Warp-knitted Fabric Defect Segmentation Based on the Shearlet Transform

Dong, Z.; Xia, D.; Ma, P.; Jiang, G.

doi:10.5604/01.3001.0010.4633

Artykuł - szczegóły

Tytuł artykułu

Warp-knitted Fabric Defect Segmentation Based on the Shearlet Transform

Autorzy

Dong Z. , Xia D. , Ma P. , Jiang G.

Treść / Zawartość

Pełne teksty:

14_Dong_Xia_Ma_Jiang_Warp-knitted_87-94.pdf

Pobierz

Identyfikatory

DOI

10.5604/01.3001.0010.4633

Warianty tytułu

Analiza defektów dzianin na bazie transformacji Shearleta

Języki publikacji

Abstrakty

The Shearlet transform has been a burgeoning method applied in the area of image processing recently which, differing from the Wavelet transform, has excellent properties in processing singularities for multidimensional signals. Not only is it similar to the performance of the Curvelet transform, it also overcomes the disadvantage of the Curvelet transform with respect to discretization. In this paper, the Shearlet transform with segmented threshold de-nosing is proposed to segment a warp-knitted fabric defect. Firstly a warp-knitted fabric image of size 512*512 is filtered by the Laplacian Pyramid transform and decomposed into low frequency and high frequency coefficients. Secondly the high frequency coefficients are operated with a pseudo-polar grid and then convoluted by the window function. Thirdly the shearlet coefficients will be obtained through redefining the Cartesian coordinates from the pseudo-polar grid coordinates and de-noised by the segmented threshold method. Then the coefficients which have high energy are selected for reconstruction in an inverse way using the previous steps. Finally the iterative threshold method and object operation based on morphology are applied to segment out the defect profile. The experiment’s result states that the Shearlet transform shows excellent performance in segmenting a common warp-knitted fabric defect, indicating that the segment results can be applied for further defect automatic recognition.

Transformacja Shearleta jest ostatnio dynamicznie rozwijającą się metodą stosowaną w dziedzinie przetwarzania obrazu, która różni się od transformaty Wavelet i ma doskonałe właściwości w przetwarzaniu sygnałów wielowymiarowych. Transformacja Shearleta ma prostszą implementację dyskretną, niż przekształcenie Curveleta w oparciu o rygorystyczne i proste ramy matematyczne. Może także dostarczyć bardziej elastycznego rozkładu na podstawie reprezentacji wieloskalowej i geometrycznej. Ostateczny wynik segmentacji uzyskano poprzez powtarzalną segmentację progową i operację morfologiczną. Wyniki wykazały, że segmentowy profil uszkodzeń jest dość wyraźny i porównywalny w porównaniu z pierwotnymi wadami dzianiny.

Słowa kluczowe

warp-knitted fabric defect Shearlet transform Fourier transform segmented threshold de-nosing

defekt dzianiny transformacja Shearleta transformacja Fouriera

Wydawca

Sieć Badawcza Łukasiewicz - Łódzki Instytut Technologiczny

Czasopismo

Fibres & Textiles in Eastern Europe

Rocznik

2017

Tom

Vol. 25, no. 5 (125)

Strony

87--94

Opis fizyczny

Bibliogr. 27 poz., rys.

Twórcy

autor

Dong Z.

Ministry of Education, Jiangnan University, Engineering Research Center for Knitting Technology, Jiangsu, Wuxi, 214122, China

autor

Xia D.

Ministry of Education, Jiangnan University, Engineering Research Center for Knitting Technology, Jiangsu, Wuxi, 214122, China

autor

Ma P.

mapibo@jiangnan.edu.cn

Ministry of Education, Jiangnan University, Engineering Research Center for Knitting Technology, Jiangsu, Wuxi, 214122, China

autor

Jiang G.

