Multi-Window Binarization of Camera Image for Document Recognition

  • Authors:
  • In-Jung Kim

  • Affiliations:
  • Inzisoft, co., ltd.

  • Venue:
  • IWFHR '04 Proceedings of the Ninth International Workshop on Frontiers in Handwriting Recognition
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes an adaptive binarization method for the document image acquired by camera. By applying multiple windows vary in size, it determines the local thresholds with the information from the global trend as well as the local detail. As the consequence, the proposed method is good at not only preserving fine detail of the character structure but also absorbing noise. The effectiveness of the proposed method was shown by the experiment.