A computational model of colour categorization

The following research elaborates on understanding and modeling the colour categorization process. The structure of colour categories is argued to resemble the structure of the distribution of colours in the perceived world. This distribution can be represented as colour statistics in some perceptual and approximately uniform colour space (e.g., the CIELUV colour space). The process of colour categorization can be modeled through the grouping of colour statistics by clustering algorithms (e.g., K-means) based on the minimum-distance criterion. This model explains the location and emergence of colour categories. The number of colour categories is presumably determined by a trade-off between accuracy in representation of the perceived world and simplicity of the category system. The model is examined on the basis of K-means clustering analysis of statistics of 630 natural images in the CIELUV colour space. © 2000 John Wiley & Sons, Inc. Col Res Appl, 26, S235–S238, 2001