Kazım HANBAY, Ömer Faruk ÖZGÜVEN, Muhammed Fatih TALU

Fourier dönüşümü kullanılarak gerçek zamanlı kumaş hatası tespiti

Kumaş üretiminde yüzey hatalarını tespit etmek için gerçek zamanlı hata tespit sistemlerine ihtiyaçduyulmaktadır. Mevcut durumda örgü kumaş üretiminde gerçek zamanlı hata tespit sistemi yoktur. Buçalışmada gerçek zamanlı kumaş hatası tespit sistemi geliştirilmiş ve yuvarlak örgü makinesi üzerinde testedilmiştir. Kumaş görüntüsünün dokusal özellikleri Fourier dönüşümü temelinde çıkarılmıştır. Bu dokusalözellikler 7 tane olup kumaş görüntüsünün Fourier frekans spektrumunun yatay ve dikey yönlerindenhesaplanmıştır. Önerilen metodunun performansı ilk olarak kapsamlı veri tabanı temel alınarak gerçekzamanlı olmayan çalışmalar yolu ile değerlendirilmiştir. Önerilen metot gerçek zamanlı kontrolde de başarısağlayabilecek üstün bir performans elde etmiştir. İkinci olarak, endüstriyel şartlarda etkin bir kumaş hatasıkontrolü için gerçek zamanlı makine görmesi sistemi tasarlanmıştır. Gerçek zamanlı hata tespit sistemiçizgi kamera tarafından elde edilen kumaş görüntüleri analiz edilerek test edilmiştir. Deneysel sonuçlarönerilen hata tespit modelinin yaygın örgü kumaş hatalarını başarılı bir şekilde tespit edebildiğinigöstermiştir.

Real time fabric defect detection by using fourier transform

In fabric productions, real time defect detection systems are needed to detect the surface defects. There iscurrently no real time defect detection system in knitting fabric production. In this paper, a real time fabricdefect detection system is developed and is tested on circular knitting machine. Textural features of fabricimage are extracted based on Fourier transform. These textural features are seven and are calculated fromthe horizontal and vertical directions of Fourier frequency spectrum of the fabric image. The performanceof the proposed method is firstly evaluated off-line through experiments based on comprehensive fabricdatabase. The proposed method obtains superior performance, which also proves its utility in real-time inspection. Secondly, a real time machine-vision system has been designed for an efficient detection of thefabric defects under industrial conditions. Real time defect detection system is tested automatically byanalyzing fabric images captured by a line scan camera. Experimental results show that the proposeddetection model can successfully detect common circular knitting fabric defects.

