Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Multi-disciplinary Studies | en_US |
| dc.contributor | Department of Electronic Engineering | en_US |
| dc.creator | Chan, Hing-wan | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/1975 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Evaluation of defect identification algorithms for textile woven fabrics | en_US |
| dcterms.abstract | In the textile industry, it is important to perform quality inspection during the production of woven fabrics. A good fabric inspection system can lower the production cost, increase the yield, improve the quality of finished products and ultimately increase the profit. At present, much of the fabric inspection is performed manually. An automatic fabric inspection system is desirable to improve the quality of woven fabrics and to lower the production cost. Furthermore, it provides consistent results that correlate with the quality control standard of the textile industry. An automatic fabric inspection system consists of an illumination system, a digital camera system, an intelligent defect detection software and an alarm system. This report will focus on the intelligent defect detection software. There are many types of fabrics and nearly 400 different kinds of defects. It is impossible to propose a mathematical model to fit in all situations. So, it may be more promising to combine several simple algorithms together. As a result, strengths of each algorithm can be complemented with each other to make them more powerful. Five algorithms have been studied in this report: subimage colour, subimage roughness, histogram analysis, aligned correlation coefficient and Fourier analysis. A Matlab program is developed to evaluate each algorithm's performance in fabric inspection. Each algorithm's optimum values of parameters, e.g. subimage size and number of histogram bins, are evaluated with explanations. Optimum defect detection rate of each algorithm for each defect is also listed out in tables. Applications and limitations of each algorithm are described and analysed in detail. This report will illustrate that combining these algorithms would obtain an efficient, effective and reliable fabric inspection system. | en_US |
| dcterms.extent | 141 leaves : ill. (some col.) ; 30 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2002 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.LCSH | Textile fabrics | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b16259919.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 24.12 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/1975