Accueil
Catégories
Ajouter le résultat dans votre panier Affiner la recherche
Etendre la recherche sur niveau(x) vers le bas
Research on sheepskin contour extraction method based on computer vision measurement technology in JOURNAL OF THE AMERICAN LEATHER CHEMISTS ASSOCIATION (JALCA), Vol. CXVI, N° 8 (08/2021)
[article]
Titre : Research on sheepskin contour extraction method based on computer vision measurement technology Type de document : texte imprimé Année de publication : 2021 Article en page(s) : p. 267-276 Note générale : Bibliogr. Langues : Américain (ame) Catégories : Algorithmes
Automatisation
Cuirs et peaux de moutons
Mesure -- Instruments
Mesures optiques
RognageIndex. décimale : 675 Technologie du cuir et de la fourrure Résumé : Manual trimming of sheepskin is intensive labor, and the working environment is full of rotten smells. The tannery is facing increasingly severe recruitment difficulties. This paper uses computer vision technology to study automatic recognition of sheepskin contours, which is the basis for the subsequent automatic trimming of sheepskin. After observing and analyzing the raw sheepskin images collected by an industrial array camera, a method of sheepskin contour extraction based on computer vision measurement technology is proposed in this paper. This method uses the fast Otsu threshold algorithm based on the pixel set to perform binary image segmentation. Combined with morphological processing for edge defect filling and topology analysis of boundary contour tracking algorithm to extract maximum contour information, it has a pixel-level three-dimensional de-noising preprocessing function and can accurately extract the sheepskin contour in the raw sheepskin image. The experimental results show that using the fast Otsu threshold algorithm proposed in this paper for binary segmentation to extract sheepskin contours, the detection rate is nearly 160% faster than the traditional Otsu algorithm, the edge protection is better, the error segmentation is reduced by nearly 3% and it has good anti-noise performance. It can meet the industrial production requirements of subsequent automatic cutting of sheepskin. Note de contenu : - MATERIALS AND METHODS : A preprocessing system based on pixel level 3D de-noising model - Fast Otsu's threshold segmentation algorithm based on the idea of pixel set - Image segmentation optimization threshold method - Accelerated search threshold strategy - Image segmentation algorithm flow - Morphological defect repair - Contour extraction - Boundary contour tracking technology - Target contour extraction
- EXPERIMENTAL RESULTS AND ANALYSIS : Effect analysis of contour extraction method - Comparison and analysis of pre-treatment de-noising effect - Force analysis of image segmentation algorithm
- Table 1 : The evaluation values
- Table 2 : Comparison of the efficiency of Otsu 2D-Otsu and this paper (ms)DOI : https://doi.org/10.34314/jalca.v116i8.4355 En ligne : https://drive.google.com/file/d/1ObCvI0CPwYSUC5bRVpPdivY4Cl9Jj8Td/view?usp=drive [...] Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=36083
in JOURNAL OF THE AMERICAN LEATHER CHEMISTS ASSOCIATION (JALCA) > Vol. CXVI, N° 8 (08/2021) . - p. 267-276[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 22875 - Périodique Bibliothèque principale Documentaires Disponible A self-learning AI algorithm to optimize composites production scheduling in JEC COMPOSITES MAGAZINE, N° 145 (04-05/2022)
[article]
Titre : A self-learning AI algorithm to optimize composites production scheduling Type de document : texte imprimé Année de publication : 2022 Article en page(s) : p. 30-31 Langues : Anglais (eng) Catégories : Algorithmes
Automatisation
Composites
Intelligence artificielle
Production -- PlanificationIndex. décimale : 668.4 Plastiques, vinyles Résumé : Plataine is a leading provider of industrial Ià T and AI-based optimization solutions for advanced manufacturing. The company's intelligent, connected digital assistants and the Practimum-Optimum AI-algorithm take manufacturing to the next level by automating and optimizing decision flows on the production floor. Note de contenu : - Spreading the "Factory of the future" all over the world
- Optimal and practical schedules to improve delivery times and KPIs
- A wide range of applicatio sectors
- Optimizing production to reduce environmental impactPermalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=38697
in JEC COMPOSITES MAGAZINE > N° 145 (04-05/2022) . - p. 30-31[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 23695 - Périodique Bibliothèque principale Documentaires Disponible Simulation numérique des écoulements de fluides à seuil in LES CAHIERS DE RHEOLOGIE, Vol. XI, N° 3-4 (10/1993)
[article]
Titre : Simulation numérique des écoulements de fluides à seuil Type de document : texte imprimé Année de publication : 1993 Langues : Français (fre) Catégories : Algorithmes
