Multi-Counterpropagation Network Model For Colour Recognition

Abstract

Minolta Chroma Meters was used to convert colours into numbers. It offers five different colour systems for measuring absolute chromaticity, that is, CIE Yxy, L*a*b*, L*C*Ho, Hunter Lab and XYZ. In this study, only L*a*b* is used, and combinations of two counterpropagation network (CPN) are required to recognise 808 colours produced by The Royal Horticultural Society, based on RHS Colour Chart [1]. Our proposed neural network model is tested; the result shows that 99% of trained data are recognised, against 98% for untrained data.