An Automated System for Fabric Faults Inspection
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24410%2F17%3A00004278" target="_blank" >RIV/46747885:24410/17:00004278 - isvavai.cz</a>
Result on the web
<a href="http://www.amazon.com/Automated-System-Fabric-Faults-Inspection/dp/3330842628" target="_blank" >http://www.amazon.com/Automated-System-Fabric-Faults-Inspection/dp/3330842628</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
An Automated System for Fabric Faults Inspection
Original language description
This work utilizes a digital camera to acquire and transmit fabric images to a computer which enhances and extracts the features for each image.Then, the features are processed using Artificial Intelligence technique to detect and classify if the fabric has a defect or not and classify 10 fabric defects. Two approaches have been used for classification using statistical features only, spectral features only or both. The first approach classifies all the defects in one step. The results show that using both statistical and spectral features with each other give a 95.5% correct classification. The second approach classifies the defect on three steps.The first step classifies if the fabric sample has a defect or free defect. The results show that statistical features get the best classification with the least time with 91% percentage. The second step classifies the direction of the defect; Area, Warp or weft. The use of both features results, a 95.5% classification rate. The third step classifies the defect. For the area defects, Fourier features get a 100% classification. While using statistical features results a 100% correct classification for warp and weft defects.
Czech name
—
Czech description
—
Classification
Type
B - Specialist book
CEP classification
—
OECD FORD branch
20503 - Textiles; including synthetic dyes, colours, fibres (nanoscale materials to be 2.10; biomaterials to be 2.9)
Result continuities
Project
<a href="/en/project/LO1201" target="_blank" >LO1201: DEVELOPMENT OF THE INSTITUTE FOR NANOMATERIALS, ADVANCED TECHNOLOGIES AND INNOVATION</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
ISBN
9783330842625
Number of pages
164
Publisher name
Noor Publishing
Place of publication
Germany
UT code for WoS book
—