Call for Papers

Special Issue on Camera-based Text and Document Recognition

Guest Editor: Dr. Majid Mirmehdi, University of Bristol

NEW Submission Deadline: December 15th 2003


PDF copy of this page

The last few years have seen a substantial increase in the use of digital cameras and web-cams, and the next few years will witness a similar increase in the use of camera-enabled mobile devices such as PDAs and mobile phones. Utilization of these devices will become more demanding and users will expect them to perform more intelligent tasks. The aim of this special issue is to consider the problems and solutions associated with document analysis and recognition using digital, mobile, and wearable image acquisition devices. All such devices are ideal for capturing textual and graphical information, both to save as an image and to understand further by performing OCR and extracting text and figures.

The application areas include the point-and-click scanning of text, capturing and extracting text for storing or translating notices, billboards, shop-signs, transforming text to audio for the visually-impaired, for navigation by reading road signs, and many more. Some of the typical problem areas are the recovery of text in perspective views, on non-planar surfaces, and in low-resolution scenes. Also, motion blurring and unsteady hands can lead to noisier images and more complex scenarios. All these and other related problems need to be addressed and this special issue aims to show how the document recognition community, academic and industrial, is aiming to handle document analysis and recognition for hand-held and mobile cameras.

Authors are encouraged to submit papers which cover some of the following topics (although this list is by no means exhaustive):

  • Using cameras for document capture.
  • Document capture and understanding for handheld mobile devices, e.g. camera-enabled mobile phones and camera or laser-enabled PDAs.
  • Document capture and understanding for wearable camera devices.
  • Extraction of textual information from the environment.
  • Point-and-click text capture and understanding.
  • Methods of perspective recovery, e.g. of planar text surfaces.
  • Novel OCR techniques for understanding low-resolution text captured on the fly.
  • Desktop Computing.
  • Other related topics...


TIMETABLE

Submission Deadline:  December 15th 2003
Review by:  March 2004
Revised Manuscripts by:  May 2004
Editor's Decisions:  June 2004
Final publication:  September/October 2004


SUBMISSION GUIDELINES

Prospective authors are invited to submit their manuscripts electronically according to the instructions on the IJDAR www page (http://ijdar.cfar.umd.edu). Manuscripts will then also be distributed electronically to reviewers to speed up the reviewing process. Any questions can be sent to the Guest Editor (majid@cs.bris.ac.uk) with a cc to the editorial office (ijdar@cfar.umd.edu).


GUEST EDITOR

Dr. Majid Mirmehdi,
Department of Computer Science,
University of Bristol,
Merchant Venturers Building,
Woodland Road,
Bristol BS8 1UB
England
Tel: +44 (0)117-954 5139
Fax: +44 (0)117-954 5208
Email: majid@cs.bris.ac.uk

Single sheet PDF copy of this page