Fluides à seuils
Fluides, Mécanique des
Polymères
Rhéologie
Simulation par ordinateur
Stockes, Théorème deIndex. décimale : 532.05 Mécanique des fluides et des liquides - Dynamique (cinétique et cinématique) Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=5799
in LES CAHIERS DE RHEOLOGIE > Vol. XI, N° 3-4 (10/1993)[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 002104 - Périodique Bibliothèque principale Documentaires Disponible Spectrophotometric colour matching algorithm for top-dyed melange yarn, based on an artificial neural network / Jiajia Shen in COLORATION TECHNOLOGY, Vol. 133, N° 4 (08/2017)
[article]
Titre : Spectrophotometric colour matching algorithm for top-dyed melange yarn, based on an artificial neural network Type de document : texte imprimé Auteurs : Jiajia Shen, Auteur ; Xiang Zhou, Auteur Année de publication : 2017 Article en page(s) : p. 341-346 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Algorithmes
Colorimétrie
Mélange de couleurs
Mesures optiques
Qualité -- Contrôle
Réseaux neuronaux (informatique)
Teinture -- Fibres textilesIndex. décimale : 667.3 Teinture et impression des tissus Résumé : 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. Note de contenu : - PROPOSED ALGORITHM FRAMEWORK : Prediction of the weighted average spectrum - Spectrophotometric colour matching algorithm
- APPLICATION AND DISCUSSION
- APPENDIX 1. Main code of prediction of weighted average spectrum
- APPENDIX 2. Recip prediction based on the ANN approach - Recipe prediction based on the sternes-Noechel model - Recipe prediction based on the Friele modelDOI : 10.1111/cote.12285 En ligne : https://drive.google.com/file/d/1_0vZV5AJsCJikPbY0C9oCHQYZFF13v2U/view?usp=drive [...] Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=28888
in COLORATION TECHNOLOGY > Vol. 133, N° 4 (08/2017) . - p. 341-346[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 19175 - Périodique Bibliothèque principale Documentaires Disponible A study of spectral reflectance reconstruction using the weighted fitting algorithm based on the Sino Colour Book / Yuexin Liu in COLORATION TECHNOLOGY, Vol. 140, N° 1 (02/2024)
[article]
Titre : A study of spectral reflectance reconstruction using the weighted fitting algorithm based on the Sino Colour Book Type de document : texte imprimé Auteurs : Yuexin Liu, Auteur ; Juan Li, Auteur ; Xin Wang, Auteur ; Xuetong Li, Auteur ; Yang Song, Auteur ; Rong Li, Auteur Année de publication : 2024 Article en page(s) : p. 61-74 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Algorithmes
Couleur -- Analyse
Spectroscopie de réflectanceIndex. décimale : 535.6 Couleur Résumé : The spectral reflectance of a colour is its most essential characteristic, and it does not change with changes of equipment or light source. Therefore, the reconstruction of spectral reflectance from parameters such as colour tristimulus value and RGB has attracted the attention of researchers. To avoid the occurrence of metamerism in the colour reproduction process and to achieve the purpose of colour spectral reproduction, the spectral reflectance and the optimal parameters of the reconstruction using the weighted fitting method were discussed experimentally with the colour data measured from the Sino Colour Book as the research object. The results show that the best results are obtained when the weighted fitting parameters are weighted by the third power and eight colour samples are involved in the fitting. The reconstructed spectral reflectance obtained by the weighted fitting method has little variation and high overlap with the actual spectral reflectance obtained at each hue and lightness, thus meets the requirements of practical applications. Note de contenu : - EXPERIMENTAL : Experimental samples: the Sino Colour Book
- THEORY : Weighted fitting algorithm - The relationship between spectral reflectance and colour tristimulus values
- EVALUATION METHODS : Colour difference - Spectral angle θ - Spectral index k - RMSE of the spectrum - Spectral similarity - Reconstruction pass rate
- RESULTS AND DISCUSSION : Influence of the weighted fitting parameters m and n on the reconstruction effectiveness - Spectral reflectance reconstruction effect evaluation
- Table 1 : Influence of the weighting power
- Table 2 : Influence of colour sample numbers involved in fittingDOI : https://doi.org/10.1111/cote.12691 En ligne : https://onlinelibrary.wiley.com/doi/epdf/10.1111/cote.12691 Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=40391
in COLORATION TECHNOLOGY > Vol. 140, N° 1 (02/2024) . - p. 61-74[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 24413 - Périodique Bibliothèque principale Documentaires Disponible Tailored composites for high volumes / Thomas Rettenwander in KUNSTSTOFFE INTERNATIONAL, Vol. 104, N° 10 (10/2014)
Permalink