poster

Active learning strategies for handwritten text transcription

Authors:

Nicolás Serrano,

Adrià Giménez,

Albert Sanchis,

Alfons JuanAuthors Info & Claims

ICMI-MLMI '10: International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction

Article No.: 48, Pages 1 - 4

https://doi.org/10.1145/1891903.1891962

Published: 08 November 2010 Publication History

Get Access

Abstract

Active learning strategies are being increasingly used in a variety of real-world tasks, though their application to handwritten text transcription in old manuscripts remains nearly unexplored. The basic idea is to follow a sequential, line-byline transcription of the whole manuscript in which a continuously retrained system interacts with the user to efficiently transcribe each new line. This approach has been recently explored using a conventional strategy by which the user is only asked to supervise words that are not recognized with high confidence. In this paper, the conventional strategy is improved by also letting the system to recompute most probable hypotheses with the constraints imposed by user supervisions. In particular, two strategies are studied which differ in the frequency of hypothesis recomputation on the current line: after each (iterative) or all (delayed) user corrections. Empirical results are reported on two real tasks showing that these strategies outperform the conventional approach.

References

[1]

T. Kristjannson, A. Culotta, P. Viola, and A. McCallum. Interactive information extraction with constrained conditional random fields. In AAAI 2004, pages 412--418, San Jose, CA (USA).

Digital Library

Google Scholar

[2]

D. Pérez et al. The GERMANA database. In ICDAR 2009, pages 301--305, Barcelona (Spain).

Digital Library

Google Scholar

[3]

N. Serrano, F. Castro, and A. Juan. The RODRIGO database. In LREC 2010, pages 2709--2712, Valleta (Malta).

Google Scholar

[4]

N. Serrano, D. Pérez, A. Sanchis, and A. Juan. Adaptation from Partially Supervised Handwritten Text Transcriptions. In ICMI-MLMI 2009, pages 289--292, Cambridge, MA (USA).

Digital Library

Google Scholar

[5]

N. Serrano, A. Sanchis, and A. Juan. Balancing error and supervision effort in interactive-predictive handwriting recognition. In IUI 2010, pages 373--376, Hong Kong (China).

Digital Library

Google Scholar

[6]

N. Serrano, L. Tarazón, D. Pérez, O. Ramos-Terrades, and A. Juan. The GIDOC prototype. In PRIS 2010, Funchal (Portugal).

Google Scholar

[7]

B. Settles. Active learning literature survey. Computer Sciences Technical Report 1648, University of Wisconsin--Madison, 2009.

Google Scholar

[8]

A. H. Toselli, V. Romero, L. Rodríguez, and E. Vidal. Computer Assisted Transcription of Handwritten Text. In ICDAR 2007, pages 944--948, Curitiba (Brazil).

Digital Library

Google Scholar

Cited By

View all

Hast ACullhed PVats EAbrate M(2019)Making Large Collections of Handwritten Material Easily Accessible and SearchableDigital Libraries: Supporting Open Science10.1007/978-3-030-11226-4_2(18-28)Online publication date: 15-Jan-2019
https://doi.org/10.1007/978-3-030-11226-4_2
Quiros LBosch VSerrano LToselli AVidal E(2018)From HMMs to RNNs: Computer-Assisted Transcription of a Handwritten Notarial Records Collection2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR)10.1109/ICFHR-2018.2018.00029(116-121)Online publication date: Aug-2018
https://doi.org/10.1109/ICFHR-2018.2018.00029
Hast ACullhed PVats E(2017)$$\textit{TexT}$$ TexT - Text Extractor Tool for Handwritten Document Transcription and AnnotationDigital Libraries and Multimedia Archives10.1007/978-3-319-73165-0_8(81-92)Online publication date: 21-Dec-2017
https://doi.org/10.1007/978-3-319-73165-0_8
Show More Cited By

Index Terms

Active learning strategies for handwritten text transcription
1. Applied computing
  1. Document management and text processing
    1. Document capture
      1. Document analysis
      2. Optical character recognition
2. Human-centered computing
  1. Human computer interaction (HCI)
    1. Interactive systems and tools

Recommendations

Balancing error and supervision effort in interactive-predictive handwriting recognition
IUI '10: Proceedings of the 15th international conference on Intelligent user interfaces

An effective approach to transcribe handwritten text documents is to follow an interactive-predictive paradigm in which both, the system is guided by the user, and the user is assisted by the system to complete the transcription task as efficiently as ...
Offline arabic handwritten text recognition: A Survey

