Spectrophotometric prediction of pre-colored fiber blends with a hybrid model based on artificial neural network and Stearns–Noechel model

The performance of the traditional color prediction model in the color prediction of colored fiber blends is usually not very satisfactory under a variety of conditions, due to the limitation of the trail data and the assumptions used for derivation. In contrast to the traditional model, artificial neural networks (ANN) have an excellent nonlinear mapping ability; however, they also have poor generalization ability if the training data are not sufficient. In this paper a hybrid model, called the Stearns–Noechel (S-N)–ANN model, is proposed, which combines the S-N model with the ANN model. This uses the S-N model first to build the approximate relationship between the recipe and spectrophotometric response of the color blends, followed by optimization with the ANN to achieve higher prediction accuracy and better practicability. Compared with the ANN model, the S-N–ANN model needs less training time with the same training data, yet achieves higher validation and correlation coefficients, indicating that the training of the S-N–ANN model is much easier. The average color difference of the predicted spectrum obtained with the S-N–ANN model was 0.86 CMC(2:1) unit, which was much lower than that obtained with either the ANN model (∼2.21) or the traditional S-N model (∼1.66), indicating that the S-N–ANN model is a more accurate method for the color prediction of colored fiber blends.

[1]  W. Vargas,et al.  Applicability conditions of the Kubelka-Munk theory. , 1997, Applied optics.

[2]  Malathy Jawahar,et al.  Artificial neural networks for colour prediction in leather dyeing on the basis of a tristimulus system , 2015 .

[3]  David Haussler,et al.  What Size Net Gives Valid Generalization? , 1989, Neural Computation.

[4]  D. A. Burlone,et al.  Formulation of blends of precolored nylon fiber , 1983 .

[5]  P. Kubelka,et al.  New Contributions to the Optics of Intensely Light-Scattering Materials. Part I , 1948 .

[6]  A. Moghassem.  Study on the Dyed Cotton Fibers Damage in Spinning Processes and its Effect on the Cotton Mélange Yarn Properties , 2008 .

[7]  Roderick McDonald,et al.  Colour Physics for Industry , 1987 .

[8]  D. A. Burlone,et al.  Theoretical and practical aspects of selected fiber‐blend color‐formulation functions , 1984 .

[9]  L. F. C. Friele,et al.  THE APPLICATION OF COLOUR MEASUREMENT IN RELATION TO FIBRE-BLENDING , 1952 .

[10]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[11]  L. Rong,et al.  Tristimulus algorithm of colour matching for precoloured fibre blends based on the Stearns–Noechel model , 2006 .

[12]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[13]  Li Yang,et al.  Revised Kubelka-Munk theory. I. Theory and application. , 2004, Journal of the Optical Society of America. A, Optics, image science, and vision.

[14]  D. Dupont,et al.  Color formulation by fiber blending using the Stearns–Noechel model , 2002 .

[15]  Feng Liu,et al.  Inconspicuous structural coloration in the elytra of beetles Chlorophila obscuripennis (Coleoptera). , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[16]  M. Bichsel.  Image processing with optimum neural networks , 1989 .

[17]  Stephen Westland,et al.  An intelligent approach to colour recipe prediction , 2008 .

[18]  John E. Moody,et al.  The Effective Number of Parameters: An Analysis of Generalization and Regularization in Nonlinear Learning Systems , 1991, NIPS.

[19]  Lapo Governi,et al.  Methods for Predicting Spectral Response of Fibers Blends , 2015, ICIAP Workshops.

[20]  D. Dupont,et al.  Formulation of colored fiber blends from Friele's theoretical model , 2002 .

[21]  Renzo Shamey,et al.  Artificial intelligence in the colour and textile industry , 2008 .

[22]  Shih-Wen Hsiao,et al.  A study on the application of an artificial neural algorithm in the color matching of Taiwanese cultural and creative commodities , 2015 .

[23]  P. Kubelka,et al.  Errata: New Contributions to the Optics of Intensely Light-Scattering Materials. Part I , 1948 .

[24]  S. An,et al.  Properties of Specialty Yarns Based on Raw and Dyed Cotton , 2003 .

[25]  Seyed Hossein Amirshahi,et al.  Applying the Kubelka-Munk Equation to Explain the Color of Blends Prepared from Precolored Fibers , 1994 .

[26]  D. A. Burlone,et al.  Effect of Fiber Translucency on the Color of Blends of Precolored Fibers , 1990 .

[27]  et al,et al.  Study of resonances in exclusive B decays to D{sup (*)}D{sup (*)}K , 2007, 0708.1565.

[28]  P. Kubelka.  Ein Beitrag zur Optik der Farban striche , 1931 .

[29]  Monica Carfagni,et al.  Prediction of the Color and of the Color Solidity of a Jigger-dyed Cellulose-based Fabric: A Cascade Neural Network Approach , 2010 .

[30]  Lapo Governi,et al.  Prediction of the spectrophotometric response of a carded fiber composed by different kinds of coloured raw materials: An artificial neural network-based approach , 2011 .

[31]  B. Rigg,et al.  Modification to the JPC79 Colour–difference Formula , 2008 .

[32]  S. H. Amirshahi,et al.  An Algorithm for Optimizing Color Prediction in Blends , 1995 .

[33]  Stephen Westland,et al.  Kubelka-Munk or neural networks for computer colorant formulation? , 2002, Other Conferences.

[34]  Zhishen Wu,et al.  Review of beetle forewing structures and their biomimetic applications in China: (I) On the structural colors and the vertical and horizontal cross-sectional structures. , 2015, Materials science & engineering. C, Materials for biological applications.