Effect of classification by competitive neural network on reconstruction of reflectance spectra using principal component analysis

The best way to describe a color is to study its reflectance spectrum, which provide the most useful information. Different methods were purposed for reflectance spectra reconstruction from CIE tristimulus values such as principal components analysis. In this study, the training samples were first divided into 3, 6, 9, and 12 subgroups by creating a competitive neural network. To do that, L*a*b*, L*C*h or L*a*b*C*h were introduced to neural network as input elements. In order to investigate the performance of reflectance spectra reconstruction, the color difference and RMS between actual and reconstructed data were obtained. The reconstruction of reflectance spectra were improved by using a six or nine‐neuron layer with L*a*b* input elements. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 182–188, 2017     

A multispectral imaging approach to colour measurement and colour matching of single yarns without winding

This paper investigates a multispectral imaging approach to colour measurement and colour matching of single yarns. The small size of a single yarn makes it impossible for spectrophotometers directly to acquire its spectral reflectance. Multispectral imaging systems, on the other hand, have the potential to measure the reflectance of single yarns as they can record both the spectral and the spatial information of a sample. A multispectral imaging system, namely imaging colour measurement, has been developed to conduct colour measurement of single yarns. A single yarn is first detected from backgrounds by a modified K‐means clustering method. The reflectance of the single yarn is then specified by an averaging method. Comparative experiments based on 100 pairs of single yarns and corresponding yarn windings show that the reflectance magnitude of a single yarn acquired by imaging colour measurement is smaller than that of corresponding yarn winding measured by a Datacolor 650 spectrophotometer. Experiments on 16 single yarns show that the repeatability and spatial reproducibility of the imaging colour measurement system in measuring a single yarn colour are 0.1185 and 0.2827 CMC(2:1) units. A colour matching comparison experiment (pass or fail), using 24 pairs of single yarns and corresponding pairs of solid‐colour yarn dyed fabrics, shows that single yarns measured by imaging colour measurement can achieve similar colour matching results to solid‐colour yarn dyed fabrics measured by the Datacolor 650 spectrophotometer, with degrees of similarity of 87.5 and 83.3% when the CMC(2:1) and CIE2000(2:1:1) colour difference formulas are employed.     

Experimental study of back‐scattering spectrum of textile structures

The back‐scattered light by textile surfaces mainly depends on their surface state, which is often periodic and directional. The analysis of the reflectance spectra in back‐scattering conditions of two types of structures (yarn, plain and twill weaves) shows the influence of the orientation of these surfaces as well as the back‐scattered angle. In fact, the declination of the yarn orientation in relation to the incidence plane involves an increase of the reflectance factor to reach a maximum value when the yarns are perpendicular to this plane. For woven fabrics, the back‐scattering of surface according to a given orientation primarily depends on its geometrical characteristic in this direction and consequently the used yarn densities. The computation of the ratio of mean quadratic surface roughness h to correlation length l for various used orientations shows the close link between this parameter and the evolution of back‐scattering. The effect of the variation of back‐scattered angle on the back‐scattered light varies with the value of h/l . The comparison between these experimental results and a theoretical study based on Gaussian and isotropic surfaces shows a satisfactory correlation between these two elements with the presence of some cases of discrepancy due to the different natures of the two types of surfaces. © 2006 Wiley Periodicals, Inc. Col Res Appl, 31, 122–132, 2006     

A novel analysis of color component for top dyed melange yarn with support vector machine