Research in offline Arabic handwriting recognition has increased considerably in the past few years. This is evident from the numerous research results published recently in major journals and conferences in the area of handwriting recognition. Features ...
Adaptation from partially supervised handwritten text transcriptions
ICMI-MLMI '09: Proceedings of the 2009 international conference on Multimodal interfaces

An effective approach to transcribe handwritten text documents is to follow an interactive-predictive paradigm in which both, the system is guided by the user, and the user is assisted by the system to complete the transcription task as efficiently as ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

ICMI-MLMI '10: International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction

November 2010

311 pages

ISBN:9781450304146

DOI:10.1145/1891903

General Chairs:
Wen Gao
PKU, China
,
Chin-Hui Lee
Georgia Tech
,
Jie Yang
Carnegie Mellon
,
Program Chairs:
Xilin Chen
ICT, CAS, China
,
Maxine Eskenazi
Carnegie Mellon
,
Zhengyou Zhang
MSR

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 November 2010

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Poster

Funding Sources

Conference

ICMI-MLMI '10

Sponsor:

SIGCHI

ICMI-MLMI '10: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERFACES/WORKSHOP ON MACHINE LEARNING FOR MULTIMODAL INTERFACES

November 8 - 10, 2010

Beijing, China

Acceptance Rates

ICMI-MLMI '10 Paper Acceptance Rate 41 of 100 submissions, 41%;

Overall Acceptance Rate 453 of 1,080 submissions, 42%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
102
Total Downloads

Downloads (Last 12 months)1
Downloads (Last 6 weeks)0

Reflects downloads up to 19 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Hast ACullhed PVats EAbrate M(2019)Making Large Collections of Handwritten Material Easily Accessible and SearchableDigital Libraries: Supporting Open Science10.1007/978-3-030-11226-4_2(18-28)Online publication date: 15-Jan-2019
https://doi.org/10.1007/978-3-030-11226-4_2
Quiros LBosch VSerrano LToselli AVidal E(2018)From HMMs to RNNs: Computer-Assisted Transcription of a Handwritten Notarial Records Collection2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR)10.1109/ICFHR-2018.2018.00029(116-121)Online publication date: Aug-2018
https://doi.org/10.1109/ICFHR-2018.2018.00029
Hast ACullhed PVats E(2017)$$\textit{TexT}$$ TexT - Text Extractor Tool for Handwritten Document Transcription and AnnotationDigital Libraries and Multimedia Archives10.1007/978-3-319-73165-0_8(81-92)Online publication date: 21-Dec-2017
https://doi.org/10.1007/978-3-319-73165-0_8
Serrano NCivera JSanchis AJuan A(2014)Effective balancing error and user effort in interactive handwriting recognitionPattern Recognition Letters10.1016/j.patrec.2013.03.01037(135-142)Online publication date: 1-Feb-2014
https://dl.acm.org/doi/10.1016/j.patrec.2013.03.010
Serrano NGiménez ACivera JSanchis AJuan A(2014)Interactive handwriting recognition with limited user effortInternational Journal on Document Analysis and Recognition10.1007/s10032-013-0204-517:1(47-59)Online publication date: 1-Mar-2014
https://dl.acm.org/doi/10.1007/s10032-013-0204-5
Alabau VLeiva LKonstan JChi EHöök K(2012)Transcribing handwritten text images with a word soup gameCHI '12 Extended Abstracts on Human Factors in Computing Systems10.1145/2212776.2223788(2273-2278)Online publication date: 5-May-2012
https://dl.acm.org/doi/10.1145/2212776.2223788
del Agua MSerrano NCivera JJuan A(2012)Character-Based Handwritten Text Recognition of Multilingual DocumentsAdvances in Speech and Language Technologies for Iberian Languages10.1007/978-3-642-35292-8_20(187-196)Online publication date: 2012
https://doi.org/10.1007/978-3-642-35292-8_20
del Agua MSerrano NJuan A(2011)Language identification for interactive handwriting transcription of multilingual documentsProceedings of the 5th Iberian conference on Pattern recognition and image analysis10.5555/2021341.2021423(596-603)Online publication date: 8-Jun-2011
https://dl.acm.org/doi/10.5555/2021341.2021423
del Agua MSerrano NJuan A(2011)Language Identification for Interactive Handwriting Transcription of Multilingual DocumentsPattern Recognition and Image Analysis10.1007/978-3-642-21257-4_74(596-603)Online publication date: 2011
https://doi.org/10.1007/978-3-642-21257-4_74

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Balancing error and supervision effort in interactive-predictive handwriting recognition

Offline arabic handwritten text recognition: A Survey

Adaptation from partially supervised handwritten text transcriptions