Computer vision and its application in detecting fabric defects

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24410%2F17%3A00004280" target="_blank" >RIV/46747885:24410/17:00004280 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.sciencedirect.com/science/article/pii/B978008101217800004X" target="_blank" >http://www.sciencedirect.com/science/article/pii/B978008101217800004X</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/B978-0-08-101217-8.00004-X" target="_blank" >10.1016/B978-0-08-101217-8.00004-X</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Computer vision and its application in detecting fabric defects

Popis výsledku v původním jazyce

There is a growing need to replace the visual fabric inspection with automated systems that detect and classify fabric defects. The digital processing of the fabric images utilizes different methods that offer a large set of image features, and the correlation between those features lead to problems during the fabric fault classification and reduces the performance of the classifiers. This chapter will introduce the different types and classifications for fabric defects, then their image analysis techniques. In the image analysis, a combination of statistical (spatial) and Fourier transform (spectral) features were presented for extraction from images of frequent fabric faults. The principal component analysis was implemented to reduce the dimensionality of the input feature dataset and its theoretical background was presented in this chapter. To classify samples, the artificial neural networks were introduced as a decision assisting soft-computing tool that helps in classifying the fabric fault categories. A practical application of these principles was introduced at the last section of the chapter with an emphasis on the classification process where different classifiers as well as different fabric descriptors (features) datasets were implemented. Finally, an overview for the future opportunities and challenges was given in closing this chapter.

Název v anglickém jazyce

Computer vision and its application in detecting fabric defects

Popis výsledku anglicky

There is a growing need to replace the visual fabric inspection with automated systems that detect and classify fabric defects. The digital processing of the fabric images utilizes different methods that offer a large set of image features, and the correlation between those features lead to problems during the fabric fault classification and reduces the performance of the classifiers. This chapter will introduce the different types and classifications for fabric defects, then their image analysis techniques. In the image analysis, a combination of statistical (spatial) and Fourier transform (spectral) features were presented for extraction from images of frequent fabric faults. The principal component analysis was implemented to reduce the dimensionality of the input feature dataset and its theoretical background was presented in this chapter. To classify samples, the artificial neural networks were introduced as a decision assisting soft-computing tool that helps in classifying the fabric fault categories. A practical application of these principles was introduced at the last section of the chapter with an emphasis on the classification process where different classifiers as well as different fabric descriptors (features) datasets were implemented. Finally, an overview for the future opportunities and challenges was given in closing this chapter.

Druh

C - Kapitola v odborné knize

CEP obor

—

OECD FORD obor

20503 - Textiles; including synthetic dyes, colours, fibres (nanoscale materials to be 2.10; biomaterials to be 2.9)

Projekt

<a href="/cs/project/LO1201" target="_blank" >LO1201: ROZVOJ ÚSTAVU PRO NANOMATERIÁLY, POKROČILÉ TECHNOLOGIE A INOVACE TECHNICKÉ UNIVERZITY V LIBERCI</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název knihy nebo sborníku

Applications of Computer Vision in Fashion and Textiles

ISBN

978-0-08-101217-8

Počet stran výsledku

41

Strana od-do

61-101

Počet stran knihy

302

Název nakladatele

Woodhead Publishing

Místo vydání

—

Kód UT WoS kapitoly

—