Weighted haze removal method with halo prevention

Y. H. Shiau, Pei-Yin Chen, H. Y. Yang, C. H. Chen, S. S. Wang

Research output: Contribution to journalArticle

37 Citations (Scopus)

Abstract

In this paper, we propose an efficient method to remove haze from a signal image based on the atmospheric scattering model and dark channel prior. Our approach applies a weighted technique that automatically finds the possible atmospheric lights, and mixes these candidates to refine the atmospheric light. Then, difference prior, a novel prior processing method, is employed for the estimation of the transmission that mitigates the halo artifact around the sharp edges. This method requires a low computational cost and is suitable for real-time applications. The experimental results show that our approach obtains the comparable results as compared with previous methods.

Original languageEnglish
Pages (from-to)445-453
Number of pages9
JournalJournal of Visual Communication and Image Representation
Volume25
Issue number2
DOIs
Publication statusPublished - 2014 Feb 1

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this