Skip to main navigation Skip to search Skip to main content

Author name recognition in degraded journal images

  • Telecom Paris

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A method for extracting names in degraded documents is presented in this article. The documents targeted are images of photocopied scientific journals from various scientific domains. Due to the degradation, there is poor OCR recognition, and pieces of other articles appear on the sides of the image. The proposed approach relies on the combination of a low-level textual analysis and an image-based analysis. The textual analysis extracts robust typographic features, while the image analysis selects image regions of interest through anchor components. We report results on the University of Washington benchmark database.

Original languageEnglish
Title of host publicationDocument Recognition and Retrieval XIII - Proceedings of SPIE-IS and T Electronic Imaging
DOIs
Publication statusPublished - 17 Apr 2006
EventDocument Recognition and Retrieval XIII - San Jose, CA, United States
Duration: 18 Jan 200619 Jan 2006

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6067
ISSN (Print)0277-786X

Conference

ConferenceDocument Recognition and Retrieval XIII
Country/TerritoryUnited States
CitySan Jose, CA
Period18/01/0619/01/06

Keywords

  • Author Name
  • Degraded Documents
  • Journal title pages
  • Neural Network
  • Textual and image-based analysis

Fingerprint

Dive into the research topics of 'Author name recognition in degraded journal images'. Together they form a unique fingerprint.

Cite this