A Somewhat Fuzzy Color Categorization Model 1

We present a computational model of color categorization using a normalized Gaussian function of perceptual color space coordinates as the basic category model, and an application based on the model that can name, point out, and select colors in images, and provide a conndence or (fuzzy) membership value for each categorial judgement. We quantify the performance of our model relative to existing data about human color naming behavior, and relative to the use of diierent color spaces, including a novel one derived from neurophysiological measurements. The application we present is to some extent able to deal with the color constancy problem in real images made in an unmodiied ooce environment with low-grade uncalibrated equipment. We present some empirical results with an example of this kind of image. The novelty of the approach lies in the fact that it models graded or fuzzy color categories as found in anthropological, psychological and psychophysical color perception work, and relates these categories in a simple way to the symbolic labels that natural languages use for them. As such the approach can be seen as a particular case study in symbol grounding, embodiment, or situated cognition, based on a well-deened computational model.