TU Darmstadt / ULB / TUbiblio

An Integrated Deep Neural Network for Defect Detection in Dynamic Textile Textures

Siegmund, Dirk and Prajapati, Ashok and Kirchbuchner, Florian and Kuijper, Arjan (2018):
An Integrated Deep Neural Network for Defect Detection in Dynamic Textile Textures.
In: Progress in Artificial Intelligence and Pattern Recognition, Cham, Springer, In: International Workshop on Artificial Intelligence and Pattern Recognition (IWAIPR), Havana, Cuba, In: Lecture Notes in Computer Science (LNCS), 11047, ISSN 0302-9743,
DOI: 10.1007/978-3-030-01132-1_9,
[Online-Edition: https://doi.org/10.1007/978-3-030-01132-1_9],
[Conference or Workshop Item]

Abstract

This paper presents a comprehensive defect detection method for two common fabric defects groups. Most existing systems require textiles to be spread out in order to detect defects. This method can be applied when the textiles are not spread out and does not require any pre- processing. The deep learning architecture we present is based on transfer learning and localizes and recognizes cuts, holes and stain defects. Classification and localization is combined into a single system combining two different networks. The experiments this paper presents show that even without adding depth information, the network was able to distinguish between stain and shadow. This method has been successful even for textiles in voluminous shape and is less computationally intensive than other state-of-the-art methods.

Item Type: Conference or Workshop Item
Erschienen: 2018
Creators: Siegmund, Dirk and Prajapati, Ashok and Kirchbuchner, Florian and Kuijper, Arjan
Title: An Integrated Deep Neural Network for Defect Detection in Dynamic Textile Textures
Language: English
Abstract:

This paper presents a comprehensive defect detection method for two common fabric defects groups. Most existing systems require textiles to be spread out in order to detect defects. This method can be applied when the textiles are not spread out and does not require any pre- processing. The deep learning architecture we present is based on transfer learning and localizes and recognizes cuts, holes and stain defects. Classification and localization is combined into a single system combining two different networks. The experiments this paper presents show that even without adding depth information, the network was able to distinguish between stain and shadow. This method has been successful even for textiles in voluminous shape and is less computationally intensive than other state-of-the-art methods.

Title of Book: Progress in Artificial Intelligence and Pattern Recognition
Series Name: Lecture Notes in Computer Science (LNCS)
Volume: 11047
Place of Publication: Cham
Publisher: Springer
Uncontrolled Keywords: Deep learning, Defect detection, Computer vision, Textile industry, Quality assurance
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: International Workshop on Artificial Intelligence and Pattern Recognition (IWAIPR)
Event Location: Havana, Cuba
Date Deposited: 19 Jun 2019 11:22
DOI: 10.1007/978-3-030-01132-1_9
Official URL: https://doi.org/10.1007/978-3-030-01132-1_9
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item