Transition pixel: A concept for binarization based on edge detection and gray-intensity histograms

  • Authors:

  • Marte A. Ramírez-Ortegón;Ernesto Tapia;Lilia L. Ramírez-Ramírez;Raúl Rojas;Erik Cuevas

  • Affiliations:

  • Institut für Informatik, Freie Universität Berlin, Takustr. 9, 14195 Berlin, Germany;Institut für Informatik, Freie Universität Berlin, Takustr. 9, 14195 Berlin, Germany;Department of Statistics and Actuarial Science, University of Waterloo, 200 University Avenue West Waterloo, Ontario, Canada N2L 3G1;Institut für Informatik, Freie Universität Berlin, Takustr. 9, 14195 Berlin, Germany;Department of Computer Science, University of Guadalajara, Av. Revolución 1500, Guadalajara, Jalisco, México, Mexico

  • Venue:
  • Pattern Recognition
  • Year:
  • 2010

Quantified Score

Hi-index 0.01

Visualization

Abstract

This paper introduces a novel binarization method based on the concept of transition pixel, a generalization of edge pixels. Such pixels are characterized by extreme transition values computed using pixel-intensity differences in a small neighborhood. We show how to adjust the threshold of several binary threshold methods which compute gray-intensity thresholds, using the gray-intensity mean and variance of the pixels in the transition set. Our experiments show that the new approach yields segmentation performance superior to several with current state-of-the-art binarization algorithms.