Textile Engineering, Amirkabir University of Technology
, Isfahan University of Technology
The color of the blends of pre-colored fibers depends on the ratio of each fiber in the blends. Some theories have been introduced for color matching of blends of pre-colored fibers. Most however, are restricted in scope and accuracy. Kubelka and Munk presented the most applicable theory, which is still used in industry. In this work, the classical Kubelka-Munk method for color prediction of a series of grays, prepared from different ratio of black and white is compared with new technique, which apply neural networks. Thirteen different blends with different ratio of virgin and black fibers were prepared. The reflection of samples was measured and then a two layers network was designed. The modified back-propagation learning strategy was applied. The Sum of Squares Error was calculated for evaluation of methods. Results showed better prediction for networks in comparison to Kubelka-Munk algorithm.