Jove
Visualize
Contact Us
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 Videos

Stroke-model-based character extraction from gray-level document images.

X Ye1, M Cheriet, C Y Suen

  • 1Centre for Pattern Recognition and Machine Intelligence, Concordia Univ., Montreal, Que., Canada. xyye@cenparmi.concordia.ca

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|February 8, 2008
PubMed
Summary
This summary is machine-generated.

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

[Research and implications of domestic and international standards and guidelines for soil contamination health risk assessment].

Zhonghua lao dong wei sheng zhi ye bing za zhi = Zhonghua laodong weisheng zhiyebing zazhi = Chinese journal of industrial hygiene and occupational diseases·2026
Same author

A clinicopathological study on the associations between ranulas and autoimmune diseases.

International journal of oral and maxillofacial surgery·2026
Same author

Overexpression of OsLTSD2 decreases cold tolerance in rice.

Plant biology (Stuttgart, Germany)·2026
Same author

Evidence for the Collective Nature of Radial Flow in Pb+Pb Collisions with the ATLAS Detector.

Physical review letters·2026
Same author

Evidence for the Dimuon Decay of the Higgs Boson in pp Collisions with the ATLAS Detector.

Physical review letters·2025
Same author

[Progress in metabolomics of multiple myeloma].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2025
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

GoP-based Quality Enhancement on Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

Traditional character extraction methods fail on complex backgrounds. A new stroke-model and hybrid approach effectively extract characters from diverse backgrounds, improving document analysis.

Area of Science:

  • Computer Vision
  • Image Processing
  • Document Analysis

Background:

  • Global and local thresholding methods are effective for simple backgrounds.
  • These methods are insufficient for complex backgrounds with varying contours and font sizes.

Purpose of the Study:

  • To develop a robust character extraction technique for diverse and complex backgrounds.
  • To improve the efficiency and accuracy of character recognition in document analysis.

Main Methods:

  • A novel stroke-model depicting character features as double-edges is proposed.
  • A hybrid method combines appropriate techniques based on background complexity using class separability.
  • The stroke-model incorporates stroke width for selective thin component detection.

Related Experiment Videos

Main Results:

  • The proposed stroke-model effectively extracts characters from complex backgrounds.
  • The hybrid method efficiently processes documents with both simple and complex backgrounds.
  • Experiments demonstrated successful character extraction from handwriting on checks and machine-printed text in scene images.

Conclusions:

  • The stroke-model and hybrid method offer a significant advancement in character extraction.
  • This approach enhances the reliability of character recognition across various document types and image qualities.
  • The technique is effective for both handwriting and machine-printed character extraction.