Thresholding using two-dimensional histogram based on local entropy

  • Authors:

  • Zhao Cheng;Tianxu Zhang;Luxin Yan

  • Affiliations:

  • State Key Laboratory for Multispectral Information Processing Technologies, Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology, Wuhan, Chi ...;State Key Laboratory for Multispectral Information Processing Technologies, Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology, Wuhan, Chi ...;State Key Laboratory for Multispectral Information Processing Technologies, Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology, Wuhan, Chi ...

  • Venue:
  • CAR'10 Proceedings of the 2nd international Asia conference on Informatics in control, automation and robotics - Volume 1
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Image Segmentation is a basal research in image processing domain. The outcome of segmentation has an immense effect on the posterior image processing. Focusing on gray-level image adaptive segmentation, in this paper, a new gray-level image segmentation algorithm using 2-D histogram thresholding based on local entropy (GLLE) is proposed. Some comparative experiments using typical image are implemented and the results are shown at the end of this paper. The results of comparative experiment demonstrate that the GLLE method can segment the target area much more intactly than the classical methods,. Furthermore, the GLLE method also has the ability of anti-illumination.