In view of the difficulty of distinguishing the color component in top dyed melange yarn due to the spectral overlap of the component colors, a novel color component analysis method based on support vector machine is presented. With this method, spectra data can be distinguished more accurately and effectively than with the traditional method—human‐eye detection—and therefore, the method will be very helpful for accurate color matching. In our work, the core idea was to convert the overlapped spectra data into linearly separable ones in a high dimension space, followed by recognition and determination of the composition of melange yarn by trained support vector machine classifier. The effects of four kernel functions, i.e., linear, radial basis kernel, sigmoid, and polynomial, as well as five spectral preprocessing methods, including amplification, first derivative, second derivative, principal components analysis, and L*a*b* values were studied. The results demonstrated that with the amplification factor of 100 of reflectance spectra coupled with L*a*b* as input data, and using radial basis kernel as kernel function, the highest recognition rate was achieved, with an average recognition rate of eight colors of 96.5%, indicating that it was a better color component analysis method for top dyed melange yarn. © 2015 Wiley Periodicals, Inc. Col Res Appl, 41, 636–641, 2016     

A novel approach to using neural networks to predict the colour of fibre blends

This work is concerned with the colour prediction of viscose fibre blends, comparing two conventional prediction models (the Stearns–Noechel model and the Friele model) and two neural network models. A total of 333 blended samples were prepared from eight primary colours, including two‐, three‐, and four‐colour mixtures. The performance of the prediction models was evaluated using 60 of the 333 blended samples. The other 273 samples were used to train the neural networks. It was found that the performance of both neural networks exceeded the performance of both conventional prediction models. When the neural networks were trained using the 273 training samples, the average CIELAB colour differences (between measured and predicted colour of blends) for the 60 samples in the test set were close to 1.0 for the neural network models. When the number of training samples was reduced to only 100, the performance of the neural networks degraded, but they still gave lower colour differences between measured and predicted colour than the conventional models. The first neural network was a conventional network similar to that which has been used by several other researchers; the second neural network was a novel application of a standard neural network where, rather than using a single network, a set of small neural networks was used, each of which predicted reflectance at a single wavelength. The single‐wavelength neural network was shown to be more robust than the conventional neural network when the number of training examples was small.     

Use of input selection techniques to improve the performance of an artificial neural network during the prediction of yarn quality properties

The performance of an artificial neural network (ANN) is affected by the number and types of inputs. The aim of this article is to study the performance of ANN algorithms, used for the prediction of cotton yarn strength, elongation, and evenness, as the input units are subtracted (skeletonized) and added to the input layer. Nineteen factors, consisting of fiber properties, processing parameters, and yarn quality properties, were used as the main source of inputs. The initial sets of inputs, which were selected on the basis of their relationship with the output factors, were 13, 13, and 12 for yarn strength, elongation, and evenness, respectively. The final sets of inputs were 14 factors for the three yarn quality properties being predicted, and the new ANN algorithms showed performance improvement of 40, 37, and 47% for strength, elongation, and evenness, respectively, when compared to the algorithms with 19 factors. Yarn twist, fiber length, and fiber length uniformity were common among the five most influential factors affecting yarn strength, elongation, and evenness, accounting for 40, 37, and 37% for the prediction of yarn strength, elongation, and evenness, respectively. © 2007 Wiley Periodicals, Inc. J Appl Polym Sci, 2008     

Spectrophotometric colour matching algorithm for top-dyed mélange yarn,based on an artificial neural network

Colour, the first element of quality control of textile products, is a complex subject relating to physical optics, psychology, and the human visual system. Colour matching remains one of the major problems in the textile industry. Mélange yarn is a class of textile product with a specific colour appearance, which colour is mainly affected by colour matching of the dyed fibres and their ratio for spinning rather than by the dyeing process. The existing colour matching models for mélange yarn derived from specific types of fibre or specific spinning processes are restricted by the adopted conditions and parameters of the model, resulting in low universal applicability and low accuracy. In this paper, a spectrophotometric colour matching algorithm based on the back-propagation (BP) neural network and its processes were proposed. The weighted average spectrum was predicted by a BP neural network, followed by recipe prediction from the weighted average with constrained least squares. The results showed that the average colour difference of practical samples, based on the prediction of nine blind testing targets, was 0.79 CMC (2:1) units if more than two a priori training samples were used. This result indicated the capability and practicality of accurate prediction of colour matching for top-dyed mélange yarn by this novel method.     

