M. Storring, H.J. Andersen, and E. Granum. Estimation of the illuminant colour from human skin colour. Proc. International Conf. on Automatic Face and Gesture Recognition, pp. 64-- 69, 2000. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Skin Color-Based Video Segmentation under Time-Varying Illumination - Sigal (2003) (Correct)
....color spaces [7, 12] however, such an approach can withstand only changes that skin color distributions undergo within a narrow set of conditions. It has been shown that even in the chromaticity plane skin color undergoes significant changes when the color temperature of the light source changes [16, 21]. The conditions that we are concerned with in this paper are broader than those assumed in many previous systems. In particular, we are concerned with three conditions: 1. time varying illumination, 2. multiple sources, with time varying illumination, and 3. single or multiple colored ....
....for the Mixture of Gaussians case. The order is generally determined via heuristics. In constrained environments, the model order can be predefined based on the known environmental conditions. The parameters of the skin color distribution can vary significantly with people and lighting conditions [12, 16, 21, 24]. Thus, to build a system that is general enough to model and track different people, or robust enough to handle even modest variations in illumination conditions, one must employ an algorithm that adjusts the parameters of the distribution accordingly. In one of the first systems to take an ....
[Article contains additional citation context not shown here]
M. Storring, H.J. Andersen, and E. Granum. Estimation of the illuminant colour from human skin colour. Proc. International Conf. on Automatic Face and Gesture Recognition, pp. 64-- 69, 2000.
Estimation Of The Illuminant Colour Using Highlights.. - Störring, Granum.. (2000) Self-citation (Storring Andersen Granum) (Correct)
....might be in combining several methods where each has its strength and weaknesses but their combination results in a robust method. One contributing element to such a combination of methods was recently proposed using the body matte reflections of human skin to estimate the illuminant colour [5]. Given a reference image taken under known illuminant colour and making the assumption that the light sources can be approximated by Blackbody radiators the average estimation error of the light source s correlated colour temperature (CCT) in an input image was 180K (Kelvin) on light sources in ....
.... taken under known illuminant colour and making the assumption that the light sources can be approximated by Blackbody radiators the average estimation error of the light source s correlated colour temperature (CCT) in an input image was 180K (Kelvin) on light sources in the range of 2600K to 6200K [5]. Another contributing element could be in exploiting the information of surface reflections. The light reflected from non homogeneous dielectric materials with a high oil or water content, such as human skin, may be described by the Dichromatic Reflection Model Type I [6] The surface ....
Moritz Storring, Hans J. Andersen, and Erik Granum. Estimation of the illuminant colour from human skin colour. In 4th IEEE International Conference on Automatic Face and Gesture Recognition, pages 64--69, Grenoble, France, March 2000.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC