Object Color Prediction from an RGB Image Based on
Metamer Estimation (Part II: Evaluation)h

Takayuki HASEGAWA, Koichi IINO, Norimichi TSUMURA, Toshiya NAKAGUCHI, YoichiMIYAKE

Graduate School of Advanced Integrated Science, Chiba University, Inage-ku, Chiba, Japan

The Journal of the institute of image electronics engineer of Japan (Accepted to be published in Vol.38, No.4, pp.375-384, 2009 ).

Abstract
Part I of this article proposed a novel method that predicts colorimetric values of an object under an arbitrary illuminant from an RGB image photographed by a digital still camera. In this paper, the performance of the proposed method is evaluated. Computer simulations were carried out to evaluate the color prediction accuracy for various combinations of illuminants, camera sensitivities, object categories, and population data used for constructing color prediction models. The results show that the proposed method outperforms conventional methods in terms of both accuracy and robustness against selection of population data. An experiment using a digital camera image also showed that the proposed method is of practical use for actual images.
Key words: metamer estimation, object color prediction, digital still camera

Full paper ( Reprint )
[PDF] (in Japanese)


Back