Color measurement of single yarn based on hyperspectral imaging system

This article proposed a novel approach to color measurement of a single yarn using hyperspectral imaging system (HIS). Due to the size of a single yarn, it is impossible for spectrophotometers to measure its color directly. The HIS can acquire the spectral reflectance of continuous bands within a region of interest on a yarn sample, which can achieve color measurement of a single yarn compared with traditional spectrophotometers. A single yarn is segmented from the background by a spectral matching method through adaptively setting threshold of Fréchet distance values. The spectral reflectance of single yarn is specified by a method that lightness of pixels used as weight. The experiment based on Pantone Cotton Chip Set shows that the interinstrument agreement between the HIS and a standard spectrophotometer Datacolor SF650 has a significant improvement after using the R-Model, and the average percentage improvement of the color difference is up to 54.99%. The yarn segmentation comparative experimental results show that the proposed method to segment single yarn from background is better in retaining the edge information of the yarn than the modified K-means clustering method, and the color of the yarn segmented by the proposed method is more similar to the actual color of single yarn.     

Imparting conductivity and chromic behavior on polyester fibers by means of poly(3‐methylthiophene) nanocoating

Poly(3‐methylthiophene) (P3MT)‐coated polyester fabric is a conductive textile with specific electrical and optical properties; for instance, color change under external stimulus (chromic behavior) was successfully prepared by chemical polymerization with continuous, speed stirring technique. To investigate the striking effect of some variable conditions of polymerization process, the effect of reaction time, temperature, and oxidant concentration on conductivity of the P3MT‐coated fabric was studied. Scanning electron microscopy confirmed that the surface of fabric has entirely been coated with P3MT particles. The further characterizations were investigated using Fourier transform infrared spectroscopy to provide evidence of forming particles onto the fabric, UV–vis absorption spectroscopy, electrical surface resistivity, and pressure dependence visible reflectance spectrophotometer measurements and X‐ray diffraction analysis. The blue shift in wavelength of maximum absorption of about 95 nm to a longer wavelength from that observed in the reflectance spectra of coated polyester fabric; under high‐pressure P3MT‐coated polyester fabric demonstrated piezochromism. © 2011 Wiley Periodicals, Inc. J Appl Polym Sci, 2012     

Application of multi‐flux theory based on Mie scattering to the problem of modeling the optical characteristics of colored pigmented paint films

Multi‐flux theory for multiple scattering calculations in pigmented/protective coating is described. Performance evaluation of the theory is made by comparing theoretically computed reflectance with experimentally measured ones for selected wavelengths for three different paint samples. Diffuse reflectance spectra for hypothetical particulate systems in visible spectral range are generated through computer calculations. Effect of variation in average pigment size and pigment size distribution on reflectance spectra is studied. Overall thrust of morphological characteristics of pigments on the color exhibited by paint dispersion is studied by calculating CIE color and color‐difference parameters of particulate systems. Results show that a very complex relationship exists between the morphological characteristics of pigments and color exhibited by the system. The outcome of the study is important for applications in paint, coating, and plastic industries. © 2001 John Wiley & Sons, Inc. Col Res Appl, 26, 234–245, 2001     

Colour‐appearance modeling using feedforward networks with Bayesian regularization method— Part I: Forward model

In this article, a method of predicting colour appearance (from colorimetric attributes to colour‐appearance attributes, i.e., forward model) using an artificial neural network is presented. The neural network model developed is a multilayer feedforward neural network model for predicting colour appearance (FNNCAM for short). The model was trained by LUTCHI colour‐appearance datasets. The Levenberg–Marquardt algorithm is incorporated into the back‐propagation procedure to accelerate the training of FNNCAM and the Bayesian regularization method is applied to the training of neural networks to improve generalization. The results of FNNCAM obtained are quite promising. © 2000 John Wiley & Sons, Inc. Col Res Appl, 25, 424–434, 2000     

