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     

A study of colour emotion and colour preference. Part II: Colour emotions for two‐colour combinations

Eleven colour‐emotion scales, warm–cool, heavy–light, modern–classical, clean–dirty, active–passive, hard–soft, harmonious–disharmonious, tense–relaxed, fresh–stale, masculine–feminine, and like–dislike, were investigated on 190 colour pairs with British and Chinese observers. Experimental results show that gender difference existed in masculine–feminine, whereas no significant cultural difference was found between British and Chinese observers. Three colour‐emotion factors were identified by the method of factor analysis and were labeled “colour activity,” “colour weight,” and “colour heat.” These factors were found similar to those extracted from the single colour emotions developed in Part I. This indicates a coherent framework of colour emotion factors for single colours and two‐colour combinations. An additivity relationship was found between single‐colour and colour‐combination emotions. This relationship predicts colour emotions for a colour pair by averaging the colour emotions of individual colours that generate the pair. However, it cannot be applied to colour preference prediction. By combining the additivity relationship with a single‐colour emotion model, such as those developed in Part I, a colour‐appearance‐based model was established for colour‐combination emotions. With this model one can predict colour emotions for a colour pair if colour‐appearance attributes of the component colours in that pair are known. © 2004 Wiley Periodicals, Inc. Col Res Appl, 29, 292–298, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.20024     

A study of colour emotion and colour preference. Part III: Colour preference modeling

In this study three colour preference models for single colours were developed. The first model was developed on the basis of the colour emotions, clean–dirty, tense–relaxed, and heavy–light. In this model colour preference was found affected most by the emotional feeling “clean.” The second model was developed on the basis of the three colour‐emotion factors identified in Part I, colour activity, colour weight, and colour heat. By combining this model with the colour‐science‐based formulae of these three factors, which have been developed in Part I, one can predict colour preference of a test colour from its colour‐appearance attributes. The third colour preference model was directly developed from colour‐appearance attributes. In this model colour preference is determined by the colour difference between a test colour and the reference colour (L*, a*, b*) = (50, ?8, 30). The above approaches to modeling single‐colour preference were also adopted in modeling colour preference for colour combinations. The results show that it was difficult to predict colour‐combination preference by colour emotions only. This study also clarifies the relationship between colour preference and colour harmony. The results show that although colour preference is strongly correlated with colour harmony, there are still colours of which the two scales disagree with each other. © 2004 Wiley Periodicals, Inc. Col Res Appl, 29, 381–389, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/col.20047     

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.     

The CRI‐CAM02UCS colour rendering index

A new colour rendering index, CRI‐CAM02UCS, is proposed. It predicts visual results more accurately than the CIE CIR‐R_a. It includes two components necessary for predicting colour rendering in one metric: a chromatic adaptation transform and uniform colour space based on the CIE recommended colour appearance model, CIECAM02. The new index gave the same ranks as those of CIE‐R_a in the six lamps tested regardless the sample sets used. It was also found that the methods based on the size of colour gamut did not agree with those based on the test‐sample method. © 2011 Wiley Periodicals, Inc. Col Res Appl, 2012     

Artificial neural networks for colour prediction in leather dyeing on the basis of a tristimulus system

Computer‐assisted colour prediction and quality control have become increasingly important to the dyeing process in many consumer goods manufacturing industries, including textile and leather. The most challenging aspect concerns dye recipe prediction for the production of the required shade on a given substrate. Computer recipe prediction based on the conventional and widely used Kubelka–Munk model often fails under a variety of conditions. In the present investigation, an attempt has been made to develop an artificial neural network model to predict colour in terms of tristimulus values (X, Y, Z) given the concentration of dyes. An artificial neural network model was trained with 300 pairs of known input vectors, i.e. dye concentrations, and output vectors, i.e. colour parameters, using a backpropagation algorithm. The artificial neural network topology consists of three neurons in the input layer to represent the concentration of dyes, three neurons in the output layer to represent the tristimulus values X, Y, and Z, and five neurons in the hidden layer with a log‐sigmoid transfer function. The artificial neural network results showed a good level of colour prediction during the training and testing phase. The results also indicate that the artificial neural network has the potential to give better predictive performance than the conventional Kubelka–Munk model.     

New colour appearance scales for describing saturation,vividness, blackness,and whiteness

This article describes the development of new models for predicting four colour appearance attributes: saturation, vividness, blackness, and whiteness. The new models were developed on the basis of experimental data accumulated in the authors' previous study, in which the four colour appearance attributes were scaled by 64 Korean and 68 British observers using the categorical judgment method. Two types of models were developed: the ellipsoid‐based and the hue‐based. For the former, the perceived saturation, vividness, blackness, and whiteness were modeled in the form of colour‐difference formulae between the test colour and a reference colour. For the latter, blackness, whiteness, and chromaticness scales were modeled by estimating hue‐dependent lightness and chroma values for the “full colour” in the framework of Adams' equation. The new models were tested using NCS data and were found to outperform some of the existing colour appearance models.     

