Fabric Defect Detection Using a Hybrid and Complementary Fractal Feature Vector and FCM-based Novelty Detector

Apply

Fabric Defect Detection Using a Hybrid and Complementary Fractal Feature Vector and FCM-based Novelty Detector

Journal Title: Fibres and Textiles in Eastern Europe - Year 2017, Vol 25, Issue 6

Abstract

Automated detect detection in woven fabrics for quality control is still a challenging novelty detection problem. This work presents five novel fractal features based on the box-counting dimension to address the novelty detection of fabric defect. Making use of the formation of woven fabric, the fractal features are extracted in a one-dimension series obtained by projecting a fabric image along the warp and weft directions, where their complementarity in discriminating defects is taken into account. Furthermore a new novelty detector based on fuzzy c-means (FCM) is devised to deal with one-class classification of the features extracted. Finally, by jointly applying the features proposed and the FCM based novelty detector, we evaluate the method proposed for eight datasets with different defects and textures, where satisfying results are achieved with a low overall missing detection rate.

Authors and Affiliations

Jian Zhou, Jun Wang, Honggang Bu

Keywords

Novel and Efficient Method to Reduce the Jute Fibre Prickle Problem

The physical especially bending properties of jute fibres treated with dimethyl sulphoxide (DMSO) were studied in this work. To the knowledge of these authors, the influence of DMSO treatment on the prickle properties of...

Numerical and Experimental Research on the Impact of the Twaron T750 Fabric Layer Number on the Stab Resistance of a Body Armour Package

The aim of the paper was to research how the depth of penetration in dependence on the fabric layer number used in the ballistic package is changed. During the research, the following methodology was adopted: the object...

EP ID EP228984
DOI 10.5604/01.3001.0010.5370
Views 67
Downloads 0