Multimedia Tools and Applications

, Volume 78, Issue 6, pp 7321–7339 | Cite as

Robust low-rank decomposition of multi-channel feature matrices for fabric defect detection

  • Chunlei LiEmail author
  • Chaodie Liu
  • Guangshuai Gao
  • Zhoufeng Liu
  • Yuping Wang


Fabric defect detection plays an important role in the quality control of textile products. Most existing defect detection techniques adopted traditional pattern recognition methods, which were lacking adaptability and presented the undesirable detection accuracy. In this paper, a fabric defect detection algorithm based on multi-channel feature matrixes extraction and joint low-rank decomposition was proposed by simulating biological visual perception mechanism. Based on the fact that the second-order gradient information is more suitable for characterizing the fabric texture, we developed a novel second-order multi-channel feature extraction method by modeling the response and distribution properties of the P-type ganglion cells in the primate retina. Upon devising a powerful descriptor, a joint low-rank decomposition method is utilized to model biological visual saliency, and decomposes the fabric images into backgrounds and salient defect objects. Experimental results demonstrate that our proposed algorithm has good self-adaptability and detection performance for plain and twill fabrics or complex patterned fabrics, and is superior to the state-of-the-art methods.


Second-order gradient Multi-channel feature Joint low-rank decomposition Fabric images Defect detection 



This work was supported by the National Natural Science Foundation of China ((No.61772576, No.61379113), the Key Natural Science Foundation of Henan Province(No.162300410338), Science and technology innovation talent project of Education Department of Henan Province(17HASTIT019), The Henan Science Fund for Distinguished Young Scholars (184100510002).