On attributes of achromatic and chromatic object‐color perceptions

Adapting luminance dependencies of various color attributes of object colors (lightness, brightness, whiteness‐blackness, whiteness‐blackness strength, chroma, and colorfulness) were clarified under white illumination with various adapting illuminances. The correlation between the perceptions of lightness and brightness and those of whiteness‐blackness and whiteness‐blackness strength is also clarified for achromatic object colors. The difference between the increase of brightness and that of whiteness‐blackness contrast (the effect studied by Stevens and Jameson—Hurvich) by raising their adapting illuminance is resolved without any contradiction. It is also shown that the nonlinear color‐appearance model developed by the author and his colleagues is able to explain the complex characteristics of all the above color attributes of object colors by making minor modifications to it. In addition, two kinds of classifications of various color attributes are given; one is based on the similarity of perception level, and the other on the degree of adapting illuminance dependency. © 2000 John Wiley & Sons, Inc. Col Res Appl, 25, 318–332, 2000     

An intelligent system for fashion colour prediction based on fuzzy C‐means and gray theory

For design and manufacturing industries, to be able to capture the fashion trend is an essential factor that leads to winning a sale. However, colour predicting process in many organizations is not visible to the public. In order to provide colour trend to industries in advance, a predicting method is proposed in this study. In the method, the fuzzy c‐means was used to separate the collected colour data, then the minimum mean‐square error was used to place the similar colour clusters within different time point together and the gray model was adopted for prediction. In order to verify the prognostication of the system, four data announced by Pantone from spring 2014 to fall, 2015 were taken as the predicted samples and the colour for spring 2016 was predicted to compare with that in Pantone spring, 2016. The results show that the system has a high accuracy for predicting colour. The residual modified model constructed with the colour samples rearranged with MMSE has the best‐predicted result that ranged from 83.3% to 99.4%. It indicates that the result obtained with the rearranged samples is higher than that without rearrangement. Besides, the accuracy of the gray predicted results with residual modification would be more precise than the one without residual modification. Moreover, the value of mean squared error is quite low, which was ranged from 0.000025 to 0.0277. Therefore, the current intelligent predicting system satisfies the criteria of capturing colour in trend for enterprises. Moreover, it enables industries to make decisions for selecting the colour trend. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 273–285, 2017     

A cross‐cultural colour‐naming study. Part III—A colour‐naming model

A colour‐naming model was developed to categorize volumes for each of the 11 basic names in CIELAB colour space. This was tested with three different sets of data for two languages (English and Mandarin), derived from extensive colour categorization experiments. The performance of the model in predicting colour names was satisfactory, with an average prediction error of 8.3%. © 2001 John Wiley & Sons, Inc. Col Res Appl, 26, 270–277, 2001     

Simulation Studies on Growth and Death of Microorganisms Using the Oil‐Degrading Bacteria Petrotoga sp.

Three models were developed to estimate the potential of the selected bacteria Petrotoga sp., a thermophilic anaerobic oil‐degrading microorganism. Fourteen data sets of these bacteria were simulated by a multilayer feed‐forward neural network and an adaptive neuro‐fuzzy interference system. Twelve data sets served for training and two for testing these models. A simplified numerical model was performed assuming two phases in the growth process of oil‐degrading microorganisms, the logarithmic growth phase and the death phase. Comparison between these models in predicting bacterial cell concentration for different data sets indicates little difference between the overall average relative errors of the three methods and that all can be applied for prediction. Effects of salinity concentration, amount of yeast extract, and temperature on bacterial cell concentration were simulated by numerical and neural network models.     

Investigation of colour appearance models for illumination changes across media

The key to achieving successful cross‐media colour reproduction is a reliable colour appearance model, which is capable of predicting the colour appearance across a variety of imaging devices under different viewing conditions. The two most commonly used media, CRT displays (soft copy) and printed images (hard copy), were included in this study using four complex images. The original printed images were captured using a digital camera and processed using eight colour appearance models (CIELAB, RLAB, LLAB, ATD, Hunt96, Nayatani97, CIECAM97s, and CAM97s2) and two chromatic adaptation transforms (von Kries and CMCCAT97). Psychophysical experiments were carried out to assess colour model performance in terms of colour fidelity by comparing soft‐copy and hard‐copy images. By employing the memory‐matching method, observers categorized the reproductions displayed on a CRT and compared them to the original printed images viewed in a viewing cabinet. The experiment was divided into three phases according to the different colour temperatures between the CRT and light source, i.e., print (D50, A, and A) and CRT (D93, D93, and D50), respectively). It was found that the CIECAM97s‐type models performed better than the other models. In addition, input parameters for each model had a distinct impact on model performance. © 2001 John Wiley & Sons, Inc. Col Res Appl, 26, 428–435, 2001     

