Unsupervised Recognition of Salient Colour for Real-Time Image Processing

Abstract. Humans have the subconscious ability to create simple ab-stractions from observations of our physical environment. The ability to consider the colour of an object in terms of “red ” or “blue”, rather than spatial distributions of reflected light wavelengths, is vital in processing and communicating information about important features within our lo-cal environment. The real-time identification of such features in image processing necessitates the software implementation of such a process; segmenting an image into regions of salient colour, and in doing so re-ducing the information stored and processed from 3-dimensional pixel values to a simple colour class label. This paper details a method by which colour segmentation may be performed offline and stored in a static data structure, allowing for constant time dimensionality reduction in an arbitrary environment of coloured features. The machine learning frame-work requires no human supervision, and its performance is evaluated in terms of feature classification performance within a RoboCup robot soc-cer environment. The developed system is demonstrated to yield an 8% improvement over slower traditional methods of manual colour mapping