An improved low illumination image enhancement algorithm with color preserving
CSTR:
Author:
Affiliation:

(Control and Simulation Center,Harbin Institute of Technology, 150080 Harbin, China)

Clc Number:

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    To solve the problem of color distortion existing in low illumination image enhancement method, a novel low illumination image enhancement method based on dark-channel prior with the capability of preserving scene color is presented. First, the intensity of every image pixel with dark-channel prior is estimated directly, and for dealing with wrong dark-channel values in white region, the regions with wrong grey values by calculating the minimum difference value of the RGB channels and correct the dark-channel values of the regions are founded. Then, a linear smoothing method is used to refine the block effect caused by dark-channel prior, and the enhanced image is achieved by scaling up the pixel intensity according to its value in dark-channel image. Finally, by comparing with the existing low illumination image enhancement method, the effectiveness of our method with better color preserving capability and higher PSNR is proved.

    Reference
    Related
    Cited by
Get Citation
Related Videos

Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:September 27,2013
  • Revised:
  • Adopted:
  • Online: April 04,2014
  • Published:
Article QR Code