Accueil
Détail de l'auteur
Auteur Denis Ashok Sathia Seelan |
Documents disponibles écrits par cet auteur
Ajouter le résultat dans votre panier Affiner la recherche
Deep learning and machine learning neural network approaches for multi class leather texture defect classification and segmentation / Praveen Kumar Moganam in JOURNAL OF LEATHER SCIENCE AND ENGINEERING, Vol. 4 (Année 2022)
[article]
Titre : Deep learning and machine learning neural network approaches for multi class leather texture defect classification and segmentation Type de document : texte imprimé Auteurs : Praveen Kumar Moganam, Auteur ; Denis Ashok Sathia Seelan, Auteur Année de publication : 2022 Article en page(s) : 21 p. Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Apprentissage automatique L'apprentissage automatique (en anglais : machine learning, litt. "apprentissage machine"), apprentissage artificiel ou apprentissage statistique est un champ d'étude de l'intelligence artificielle qui se fonde sur des approches mathématiques et statistiques pour donner aux ordinateurs la capacité d'"apprendre" à partir de données, c'est-à -dire d'améliorer leurs performances à résoudre des tâches sans être explicitement programmés pour chacune. Plus largement, il concerne la conception, l'analyse, l'optimisation, le développement et l'implémentation de telles méthodes. (Wikipedia)
Cuirs et peaux -- Défauts
Détection de défauts (Ingénierie)
Réseaux neuronaux (informatique)Tags : 'Réseaux de neurones à convolution' 'Classificateur d'apprentissage automatique' 'Défauts du cuir' 'Classement multi-classes' 'Carte d'activation classe' Segmentation Index. décimale : 675 Technologie du cuir et de la fourrure Résumé : Modern leather industries are focused on producing high quality leather products for sustaining the market competitiveness. However, various leather defects are introduced during various stages of manufacturing process such as material handling, tanning and dyeing. Manual inspection of leather surfaces is subjective and inconsistent in nature; hence machine vision systems have been widely adopted for the automated inspection of leather defects. It is necessary develop suitable image processing algorithms for localize leather defects such as folding marks, growth marks, grain off, loose grain, and pinhole due to the ambiguous texture pattern and tiny nature in the localized regions of the leather. This paper presents deep learning neural network-based approach for automatic localization and classification of leather defects using a machine vision system. In this work, popular convolutional neural networks are trained using leather images of different leather defects and a class activation mapping technique is followed to locate the region of interest for the class of leather defect. Convolution neural networks such as Google net, Squeeze-net, RestNet are found to provide better accuracy of classification as compared with the state-of-the-art neural network architectures and the results are presented. Note de contenu : - MACHINE VISION-BASED LEATHER INSPECTION SYSTEM : Leather Image acquisition - Leather texture defects
- DEEP LEARNING NEURAL NETWORK APPROACH FOR CLASSIFICATION AND LOCALIZATION OF LEATHER DEFECTS : Leather image Data Set preparation and preprocessing - Deep learning convolutional neural network architectures - Visualization of region of interest for defect localization
- MACHINE LEARNING BASED APPROACHES FOR MULTI CLASS DEFECT CLASSIFICATION OF LEATHER DEFECTS : Hand crafted Feature extraction from leather images - Shallow feed-forward neural network-based machine learning classifier
- PERFORMANCE METRICS OF DEEP LEARNING AND MACHINE LEARNING CLASSIFIERS
- RESULTS AND DISCUSSION : Feature maps of convolution neural networks - Feature extraction using GLCM, autocorrelation - Training and testing performance of deep learning neural networks
Training performance of shallow feed forward neural network classifier - Classification performance of deep learning neural networks - Classification performance of machine learning approaches - Class activation maps for selection of region of interest in leather imagesDOI : https://doi.org/10.1186/s42825-022-00080-9 En ligne : https://link.springer.com/content/pdf/10.1186/s42825-022-00080-9.pdf Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=37575
in JOURNAL OF LEATHER SCIENCE AND ENGINEERING > Vol. 4 (Année 2022) . - 21 p.[article]