| Titre : |
Machine vision inspection system for detection of leather surface defects |
| Type de document : |
texte imprimé |
| Auteurs : |
Malathy Jawahar, Auteur ; K. Vani, Auteur ; Chandra Babu Narasimhan Kannan, Auteur |
| Année de publication : |
2019 |
| Article en page(s) : |
p. 10-19 |
| Note générale : |
Bibliogr. |
| Langues : |
Américain (ame) |
| Catégories : |
Analyse d'image L'analyse d'image est la reconnaissance des éléments contenus dans l'image. Il ne faut pas confondre analyse (décomposition en éléments) et traitement (action sur les composantes) de l'image.
Cuir
Cuirs et peaux -- Défauts -- Classification
Cuirs et peaux -- Texture
Détection de défauts (Ingénierie)
Imagerie (technique)
Qualité -- Contrôle
Réseaux neuronaux (informatique)
|
| Index. décimale : |
675 Technologie du cuir et de la fourrure |
| Résumé : |
Leather quality inspection is very important in assessing the effective cutting value that can be obtained from the leather. Current practice involves an expert to inspect each piece of leather individually and detect defects manually. However, such a manual inspection is highly subjective and varies quite considerably from one assessor to another. Often this subjectivity leads to dispute between the buyer and the seller of the leathers and hence attempts are made to automate this. Automatic leather defect classification is a challenging research problem due to the difficulties that arise when segmenting defects from the leather background and determining the characteristics that describe the defects objectively. The present study describes application of machine vision system to capture leather surface images and the novel multi-level thresholding algorithm to segment defective and non-defective regions of leather followed by texture feature extraction to objectively quantify the leather surface defects. A dataset consisting of 90 leather images comprising 20 good leather and 50 defective samples has been used in the study. Experimental results on the leather defect image library database achieved an accuracy of 90% using neural network as classifier, confirming potential of using the proposed system for automatic leather defect classification. |
| Note de contenu : |
- Materials
- Image acquisition system
- Image analysis
- Image segmentation
- Feature extraction using texture analysis
- Defect classification using artificial neural network |
| En ligne : |
https://drive.google.com/file/d/19bCDm5My0DozDCYyRxrzlQuQkzRwxUhI/view?usp=drive [...] |
| Format de la ressource électronique : |
Pdf |
| Permalink : |
https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=31549 |
in JOURNAL OF THE AMERICAN LEATHER CHEMISTS ASSOCIATION (JALCA) > Vol. CXIV, N° 1 (01/2019) . - p. 10-19
Aller sur edunet
Accueil
Machine vision inspection system for detection of leather surface defects in JOURNAL OF THE AMERICAN LEATHER CHEMISTS ASSOCIATION (JALCA), Vol. CXIV, N° 1 (01/2019)
