A color similarity test was conducted on the 24 color patches of a Gretag Macbeth color checker. Color similarities were measured either by distances between standard colorimetric representations (such as RGB, Lab or spectral reflectance curves) or by human observer judgments. In each case, the dissimilarity matrix was processed by a classical, metric, multidimensional scaling algorithm, in order to produce a visually-interpretable two-dimensional plot of color dissimilarity. The analysis of the plots produces some interesting conclusions. First, the plots produced by the Lab, RGB and spectral representations exhibit very evident variation axes according to the luminance and basic chromatic differences (red-green, blue-yellow). This behavior (trivial for the Lab representation) suggests that the color similarity measurement by chromatic differences is implicitly embedded in the RGB and spectral representations. The color dissimilarity plots associated to the human judgments (for any individual, as well as for an “average” observer) exhibit a different organization, which mixes hue, saturation and luminance (HSV). According to these plots, the human similarity judgment is not entirely HSV-based. We prove that it is possible to obtain the same color dissimilarity plots if a fuzzy color model is assumed. The fuzzy color model provides similarity coefficients (similarity degrees) between pairs of colors, based on their inter-distance, according to an imposed “color confusion” control parameter, which seems to be relevant for the human vision.