A novel approach to using neural networks to predict the colour of fibre blends / Caroline Hemingray in COLORATION TECHNOLOGY, Vol. 132, N° 4 (08/2016)  

[article]  inCOLORATION TECHNOLOGY > Vol. 132, N° 4 (08/2016) . - p. 297-303 Titre : A novel approach to using neural networks to predict the colour of fibre blends Type de document : texte imprimé Auteurs : Caroline Hemingray, Auteur ; Stephen Westland, Auteur Année de publication : 2016 Article en page(s) : p. 297-303 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Mélanges de fibres Prévision, Théorie de la Réseaux neuronaux (informatique) Viscose Index. décimale : 667.9 Revêtements et enduits Résumé : 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. DOI : 10.1111/cote.12220 En ligne : https://onlinelibrary.wiley.com/doi/epdf/10.1111/cote.12220 Format de la ressource électronique : Pdf Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=26731 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
18246	-	Périodique	Bibliothèque principale	Documentaires	Disponible

Towards the design of a blending system for precoloured fibres / Caroline Hemingray in COLORATION TECHNOLOGY, Vol. 135, N° 5 (10/2019)  

[article]  inCOLORATION TECHNOLOGY > Vol. 135, N° 5 (10/2019) . - p. 407-414 Titre : Towards the design of a blending system for precoloured fibres Type de document : texte imprimé Auteurs : Caroline Hemingray, Auteur ; Louise Dean, Auteur ; Stephen Westland, Auteur Année de publication : 2019 Article en page(s) : p. 407-414 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Chimie physique et théorique Couleur -- Analyse Mélanges de fibres Tricot Index. décimale : 667.3 Teinture et impression des tissus Résumé : In order to create a commercial system for blending precoloured fibres that will appear visually solid once combined, it is necessary to understand the maximum colour difference required between the blend components. Based on this understanding, the lowest number of primaries required to populate a given colour gamut can be determined. A series of psychophysical experiments was carried out to explore the colour difference between fibre-blend components and whether the resulting blended samples are perceived as visually solid. Experiments were carried out with loose stock fibre, yarn and knitted samples. Generally, it was found that the likelihood a blend appeared as visually solid increased as the average colour difference between the blend components, or primaries, decreased. The value of the mean colour difference at which 50% of participants viewed the blend as being visually solid was found to be 20.8, 20.5 and 18.0 for fibre, yarn and knitted samples, respectively. Consequently, it was found that it was more difficult to obtain a solid shade with the knitted form than with the loose stock fibre form. Note de contenu : - EXPERIMENTAL : Determination of the colour difference threshold between primaries - Preparation of samples - Physicophysical experiments - RESULTS AND DISCUSSION : Implications for commercial fibre blending systems DOI : 10.1111/cote.12428 En ligne : https://onlinelibrary.wiley.com/doi/epdf/10.1111/cote.12428 Format de la ressource électronique : Pdf Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=33072 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
21251	-	Périodique	Bibliothèque principale	Documentaires	Disponible

---

1 (1 - 2 / 2)