  1. 1.
    Baykal IC, Muscedere R, Jullien GA (2002) On the use of hash functions for defect detection in textures for in-camera web inspection systems. In: IEEE International symposium on circuits and systems, vol 5. IEEE, pp V-665-V-668Google Scholar
  2. 2.
    Brzakovic D, Bakic P, Vujovic N, et al (1997) A generalized development environment for inspection of web material. In: IEEE International conference on robotics and automation, vol 1. IEEE Press, New York, pp 1–8Google Scholar
  3. 3.
    Cao J, Zhang J, Wen Z (2015) Fabric defect inspection using prior knowledge guided least squares regression. Multimed Tools Appl 76(3):1–17Google Scholar
  4. 4.
    Cohen FS, Fan Z, Attali S (1991) Automated inspection of textile fabrics using textual models. IEEE Trans Pattern Anal Mach Intell 13(8):803–808CrossRefGoogle Scholar
  5. 5.
    Guan S (2016) Fabric defect detection using an integrated model of bottom-up and top-down visual attention. J Textile Institute 107(2):215–224Google Scholar
  6. 6.
    Guan S, Gao Z, Wu N, et al (2014) Defect detection of plain weave based on visual saliency mechanism. J Textile Res 35(4):56–61Google Scholar
  7. 7.
    Hou X, Zhang L (2007) Saliency detection: a spectral residual approach. Comput Vis Pattern Recogn, 1–8Google Scholar
  8. 8.
    Huang D, Zhu C, Wang Y, et al (2014) HSOG: a novel local image descriptor based on histograms of the second-order gradients. IEEE Trans Image Process 23(11):4680–4695MathSciNetCrossRefGoogle Scholar
  9. 9.
    Imamoglu N, Lin W, Fang Y (2013) A saliency detection model using low-level features based on wavelet transform. IEEE Trans Multimed 15(1):96–105CrossRefGoogle Scholar
  10. 10.
    Kamermans M, Hark J, Habraken J, et al (1996) The size of the horizontal cell receptive fields adapts to the stimulus in the light adapted goldfish retina. Vis Res 36(24):4105–4119CrossRefGoogle Scholar
  11. 11.
    Lang C, Liu G, Yu J, Yan S (2012) Saliency detection by multitask sparsity pursuit. IEEE Trans Image Process 21(3):1327–1338MathSciNetCrossRefGoogle Scholar
  12. 12.
    Li C, Gao GS, Liu Z, et al (2017) Fabric defect detection algorithm based on histogram of oriented gradient and low-rank decomposition. J Textile Res 38(3):153–158Google Scholar
  13. 13.
    Li C, Yang R, Liu Z, et al (2016) Fabric defect detection via learned dictionary-based visual saliency. Int J Cloth Sci Technol 28(4):530–542CrossRefGoogle Scholar
  14. 14.
    Li C, Zhang Z, Liu Z, et al (2014) A novel fabric defect detection algorithm using textural difference-based visual saliency model. J Shandong Univ (Eng Sci) 44(4):1–9Google Scholar
  15. 15.
    Li M, Cui S, Xie Z (2015) Application of Gaussian mixture model on defect detection of print fabric. J Textile Res 36(8):94–98Google Scholar
  16. 16.
    Li Y, Li H, Gong HQ, et al (2011) Characteristics of receptive field encoded by synchronized firing pattern of ganglion cell group. Acta Biophysica Sinica 27(3):211–221MathSciNetCrossRefGoogle Scholar
  17. 17.
    Li X, Li Y, Shen C, et al (2013) Contextual hypergraph modeling for salient object detection. In: IEEE International conference on computer vision. IEEE, pp 3328–3335Google Scholar
  18. 18.
    Li Y, Zhao W, Pan J (2017) Deformable patterned fabric defect detection with fisher criterion-based deep learning. IEEE Trans Autom Sci Eng 14(2):1256–1264CrossRefGoogle Scholar
  19. 19.
    Lin Z, Liu R, Su Z (2011) Linearized alternating direction method with adaptive penalty for low-rank representation. Adv Neural Inf Process Syst, 612–620Google Scholar
  20. 20.
    Liu G, Lin Z, Yu Y (2010) Robust subspace segmentation by low-rank representation. In: International conference on machine learning, pp 663–670Google Scholar
  21. 21.
    Liu Z, Li C, Zhao Q, et al (2015) A fabric defect detection algorithm via context-based local texture saliency analysis. Int J Cloth Sci Technol 27(5):738–750CrossRefGoogle Scholar
  22. 22.
    Ng MK, Ngan HYT, Yuan X, et al (2014) Patterned fabric inspection and visualization by the method of image decomposition. IEEE Trans Autom Sci Eng 11 (3):943–947CrossRefGoogle Scholar
  23. 23.
    Ngan HYT, Pang GKH (2006) Novel method for patterned fabric inspection using Bollinger bands. Opt Eng 45(8):087202CrossRefGoogle Scholar
  24. 24.
    Ngan HYT, Pang GKH, Yung SP, et al (2005) Wavelet based methods on patterned fabric defect detection. Pattern Recogn 38(4):559–576CrossRefGoogle Scholar
  25. 25.
    Peng H, Li B, Ling H, et al (2016) Salient object detection via structured matrix decomposition. IEEE Trans Pattern Anal Mach Intell 39(4):818–832CrossRefGoogle Scholar
  26. 26.
    Qu T, Zou L, Zhang Q, et al (2016) Defect detection on the fabric with complex texture via dual-scale over-complete dictionary. J Textile Institute 107(6):743–756CrossRefGoogle Scholar
  27. 27.
    Rodieck R (1965) Quantitative analysis of cat retinal ganglion cell response to visual stimuli. Vision Res 5(12):583–601CrossRefGoogle Scholar
  28. 28.
    Selver M, Avşar V, Özdemir H (2014) Textural fabric defect detection using statistical texture transformations and gradient search. J Text Inst 105(9):998–1007CrossRefGoogle Scholar
  29. 29.
    Shapley R (1997) Retinal physiology: adapting to the changing scene. Curr Biol 7(7):R421–R423CrossRefGoogle Scholar
  30. 30.
    Shen X, Wu Y (2012) A unified approach to salient object detection via low rank matrix recovery. IEEE Conf Comput Vis Pattern Recogn 23(10):853–860Google Scholar
  31. 31.
    Tang C, Wang P, Zhang C, et al (2017) Salient object detection via weighted low rank matrix recovery. IEEE Signal Process Lett 24(4):490–494CrossRefGoogle Scholar
  32. 32.
    Toh K-C, Yun S (2010) An accelerated proximal gradient algorithm for nuclear norm regularized least squares problems. Pac J Optim 6(3):615–640MathSciNetzbMATHGoogle Scholar
  33. 33.
    Tong L, Wong WK, Kwong CK (2017) Fabric defect detection for apparel industry: a nonlocal sparse representation approach. IEEE Access 5(99):5947–5964Google Scholar
  34. 34.
    Weng D, Wang Y, Gong M, et al (2015) DERF: distinctive efficient robust features from the biological modeling of the p ganglion cells. IEEE Trans Image Process 24(8):2287–2302MathSciNetCrossRefGoogle Scholar
  35. 35.
    Workgroup on texture analysis of DFG TILDA textile texture database[DB/OL] [2013-05-06].
  36. 36.
    Xia D, Jiang G, Li Y, et al (2017) Warp-knitted fabric defect segmentation based on non-subsampled contour let transform. J Textile Institute 108(2):239–245Google Scholar
  37. 37.
    Yang X, Pang CG, Yung N (2005) Robust fabric defect detection and classification using multiple adaptive wavelets. IEE Proc-Vis Image Signal Process 152(6):715723Google Scholar
  38. 38.
    Yan J, Liu J, Li Y, et al (2010) Visual saliency detection via rank-sparsity decomposition. IEEE Int Conf Image Process 119(5):1089–1092Google Scholar
  39. 39.
    Ying S (2014) Fabric defects detection using adaptive wavelets. Int J Cloth Sci Technol 26(3):202–211CrossRefGoogle Scholar
  40. 40.
    Zengbo X, Yunan G, Xiubao H (2000) Fabric detects detection with wold-based texture model and fractal. Theory 26(1):6–9Google Scholar
  41. 41.
    Zhang D, Gao G, Li C (2016) Fabric defect detection algorithm based on Gabor filter and low-rank decomposition. In: Eighth International conference on digital image processing, pp 100330L1–100330L6Google Scholar
  42. 42.
    Zhou J, Wang J (2013) Fabric defect detection using adaptive dictionaries. Text Res J 83(17):1846–1859CrossRefGoogle Scholar
  43. 43.
    Zhou J, Semenovich D, Sowmya A, et al (2014) Dictionary learning framework for fabric defect detection. J Text Inst 105(3):223–234CrossRefGoogle Scholar
  44. 44.
    Zhu Q, Wu M, Li J, Deng D (2012) Fabric defect detection via small scale over-complete basis set. Textile Res J 84(15):1634–1649CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Electric and Information EngineeringZhongyuan University of TechnologyZhengzhouChina
  2. 2.Biomedical Engineering DepartmentTulane UniversityNew OrleansUSA

Personalised recommendations