TU Darmstadt / ULB / TUbiblio

Stereo-Image Normalization of Voluminous Objects Improves Textile Defect Recognition

Siegmund, Dirk and Kuijper, Arjan and Braun, Andreas (2016):
Stereo-Image Normalization of Voluminous Objects Improves Textile Defect Recognition.
In: Advances in Visual Computing, Springer International Publishing, In: Advances in Visual Computing. 12th International Symposium, ISVC 2016, Las Vegas, NV, USA, December 12-14, 2016, In: Lecture Notes in Computer Science (LNCS); 10072, DOI: 10.1007/978-3-319-50835-1₁₇,
[Conference or Workshop Item]

Abstract

The visual detection of defects in textiles is an important application in the textile industry. Existing systems require textiles to be spread flat so they appear as 2D surfaces, in order to detect defects. In contrast, we show classification of textiles and textile feature extraction methods, which can be used when textiles are in inhomogeneous, voluminous shape. We present a novel approach on image normalization to be used in stain-defect recognition. The acquired database consist of images of piles of textiles, taken using stereo vision. The results show that a simple classifier using normalized images outperforms other approaches using machine learning in classification accuracy.

Item Type: Conference or Workshop Item
Erschienen: 2016
Creators: Siegmund, Dirk and Kuijper, Arjan and Braun, Andreas
Title: Stereo-Image Normalization of Voluminous Objects Improves Textile Defect Recognition
Language: English
Abstract:

The visual detection of defects in textiles is an important application in the textile industry. Existing systems require textiles to be spread flat so they appear as 2D surfaces, in order to detect defects. In contrast, we show classification of textiles and textile feature extraction methods, which can be used when textiles are in inhomogeneous, voluminous shape. We present a novel approach on image normalization to be used in stain-defect recognition. The acquired database consist of images of piles of textiles, taken using stereo vision. The results show that a simple classifier using normalized images outperforms other approaches using machine learning in classification accuracy.

Title of Book: Advances in Visual Computing
Series Name: Lecture Notes in Computer Science (LNCS); 10072
Publisher: Springer International Publishing
Uncontrolled Keywords: Guiding Theme: Digitized Work, Research Area: Computer vision (CV), 3D Image processing, Multi-view stereo, Machine learning, Pattern recognition
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: Advances in Visual Computing. 12th International Symposium, ISVC 2016
Event Location: Las Vegas, NV, USA
Event Dates: December 12-14, 2016
Date Deposited: 06 May 2019 07:25
DOI: 10.1007/978-3-319-50835-1₁₇
Export:

Optionen (nur für Redakteure)

View Item View Item