The Use of Fundamental Color Stimulus to Improve the Performance of Artificial Neural Network Color Match Prediction Systems

Document Type: Research Article


1 Department of Polymer and Color Engineering, Amirkabir University of Technology, I.R. IRAN

2 Department of Textile Engineering, Amirkabir University of Technology, I.R. IRAN

3 Department of Electrical and Electronic Engineering, Amirkabir University of Technology, I.R. IRAN


In the present investigation attempts were made for the first time to use the fundamental color stimulus as the input for a fixed optimized neural network match prediction system. Four sets of data having different origins (i.e. different substrate, different colorant sets and different dyeing procedures) were used to train and test the performance of the network. The results showed that the use of fundamental color stimulus greatly reduces the errors as depicted by the MSE and D Cave data and improves the performance of the neural network prediction system. Additionally the use of fundamental color stimulus makes provisions for predicting the concentrations of one data set whilst being trained by a second data set of completely different origin.


Main Subjects

[1] Davidson, H.R., Hemmendinger, H. and Landry, J. L. R., A system of instrumental color control for the textile industry, J.Soc. Dyers Colour, 79, 577 (1963).

[2] Alderson, J. V., Altherton, E. and Derbyshire, A. N., Modern physical techniques in colour formulation, J. Soc. Dyers  Colour, 77, 657(1961).

[3] Mizutani, E., Takagi, H., Auslander, D. M. and Jang, J. R., Evolving color recipes, IEEE Transactions on Systems, Man and Cybernetics-Part c, 30, 537 (2000).

[4] Bezerra, C. M. and Hawkyard, C.J., Computer match prediction for florescent dyes by neural networks,
J S D C, 116, 163(2000).

[5] Westland, S., Artificial neural networks and colour recipe prediction, in Proceedings of Colour Science 98, Leeds University, 3, 225(2001).

[6] Wyszecki,  G.,  Valenzmetrische Untersuchung des Zusammenhanges zwischen normaler und anomaler Trichromasie, Die Farbe, 2, 39(1953).

[7] Cohen, J. B. and Kappauf, W. E., Metameric color stimuli, fundamental metamers and wyszecki's metameric blacks, Am. J. Psychol., 95, 537(1982).

[8] Ameri,  F.,  Moradian,  S., Amani  Tehran,  M.  and Faez, K., The use of transformed reflection functions in artificial neural network match prediction systems, presented at the Inter-Society Color Council (ISCC), Annual  Meeting and Symposium, Gaithersburg, Maryland , U.S.A., May (2004).

[9] Ameri, F., Moradian, S., Amani  Tehran, M. and Madgidi, N., The use of transformed  functions of reflectance in the color match prediction of textiles, presented at the 4th  AUTEX Conference, Roubaix, France, June (2004).

[10] Glasser, L. G., Mckinney, A. H. and Reilly, C. D., Cube root color coordinate system, J. Opt. Soc. Am., 48, 736(1958).

[11] Newhall,  S.  M.,  Nickerson,  D. and Judd, D. B.,  Final report of the O.S.A. subcommittee on spacing of the munsell colors, J. Opt. Soc. Am., 33, 385(1943).

[12] Matlab, Version  6.5,  Neural  Networks Toolbox,    The MathWorks Inc, (2002).

[13] Moller, M. F., A scaled conjugate gradient algorithm for fast supervised learning, Neural Networks, 6, 525(1993).

[14] Coates, E., Fong, K. and Rigg, B., Uniform lightness scales, J S D C, 97, 179(1981).

[15] Myers, R. H., Myers, S. L. and Walpole, R. E., "Probability and statistics for engineers and scientists", 6th edition: Prentice Hall International, U.S.A. (1998).

[16] Luo, R. and Rigg, B., BFD colour-difference formula Part1-Development of the formula, J S D C, 103, 86 (1987).