LNCS Homepage
ContentsAuthor IndexSearch

Face-Based Illuminant Estimation

Simone Bianco and Raimondo Schettini

University of Milano-Bicocca, DISCo - Department of Informatics, Systems and Comunication, Italy

Abstract. In this work we show that it is possible to use skin tones to estimate the illuminant color. We use a face detector to find faces in the scene, and the corresponding skin colors to estimate the chromaticity of the illuminant. The method, that has been presented at CVPR 2012 [1] is based on two observations: first, skin colors tend to form a cluster in the color space, making it a cue to estimate the illuminant in the scene; second, many photographic images are portraits or contain people. If no faces are detected, the input image is processed with a low-level illuminant estimation algorithm automatically selected according to [2]. The method will be demonstrated on a public dataset of images in RAW format [3], and on images acquired live during the demo.

LNCS 7585, p. 623 ff.

Full article in PDF | BibTeX


lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012