PDF

___

1. Ngan H.Y.T., Pang G.K.H., Yung N.H.C., Automated Fabric Defect Detection-A Review, Image and Vision Comput., 29, 442-458, 2011.
2. Hamdi A.A., Sayed M.S., Fouad M.M., Hadhoud M.M., Fully Automated Approach for Patterned Fabric Defect Detection, Fourth International Japan-Egypt Conference on Electronics, Communications and Computers (JEC-ECC), Cairo, 48-51, 31 Mayıs-2 Haziran 2016.
3. Jing J., Wang J., Li P., Li Y., Automatic Classification of Woven Fabric Structure by Using Learning Vector Quantization, Procedia Eng., 15, 5005-5009, 2011.
4. Tilocca A., Borzone P., Carosio S., Durante A., Detecting Fabric Defects with A Neural Network Using Two Kinds of Optical Patterns, Text. Res. J., 72, 545-550, 2002.
5. Li Y., Zhao W., Pan J., Deformable Patterned Fabric Defect Detection with Fisher Criterion-Based Deep Learning, IEEE Trans. Autom. Sci. Eng., 99, 1-9, doi: 10.1109/TASE.2016.2520955.
6. Tsang C.S.C., Ngan H.Y.T., Pang G.K.H., Fabric Inspection Based on the Elo Rating Method, Pattern Recognit., 51, 378-394, 2016.
7. Jayashree V., Subbaramn S., Hybrid Approach Using Correlation and Morphological Approaches for GFDD of Plain Weave Fabric, IEEE Control and System Graduate Research Colloquium (ICSGRC), 197-202, 2012.
8. Seker A.K., Peker A., Yuksek A.G., Delibas E., Fabric Defect Detection Using Deep Learning, 24th Signal Processing and Communication Application Conference (SIU), Zonguldak, 1437-1440, 2016.
9. Stivanello M.E., Vargas S., Roloff M.L., Stemmer M. R., Automatic Detection and Classification of Defects in Knitted Fabrics, IEEE Lat. Am. Trans.,14 (7), 3065- 3073, 2016.
10. Selver M.A., Avşar V., Özdemir H., The Journal of The Textile Institute, 105 (9), 998-1007, 2014.
11. Li Y., Ai J., Sun C., Online Fabric Defect Inspection Using Smart Visual Sensors, Sensors, 13 (4), 4659- 4673, 2013.
12. Hanbay K., Talu M.F., Ozguven O.F., Ozturk D., Fabric Defect Detection Methods for Circular Knitting Machines, IEEE 23th Signal Processing and Communications Applications Conference (SIU), 735- 738, 16-19 May 2015.
13. Zhou Y.W., Song G.L., Fang M., The Automating Detecting of Stitch Distortion in Knitted Fabric by Image Processing Technology, International Conference on Control, Automation and Systems Engineering (CASE), 1-3, 2011.
14. Zhao D.X., Wang H., Zhu J.L., Li J.L., Research on a New Fabric Defect Identification Method, International Conference on Computer Science and Software Engineering, 814-817, 2008.
15. Ismail N., Syahrir W.M., Zain J.M., Hai T., Fabric Authenticity Method Using Fast Fourier Transformation Detection, International Conference on Electrical, Control and Computer Engineering (INECCE), 233-237, 2011.
16. Abou-Taleb H.A., Sallam A.T.M., On-line Fabric Defect Detection and Full Control in a Circular Knitting Machine, Autex Research Journal, 8 (1), 21- 29, 2008.
17. Hanbay K., Talu M.F., Kumaş Hatalarının Online/offline Tespit Sistemleri ve Yöntemleri, Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 18 (1), 49-69, 2014.
18. Han R., Zhang L., Fabric Defect Detection Method Based on Gabor Filter Mask, Intelligent Systems, Global Congress on Intelligent Systems, 184-188, 2009.
19. Jing J., Zhang H., Wang J., Li P., Jia J., Fabric Defect Detection Using Gabor Filters and Defect Classification Based on LBP and Tamura Method, J. Text. Inst., 104, 18-27, 2012.
20. Tong L., Wong W.K., Kwong C.K., Differential Evolution-based Optimal Gabor Filter Model for Fabric Inspection, Neurocomputing, 173, 1386-1401, 2016.
21. Kırıcı T.K., Marmaralı A., Online Fault Detection System for Circular Knitting Machines, Tekstil ve Konfeksiyon, 21 (2), 164-170, 2011.
22. Das B., Turkoglu I., Classification of DNA sequences using numerical mapping techniques and Fourier transformation, Journal of the Faculty of Engineering and Architecture of Gazi University, 31 (4), 921-932, 2016.
23. Cooley J.W., Tukey J.W., An Algorithm for the Machine Calculation of Complex Fourier Series, Math. Comput., 19, 297-301, 1995.
24. Akben S.B., Alkan A., Density-based feature extraction to improve the classifıcation performance in the datasets having low correlation between attributes, Journal of the Faculty of Engineering and Architecture of Gazi University, 30 (4), 597-603, 2015.
25. Kasım O., Kuzucuoglu A.E., Detection and classification of leukocyte cells from smear image, Journal of the Faculty of Engineering and Architecture of Gazi University, 30 (1), 95-109, 2015.
26. Guo Z., Li Q., Zhang, L., You J., Zhang D., Liu W., Is Local Dominant Orientation Necessary for the Classification of Rotation Invariant Texture?, Neurocomputing, 116, 182-191, 2013