Optimum solution of the CIECAM02 yellow–blue and purple problems

Brill [Color Res Appl 2006;31:142‐145] and Brill and Süsstrunk [Color Res Appl 2008;33:424‐426] found that CIECAM02 has the yellow–blue and purple problems and gave partial solutions to them. In this article we model the optimum solution to the yellow–blue and purple problems simultaneously as a constrained non‐linear optimization problem. An optimum solution resulting in a new CAT02 matrix is numerically obtained. This new matrix satisfies the nesting rule and performs better than the Hunt‐Pointer‐Estévez (HPE) matrix in predicting both corresponding colours and colour appearance data sets. Specifically, it was found that the new and HPE matrices performed significantly different on nine (out of 21) corresponding colour data sets and on all corresponding colours data sets as a whole. © 2014 Wiley Periodicals, Inc. Col Res Appl, 40, 491–503, 2015     

Proposal of a new concept for color‐appearance modeling

A new type of color‐appearance model (CAM) is proposed together with its concept and flow of formulations. The topics described are: (1) The existence of two kinds of color‐appearance models, CAMs previously used and CAMs newly proposed. (2) All the CAMs, previously developed and used, do not predict color‐appearance attribute of perceived lightness of object colors under any illuminations. They may be adequately called “the model for predicting color‐appearance match between object colors under different adapting conditions.” (3) Newly improved CAMs take the Helmholtz–Kohlrausch effect in the VCC method into account. They can determine object colors with the same Tone (equi‐perceived lightness, equi‐whiteness‐blackness, and equi‐perceived chroma) irrespective of hues under reference illuminant. The newly improved models can be named Integrated CAMs. Their applicable fields are described in detail. © 2007 Wiley Periodicals, Inc. Col Res Appl, 32, 113–120, 2007     

Development of a hybrid neural network model to predict feeding method in fed‐batch cultivation for enhanced recombinant streptokinase productivity in Escherichia coli

BACKGROUND: A simple and efficient model for enhancing production of recombinant proteins is essential for cost effective development of processes at industrial scale. A hybrid neural network (HNN) model is proposed combining an unstructured model and neural network to predict the feeding method for the post‐induction phase of fed‐batch cultivation for increased recombinant streptokinase activity in Escherichia coli. RESULTS: The parameters of the unstructured model were estimated from experiments conducted with various feeding methods. The simulated model described the dynamics of the process satisfactorily, however, its predictive capability of the process for different feeding methods is limited due to wide disparity in process parameters. In contrast, a neural network model trained to map the variations in process parameters to state variables complements the ‘first principle’ model in predicting the state variables effectively. CONCLUSIONS: The HNN model is able to predict the product profile for different substrate feed rates. Further, the average volumetric streptokinase activity predicted by the HNN model matches closely the experimental values for fed‐batches having high as well as low streptokinase activity. The HNN model developed in this study could facilitate development of a process for recombinant protein production with minimum number of experiments. Copyright © 2011 Society of Chemical Industry     

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.     

An integrated color‐appearance model using CIELUV and its applications

A new type of color‐appearance model is presented together with its formulations. It is named In‐CAM(CIELUV), which means the integrated color‐appearance model using CIELUV space. Using the In‐CAM(CIELUV), we can integrate its fields of applications in both colorimetric engineering and artistic color design. Various applications are introduced in colorimetric and color design fields. The In‐CAM(CIELUV) connects directly colorimetric color space and perceptual Hue‐Tone color order systems. In other words, the In‐CAM (CIELUV) gives a colorimetric basis for Hue‐Tone system. The three color attributes in the In‐CAM(CIELUV) space are mutually independent. This is a very convenient feature for selecting color combinations. Some two‐color combinations selected systematically in the In‐CAM(CIELUV) space are shown. © 2008 Wiley Periodicals, Inc. Col Res Appl, 33, 125–134, 2008     

Development of calibration models for quality control in the production of ethylene/propylene copolymers by FTIR spectroscopy,multivariate statistical tools,and artificial neural networks

Principal component regression (PCR), partial least squares (PLS), StepWise ordinary least squares regression (OLS), and back‐propagation artificial neural network (BP‐ANN) are applied here for the determination of the propylene concentration of a set of 83 production samples of ethylene–propylene copolymers from their infrared spectra. The set of available samples was split into (a) a training set, for models calculation; (b) a test set, for selecting the correct number of latent variables in PCR and PLS and the end point of the training phase of BP‐ANN; (c) a production set, for evaluating the predictive ability of the models. The predictive ability of the models is thus evaluated by genuine predictions. The model obtained by StepWise OLS turned out to be the best one, both in fitting and prediction. The study of the breakdown number of samples to be included in the training set showed that at least 52 experiments are necessary to build a reliable and predictive calibration model. It can be concluded that FTIR spectroscopy and OLS can be properly employed for monitoring the synthesis or the final product of ethylene–propylene copolymers, by predicting the concentration of propylene directly along the process line. © 2008 Wiley Periodicals, Inc. J Appl Polym Sci, 2008