GRAPHONOMICS WITH HUMAN MOVEMENTS, IGS 2021, 2022, 13424 : 61 - 75
  • [3] Skew Correction and Text Line Extraction of Arabic Historical Documents
    Zoizon, Abdelhay
    Zarghili, Ars Alane
    Chaker, Ilham
    ARABIC LANGUAGE PROCESSING: FROM THEORY TO PRACTICE, ICALP 2019, 2019, 1108 : 181 - 193
  • [4] Transfer Learning for Handwriting Recognition on Historical Documents
    Granet, Adeline
    Morin, Emmanuel
    Mouchere, Harold
    Quiniou, Solen
    Viard-Gaudin, Christian
    PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION APPLICATIONS AND METHODS (ICPRAM 2018), 2018, : 432 - 439
  • [5] Fast handwriting recognition for indexing historical documents
    Govindaraju, V
    Xue, HH
    FIRST INTERNATIONAL WORKSHOP ON DOCUMENT IMAGE ANALYSIS FOR LIBRARIES, PROCEEDINGS, 2004, : 314 - 320
  • [6] CHARACTER PROTOTYPE SELECTION FOR HANDWRITING RECOGNITION IN HISTORICAL DOCUMENTS
    Fischer, Andreas
    Bunke, Horst
    19TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO-2011), 2011, : 1435 - 1439
  • [7] Handwriting Recognition of Historical Documents with few labeled data
    Chammas, Edgard
    Mokbel, Chafic
    Likforman-Sulem, Laurence
    2018 13TH IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS (DAS), 2018, : 43 - 48
  • [8] Text line segmentation and word recognition in a system for general writer independent handwriting recognition
    Marti, UV
    Bunke, H
    SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 159 - 163
  • [9] Text Line Extraction in Historical Documents Using Mask R-CNN
    Droby, Ahmad
    Barakat, Berat Kurar
    Alaasam, Reem
    Madi, Boraq
    Rabaev, Irina
    El-Sana, Jihad
    SIGNALS, 2022, 3 (03): : 535 - 549
  • [10] Combining Handwriting and Speech Recognition for Transcribing Historical Handwritten Documents
    Granell, Emilio
    Martinez-Hinarejos, Carlos-D.
    2015 13TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), 2015, : 126 - 130
12345