Article

Assessing human skin color from uncalibrated images

  1. J. Marguier1,*,
  2. N. Bhatti2,
  3. H. Baker2,
  4. M. Harville2,
  5. S. Süsstrunk1

Article first published online: 10 OCT 2007

DOI: 10.1002/ima.20114

Issue

International Journal of Imaging Systems and Technology

International Journal of Imaging Systems and Technology

Special Issue: Special Issue on Applied Color Image Processing

Volume 17, Issue 3, pages 143–151, 2007

Additional Information

How to Cite

Marguier, J., Bhatti, N., Baker, H., Harville, M. and Süsstrunk, S. (2007), Assessing human skin color from uncalibrated images. Int. J. Imaging Syst. Technol., 17: 143–151. doi: 10.1002/ima.20114

Author Information

  1. 1

    School of Computer and Communication Sciences, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland

  2. 2

    Hewlett-Packard Laboratories, Palo Alto, CA

*School of Computer and Communication Sciences, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland

Publication History

  1. Issue published online: 10 OCT 2007
  2. Article first published online: 10 OCT 2007
  3. Manuscript Accepted: 30 AUG 2007
  4. Manuscript Received: 9 FEB 2007

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (516K)

Keywords:

  • digital photography;
  • color assessment;
  • color calibration target;
  • uncalibrated imaging systems

Abstract

Images of a scene captured with multiple cameras will have different color values because of variations in color rendering across devices. We present a method to accurately retrieve color information from uncalibrated images taken under uncontrolled lighting conditions with an unknown device and no access to raw data, but with a limited number of reference colors in the scene. The method is used to assess skin tones. A subject is imaged with a calibration target. The target is extracted and its color values are used to compute a color correction transform that is applied to the entire image. We establish that the best mapping is done using a target consisting of skin colored patches representing the whole range of human skin colors. We show that color information extracted from images is well correlated with color data derived from spectral measurements of skin. We also show that skin color can be consistently measured across cameras with different color rendering and resolutions ranging from 0.1 to 4.0 megapixels. © 2007 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 143–151, 2007

Get PDF (516K)