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

Related Articles

Przewidywanie właściwości dzianin lewo-prawych podczas ściskania stosując metodę elementów skończonych opartą na modelu ściskania pianki

Publikacja dotyczy analizy kompresji dzianin lewo-prawych o trzech wariantach splotów. Scharakteryzowano parametry dzianin, tj. ścisłości rządkowe i kolumienkowe, masy, zapis splotu w rzeczywistym przebiegu i na igłach....

Optimisation of Selected Components of a Roller Carding Machine in the Aspect of Improving their Cooperation Quality

The quality of web produced by a carding machine is largely influenced by the shape and height of the gaps between card clothings of workers and the doffer cooperating with the main cylinder as well as between the doffe...

Photometric Properties of Retroreflective Materials in Dependence on their Structure and Angle of Illumination

The purpose of high visibility products is to reflect light at a low angle towards the source, such as vehicle headlights. The article presents measurements of the photometric properties of selected retroreflective mater...

Study on Radiant Heat Flux Transfer Through Aluminised Multi-Layer Fabric at Low Level Thermal Radiation

This paper presents a method to measure the thermal radiant flux transfer through aluminised multi-layer protective clothing. The multilayer fabric consisted of a layer of aluminum foil, one of glass fabric, and a layer...

Effect of Blending Methodologies on Cotton Mélange Yarn Quality

Fibre of dyed mélange yarn is becoming an emerging product in the field of textiles. The quality of mélange yarn is largely influenced by the types of blending methodologies. There exists hardly any reported work where t...

Download PDF file
  • EP ID EP228984
  • DOI 10.5604/01.3001.0010.5370
  • Views 70
  • Downloads 0

How To Cite

Jian Zhou, Jun Wang, Honggang Bu (2017). Fabric Defect Detection Using a Hybrid and Complementary Fractal Feature Vector and FCM-based Novelty Detector. Fibres and Textiles in Eastern Europe, 25(6), 46-52. https://europub.co.uk/articles/-A-228984