White point estimation for uncalibrated images

Vlad C. Cardei, Brian Funt, Kobus Barnard

Research output: Contribution to conferencePaper

53 Scopus citations

Abstract

Color images often must be color balanced to remove unwanted color casts. We extend previous work on using a neural network for illumination, or white-point, estimation from the case of calibrated images to that of uncalibrated images of unknown origin. The results show that the chromaticity of the ambient illumination can be estimated with an average CIE Lab error of 5ΔE. Comparisons are made to the grayworld and white patch methods.

Original languageEnglish (US)
Pages97-100
Number of pages4
StatePublished - Dec 1 1999
Externally publishedYes
EventFinal Program and Proceedings of the 7th IS and T/SID Color Imaging Conference: Color Science, Systems and Applications - Scottsdale, AZ, United States
Duration: Nov 16 1999Nov 19 1999

Other

OtherFinal Program and Proceedings of the 7th IS and T/SID Color Imaging Conference: Color Science, Systems and Applications
CountryUnited States
CityScottsdale, AZ
Period11/16/9911/19/99

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'White point estimation for uncalibrated images'. Together they form a unique fingerprint.

  • Cite this

    Cardei, V. C., Funt, B., & Barnard, K. (1999). White point estimation for uncalibrated images. 97-100. Paper presented at Final Program and Proceedings of the 7th IS and T/SID Color Imaging Conference: Color Science, Systems and Applications, Scottsdale, AZ, United States.