Color matching of fabric blends: a hybrid Kubelka-Munk + artificial neural network based method

Colour matching of fabric blends is a key issue for textile industry, mainly due to the raising need of creating high quality products for fashion market. The process of mixing together differently coloured fibres to match a desired colour is usually performed by using some “historical” recipes, skilfully managed by company colourists. More often than desired, the first attempt in creating a blend is not satisfactory, thus requiring the experts to spend efforts in changing the recipe with a trial and error process. To confront with this issue a number of computer-based methods have been proposed in the last decades, roughly classified in “theoretical” and “artificial neural network (ANN) based” approaches. Inspired by the above literature works, the present paper provides a method for accurate estimation of spectrophotometric response of a textile blend composed by differently coloured fibres, made of different materials. In particular, the performance of the Kubelka-Munk theory is enhanced by introducing an artificial intelligence approach to determine a more consistent value of the non-linear function relationship between the blend and its components. Therefore, a hybrid K-M-ANN-based method able to model the colour mixing mechanism is devised to predict the reflectance values of a blend.