Ministry of Education, Jiangnan University, Engineering Research Center for Knitting Technology, Jiangsu, Wuxi, 214122, China

Bibliografia

1. Jiang GM. Production technology of warp-knitted fabric-warp knitting theory and typical products.1st edn. Beijing: China Textile & Apparel Press, 2010: 1-3.
2. Ngan H Y T, Pang G K H, Yung N H C. Automated fabric defect detection – A review. Image & Vision Computing 2011; 29(7): 442-458.
3. Haralick R M. Statistical and structural approaches to texture. Proceedings of the IEEE 1979, 67(5): 786-804.
4. Haralick R M, Shanmugam K, Dinstein I. Textural Features for Image Classification. Systems Man & Cybernetics IEEE Transactions on, 1973, smc-3(6): 610-621.
5. Serra J. Image Analysis and Mathematical Morphology. Academic Press, Inc., 1982.
6. Conci A, Proença C B. A fractal image analysis system for fabric inspection based on a box-counting method. Computer Networks & Isdn Systems 1998; 30(98): 1887-1895.
7. Han Y, Shi P. An adaptive level-selecting wavelet transform for texture defect detection. Image & Vision Computing 2007; 25(8): 1239-1248.
8. Castellini C, Francini F, Longobardi G, et al. On-line textile quality control using optical Fourier transforms. Optics & Lasers in Engineering 1996; 24(1): 19-32.
9. Liu X, Su Z, Wen Z, et al. Slub Extraction in Woven Fabric Images Using Gabor Filters. Textile Research Journal 2008; 78(4): 320-325.
10. Hajimowlana S H, Muscedere R, Jullien G A, et al. 1D autoregressive modeling for defect detection in web inspection systems. Circuits and Systems. 1998. Proceedings. 1998 Midwest Symposium on. IEEE, 1998: 318-321.
11. Ozdemir S, Ercil A. Markov random fields and Karhunen-Loeve transforms for defect inspection of textile products. Emerging Technologies and Factory Automation, 1996. EFTA '96. Proceedings., 1996 IEEE Conference on. IEEE, 1996: 697-703.
12. Kumar A. Neural network based detection of local textile defects[J]. Pattern Recognition 2003; 36(7):1645-1659.
13. Bodnarova A, Bennamoun M, Kubik K K. Defect detection in textile materials based on aspects of the HVS. Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on. IEEE, 1998: 4423-4428 vol.5.
14. Bodnarova M B A. Digital Image Processing Techniques for Automatic Textile Quality Control. Systems Analysis Modelling Simulation 2003; volume 43(11): 1581-1614.
15. Ngan H Y T, Pang G K H, Yung N H C. Ellipsoidal decision regions for motif-based patterned fabric defect detection. Pattern Recognition 2010; 43(6): 2132-2144.
16. Kingsbury N. Complex Wavelets for Shift Invariant Analysis and Filtering of Signals. Applied & Computational Harmonic Analysis 2001; 10(3): 234-253.
17. Meyer F G, Coifman R R. Brushlets: A Tool for Directional Image Analysis and Image Compression. Applied & Computational Harmonic Analysis 1997, 4(2): 147-187.
18. Candès E J, Donoho D L. Ridgelets: A Key to Higher-Dimensional Intermittency? Philosophical Transactions of the Royal Society of London, 1999, 357(1760): 2495.
19. Candès E J, Donoho D L. New tight frames of curvelets and optimal representations of objects with C2 singularities. Communications on Pure & Applied Mathematics 2004; 57: 219-266.
20. Do M N, Vetterli M. The contourlet transform: an efficient directional multiresolution image representation. IEEE Trans Image Process. IEEE Transactions on Image Processing 2006; 14: 2091-2106.
21. Easley G, Labate D, Lim W Q. Sparse directional image representations using the discrete shearlet transform. Applied & Computational Harmonic Analysis 2008, 25(1): 25-46.
22. Guo K, Labate D. Optimally sparse multidimensional representation using shearlets. SIAM J. Math. Anal. 39, 298-318.
23. Guo K, Labate D, Lim W Q, et al. Wavelets with composite dilations and their MRA properties. Applied & Computational Harmonic Analysis 2006; 20(2): 202-236.
24. Dou J, Li J. Optimal image-fusion method based on nonsubsampled contourlet transform. Optical Engineering 2012; 51(10): 2002-2009.
25. Gonzalez R C, Woods R E, Eddins S L. Digital Image Processing Using MATLAB. Pearson Education India, 2004: 334-377.
26. Gonzalez R C, Woods R E. Digital Image Process, Third Edition. Pearson Education India, 2010: 649-702.
27. Vivek C, Audithan S.. Colour Texture Image Analysis by Shearlets. J. Applied Sci. 2014; 14: 697-702.

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-871223f8-a783-43b1-a083-b9482684ebb1