Jove
Visualize
Contact Us

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

MResTNet: A Multi-Resolution Transformer Framework with CNN Extensions for Semantic Segmentation.

Journal of imaging·2024
Same author

HTR for Greek Historical Handwritten Documents.

Journal of imaging·2021
See all related articles
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Oct 9, 2025

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment
06:48

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

9.3K

Word Spotting as a Service: An Unsupervised and Segmentation-Free Framework for Handwritten Documents.

Konstantinos Zagoris1, Angelos Amanatiadis2, Ioannis Pratikakis3

  • 1Department of Computer Science, Neapolis University, Pafos 8042, Cyprus.

Journal of Imaging
|December 23, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a novel word spotting method for historical handwritten documents, utilizing document-oriented local features and spatial context for accurate matching without training data. This approach enables efficient cloud-based word spotting services for mobile devices.

Keywords:
cloud servicedocument-oriented featureshandwritten documentsindexingword spotting

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.2K

Related Experiment Videos

Last Updated: Oct 9, 2025

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment
06:48

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

9.3K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.2K

Area of Science:

  • Computer Science
  • Digital Humanities
  • Information Retrieval

Background:

  • Historical handwritten documents present significant challenges for word spotting due to writing style variations and degradation.
  • Existing word spotting methods often require extensive training data, limiting their applicability to diverse historical collections.

Purpose of the Study:

  • To develop an efficient and effective word spotting method for historical handwritten documents.
  • To enable word spotting as a cloud-based service accessible via mobile devices.

Main Methods:

  • A novel approach using document-oriented local features extracted around keypoints.
  • A matching process incorporating spatial context within a local proximity search.
  • A fast feature matching technique, eliminating the need for training data.

Main Results:

  • The proposed method demonstrates high matching accuracy in word spotting tasks.
  • The system achieves fast retrieval times, indicating high efficiency.
  • Consistent evaluation across several historical handwritten datasets validates the method's performance.

Conclusions:

  • The developed method offers an effective and efficient solution for word spotting in challenging historical handwritten documents.
  • The cloud-based implementation facilitates the deployment of word spotting as a service on modern mobile devices.
  • The absence of training data requirements enhances the method's versatility and applicability.