W. Freeman and D. Brainard, "Bayesian Decision Theory, the Maximum Local Mass Estimate, and Color Constancy," in Proceedings: Fifth International Conference on Computer Vision, pp 210-217, (IEEE Computer Society Press, 1995). Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Color Constancy Using KL-Divergence - Rosenberg, Hebert, Thrun (2001) (5 citations) (Correct)
....entropy measure and the maximum observed error. This suggests that this might provide a useful means of estimating the worst case error of a particular estimate generated by the algorithm. 5 Related Work Many color constancy methods have been described in the literature: 17] 16] 11] 7] [12], 13] 4] 8] 1] 19] 15] 10] One class of algorithms described by Forsyth [11] and Finlayson [7] utilizes constraints about the distribution of the extreme colors in an image and a search procedure to determine the transformation which best satisfies the given constraints. Funt [13] ....
....which best satisfies the given constraints. Funt [13] uses a neural network which takes as input the image color histogram to estimate chromaticities. Recent work by Funt [15] has made use of bootstrapping techniques, as was used here, as a source of training data. Freeman and Brainard, in [12] and [4] also describe a probabilistic model and attempt to solve the more ambitious problem of recovering full surface reflectance spectra. The work presented here is most closely related to the work described by Finlayson [8] 10] and Sapiro [19] Both of the algorithms described in these ....
W. T. Freeman and D. H. Brainard, "Bayesian decision theory, the maximum local mass estimate, and color constancy," Proceedings of the International Conference on Computer Vision, 1995.
Colour Constancy for Scenes with Varying Illumination - Barnard, Finlayson, Funt (1996) (2 citations) (Correct)
....response to the same scene under a known, canonical light. In a general context this problem has proven difficult to solve, so to make progress, restrictive assumptions are made. In particular, it is common to assume that the scene is flat [9, 13, 14] that the illumination is constant throughout [2, 3, 9, 10, 15], and that all reflectances are matte. Finlayson [8] has shown that if we focus on solving only for surface chromaticity and forego estimating surface lightness then the restriction to flat matte surfaces can be relaxed. However, the assumption that the chromaticity of the illumination does not ....
W. Freeman and David Brainard, "Bayesian Decision Theory, the Maximum Local Mass Estimate, and Color Constancy", in Proceedings: Fifth International Conference on Computer Vision, pp 210-217, (IEEE Computer Society Press, 1995)
Color Machine Vision for Autonomous Vehicles - Buluswar, Draper (1998) (2 citations) (Correct)
.... reflectances over the entire scene is gray (the gray world assumption) Gershon [19] assumes that the average scene reflectance matches that of another known color; Vrhel [47] assumes knowledge of the general covariance structure of the illuminant, given a small set of illuminants, and Freeman [16] assumes that the illumination and reflection in a scene follow known probability distributions. These methods are effective when the distribution of colors within the scene follows the assumed model or distribution. In outdoor scenes, the CIE daylight model [22] suggests that the gray world ....
W. Freeman and D. Brainard, "Bayesian Decision Theory: the maximum local mass estimate ", Proceedings of the Fifth International Conference on Computer Vision, 1995.
Color Recognition in Outdoor Scenes By Non-Parametric Learning - Buluswar (1998) (1 citation) (Correct)
....over the entire scene is gray (the gray world assumption) Gershon [16] assumes that the average scene reflectance matches that of some other known color. Vrhel [42]assumes knowledge of the general covariance structure of the illuminant, given a small set of illuminants. Similarly, Freeman [13] assumes that the illumination and reflection in a scene follow known probability distributions. These methods are effective when the distribution of colors within the scene follows the assumed model or distribution. In outdoor scenes, the CIE daylight model [20] suggests that the grayworld ....
W. Freeman and D. Brainard, "Bayesian Decision Theory: the maximum local mass estimate ", Proceedings of the Fifth International Conference on Computer Vision, 1995.
Colour Recognition In Outdoor Images Through Context-Based Models - Buluswar (1998) (Correct)
....over the entire scene is gray (the gray world assumption) Gershon [12] assumes that the average scene reflectance matches that of some other known color. Vrhel [37]assumes knowledge of the general covariance structure of the illuminant, given a small set of illuminants. Similarly, Freeman [9] assumes that the illumination and reflection in a scene follow known probability distributions. These methods are effective when the distribution of colors within the scene follows the assumed model or distribution. In outdoor scenes, the CIE daylight model [18] suggests that the grayworld ....
W. Freeman and D. Brainard, "Bayesian Decision Theory: the maximum local mass estimate ", Proceedings of the Fifth International Conference on Computer Vision, 1995.
Color constancy in the nearly natural image. I. Asymmetric .. - Brainard, Brunt, Speigle Self-citation (Brainard) (Correct)
No context found.
W. T. Freeman and D. H. Brainard, "Bayesian decision theory, the maximum local mass estimate, and color constancy, " in Proceedings of the 5th International Conference on Computer Vision (IEEE Computer Society Press, Los Alamitos, Calif., 1995), pp. 210--217.
Digital color cameras - 2 - Spectral response - Vora, Farrell (1997) (3 citations) Self-citation (Brainard) (Correct)
....acquired image. This prediction error was also small. 1 Introduction To process data from digital color cameras, it is often necessary to know the spectral response properties of the camera s sensors. For example, many demosaicing [1] color correction [13] and illuminant estimation algorithms [4, 5] require this knowledge. In addition, the intrinsic color quality of an image depends on the spectral characteristics of the sensors [2, 7, 12, 14, 15] used. Thus an important component of characterizing a digital color camera is measuring its sensor spectral response functions. We describe ....
Freeman, W. T. and Brainard, D. H., `Bayesian decision theory, the maximum local mass estimate, and color constancy', Proceedings of the 5th International Conference on Computer Vision, pp. 210-217, 1995.
Analysis and Improvement of Multi-Scale Retinex - Kobus Barnard And (1997) (Correct)
No context found.
W. Freeman and D. Brainard, "Bayesian Decision Theory, the Maximum Local Mass Estimate, and Color Constancy," in Proceedings: Fifth International Conference on Computer Vision, pp 210-217, (IEEE Computer Society Press, 1995).
Investigations into Multi-Scale Retinex - Barnard, Funt (1999) (2 citations) (Correct)
No context found.
W. Freeman and D. Brainard, "Bayesian Decision Theory, the Maximum Local Mass Estimate, and Colour Constancy," in Proceedings: Fifth International Conference on Computer Vision, pp 210-217, (IEEE Computer Society Press, 1995).
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