Low resolution character recognition by dual eigenspace and synthetic degraded patterns

Jun Sun*, Yushinobu Hotta, Yutaka Katsuyama, Satoshi Naoi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

As the rapid progress of digital imaging technology, the requirements of character recognition for text embedded in image increase dramatically. Many image text characters are in low resolution with heavy degradation. Traditional OCR methods don't have good recognition performance on these degraded images due to poor binarization. In this paper, a novel feature extraction method based on dual eigenspace and synthetic pattern generation is proposed to recognize character images under low resolution. A subpixel grayscale normalization method is first used to normalize the low resolution character images. The dual eigenspace performs classification from coarse to fine. The multi-templates generated from the synthetic patterns provide good robustness against real degradation. Experimental results indicate that our method is very effective on low resolution Japanese character images.

Original languageEnglish
Title of host publicationHDP 2004
Subtitle of host publicationProceedings of the First ACM Hardcopy Document Processing Workshop
PublisherAssociation for Computing Machinery (ACM)
Pages15-22
Number of pages8
ISBN (Print)1581139764, 9781581139761
DOIs
Publication statusPublished - 2004
Externally publishedYes
EventHDP 2004: Proceedings of the First ACM Hardcopy Document Processing Workshop - Washington, DC, United States
Duration: 2004 Nov 122004 Nov 12

Publication series

NameHDP 2004: Proceedings of the First ACM Hardcopy Document Processing Workshop

Conference

ConferenceHDP 2004: Proceedings of the First ACM Hardcopy Document Processing Workshop
Country/TerritoryUnited States
CityWashington, DC
Period04/11/1204/11/12

Keywords

  • Character recognition
  • Degradation model
  • Dual eigenspace
  • Grayscale feature extraction

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Low resolution character recognition by dual eigenspace and synthetic degraded patterns'. Together they form a unique fingerprint.

Cite this