Combining Statistical Measures to Find Image Text Regions

  • Authors:
  • Affiliations:
  • Venue:
  • ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a method based on statistical properties of local image pixels for focusing attention on regions of text in arbitrary scenes where the text plane is not necessarily front-of-parallel to the camera. This is particularly useful for Desktop or Wearable Computing applications. The statistical measures are chosen to reveal characteristic properties of text. We combine a number of localized measures using a neural network to classify each pixel as text or non-text. We demonstrate our results on typical images.