A soft computing approach to model the structure–property relations of nonwoven fabrics

A soft computing approach to model the structure–property relations of nonwoven fabrics for filtration use is developed. Because the number of samples is very limited, the artificial neural network model to be established must be a small‐scale one. Consequently, this soft computing approach includes two stages. In the first stage, the structural parameters are selected by using a ranking method, to find the most relevant parameters as the input variables to fit the small‐scale artificial neural network model. The first part of this method takes the human knowledge on the nonwoven products into account. The second part uses a data sensitivity criterion based on a distance method that analyzes the measured data of nonwoven properties. In the second stage, the artificial neural network model of the structure–property relations of nonwoven fabrics is established. The results show that the artificial neural network model yields accurate prediction and a reasonably good artificial neural network model can be achieved with relatively few data points by integrated with the input variable selecting method developed in this research. The results also show that there is great potential for this research in the field of computer‐assisted design in nonwoven technology. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 103: 442–450, 2007     

Methods of selecting a small reflectance set as a transfer standard for correcting spectrophotometers

The present article concerns the use of software and transfer standards of reflectance to correct a fielded spectrophotometer so that it behaves closely like a reference instrument. A method is described to choose from a large set of reflectances the best subset of a few reflectances to act as a transfer standard. A reflectance set is generated from the algorithm using each of two alternative metrics for instrument closeness: CIELAB ΔE* and a weighted sum of absolute differences over wavelength. Both metrics yield transfer standards that conspicuously exclude BCRA reflectances and also show improvement over the BCRA reflectances currently used for this purpose. © 2005 Wiley Periodicals, Inc. Col Res Appl, 31, 13–17, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.20169     

Melt index prediction by RBF neural network with an ICO‐VSA hybrid optimization algorithm

Melt index (MI) is considered as one of the most significant parameter to determine the quality and the grade of the practical polypropylene polymerization products. A novel ICO‐VSA‐RNN (RBF neural network with ICO‐VSA algorithm) MI prediction model is proposed based on radial basis function (RBF) neural network and improved chaos optimization (ICO), and variable‐scale analysis (VSA), where the ICO is first added and then combined with the VSA to overcome the defects of ICO and VSA, then the parameters of the RBF neural network are optimized with them. At last, the RBF neural network model for MI prediction model is developed. Further researches on the optimal RBF neural network model of MI prediction are carried out with the data from a real industrial plant, and the prediction results show that the performance of this prediction model is much better than the RBF neural network model without optimization. © 2012 Wiley Periodicals, Inc. J Appl Polym Sci, 2012     

Rapid absolute diffuse spectral reflectance factor measurements using a silicon-photodiode array

The absolute diffuse reflectance factors of white standard reference materials have been measured in d/0 geometry (Sharp–Little method) over the visible spectral range using a silicon-photodiode array. This method reduces the measuring time to a few seconds to obtain complete spectral reflectance factor data from 380–780 nm in the visible range. The effects of the openings and the wall thickness at the sample port onto the spectral reflectance factors were considered to get more accurate results. The precision of the diffuse reflectance factors in our system was 0.1% in the wavelength region longer than 550 nm and 0.4% in that shorter than 400 nm. We have obtained the absolute diffuse reflectance factors in the visible range of two kinds of barium sulfate, and of pressed polytetrafluoroethylene (PTFE) at three different densities. © 1997 John Wiley & Sons, Inc. Col Res Appl, 22, 275–279, 1997     

Determination of twisting angle of electrospun nanofiber bundle for continuous electrospinning system

Electrospinning continuously produced twisted nanofibers with a convergence coil and a rotating ring collector. The positively charged nozzle was used in the electrospinning process to deposit electrospun fibers of polyacrylonitrile onto a rotating ring collector. By withdrawing the electrospun fibers from the rotating ring collector, it was possible to spin the electrospun fibers yarn. In this study, theoretical approaches and numerical simulations were used to determine the twisting angle of the yarn. Using the equations developed in this study, we performed numerical simulations and compared the experimental results with the numerical simulation results. Mechanical properties of the fiber bundle were analyzed for twisting angle. It was confirmed the relationship among the winding drum, the ring collector, and flux of the fibers mass per time during electrospinning in the developed system. © 2017 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2017 , 134, 45528.     

