Combining Statistical Measures to Find Image Text Regions

Paul Clark, A Sanfeliu, Majid Mirmehdi, J J Villanueva, M Vanrell, R Alquezar, J-O Eklundh, Y Aloimonos

Research output: Contribution to journalArticle (Academic Journal)peer-review

Abstract

We present a method based on statistical properties of local image pixels for focussing attention on regions of text in arbitrary scenes where the text plane is not necessarily fronto-parallel to the camera. This is particularly useful for Desktop or Wearable Computing applications. The statistical measures are cho sen to reveal charactersitic properties of text. We combine a number of localised measures using a neural network to classify each pixel as text or non-text. We demonstrate our results on typical images.
Translated title of the contributionCombining Statistical Measures to Find Image Text Regions
Original languageEnglish
Pages (from-to)450-453
JournalProceedings of the 15th International Conference on Pattern Recognition
Publication statusPublished - 2000

Bibliographical note

ISBN: 0796507506
Publisher: IEEE Computer Society
Name and Venue of Conference: Proceedings of the 15th International Conference on Pattern Recognition
Other identifier: 1000508

Fingerprint Dive into the research topics of 'Combining Statistical Measures to Find Image Text Regions'. Together they form a unique fingerprint.

Cite this