Colour‐appearance modeling using feedforward networks with Bayesian regularization method. Part II: Reverse model

In Part I of this article, the development of a multilayer perceptrons feedforward artificial neural network model to predict colour appearance from colorimetric values was reported. Bayesian regularization was employed for the training of the network. In this part of the article, the reverse model, that is, the perdition of colorimetric values from the colour appearance attributes is reported using the same neural network design methodology developed in Part I. This study should contribute to the building of an artificial neural network–based colour appearance prediction, both forward and reverse, using the most comprehensive LUTCHI colour appearance data sets for training and testing. Good prediction accuracy and generalization ability were obtained using the neural networks built in the study. Because the neural network approach is of a black‐box type, colour appearance prediction using this method should be easier to apply in practice. © 2002 Wiley Periodicals, Inc. Col Res Appl, 27, 116–121, 2002; DOI 10.1002/col.10030     

Determination of Scattering and Absorption Coefficients for Plasma-Sprayed Yttria-Stabilized Zirconia Thermal Barrier Coatings

Prediction of radiative transport through translucent thermal barrier coatings (TBCs) can only be performed if the scattering and absorption coefficients and index of refraction of the TBC are known. To date, very limited information on these coefficients, which depend on both the coating composition and the microstructure, has been available for the very commonly utilized plasma-sprayed 8 wt% yttria-stabilized zirconia (8YSZ) TBCs. In this work, the scattering and absorption coefficients of freestanding plasma-sprayed 8YSZ coatings were determined from room-temperature normal-incidence directional-hemispherical reflectance and transmittance spectra over the wavelength range from 0.8 to 7.5 μm. Spectra were collected over a wide range of coating thickness from 60 to almost 900 μm. From the reflectance and transmittance spectra, the scattering and absorption coefficients as a function of wavelength were obtained by fitting the reflectance and transmittance values predicted by a four flux model to the experimentally measured values at all measured 8YSZ thicknesses. While the combined effects of absorption and scattering were shown in general to exhibit a nonexponential dependence of transmittance on specimen thickness, it was shown that for sufficiently high absorption and optical thickness, an exponential dependence becomes a good approximation. In addition, the implications of the wavelength dependence of the plasma-sprayed 8YSZ scattering and absorption coefficients on (1) obtaining accurate surface-temperature pyrometer measurements and on (2) applying mid-infrared reflectance to monitor TBC delamination are discussed.     

Towards automation of color/weave selection in Jacquard design: Model verification

Jacquard woven fabrics are made from colored yarns and different weaves for designing complex pictorial and other patterning effects. The final visualized color effect is the result of assigning weave designs to different areas of the pattern to be created. The current practice in creating Jacquard woven fabric designs is to produce many samples in a trial‐and‐error attempt to match artwork colors. An ability to simulate accurately the appearance of a design prior to manufacture is highly desirable to reduce trial‐and‐error sample production. No automated accurate digital color methodology is yet available to assist designers in matching the patterned woven fabric to the desired artwork. To achieve this, we developed a geometrical model to predict the color contribution of each yarn on the face of the fabric. The geometrical model combined with a Kubelka‐Munk based color mixing model allowed the prediction of the reflectance properties of the final color for a given design. We compared the predicted and experimental values of the reflectance properties for a range of fabrics using the same geometric model with three separate color mixing models. The geometrical model combined with a log‐based color mixing model produced reasonable agreement between predicted and measured ΔE_ab, with an average ΔE_ab of approximately five. © 2009 Wiley Periodicals, Inc. Col Res Appl, 34, 225–232, 2009