Skip to main content
SpringerLink
Log in

Fabric defect detection via feature fusion and total variation regularized low-rank decomposition

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Fabric defect detection plays a key role in quality control for textile products. Existing methods based on traditional image processing techniques suffer from low detection accuracy and poor adaptability. The low-rank decomposition model is able to decompose the images into sparse parts (defects) and low-rank parts (background), thus can be applied to fabric defect detection. However, such model is likely to maintain more sparse noises in the sparse parts, resulting in high false-positive rate. Meanwhile, it is difficult to comprehensively represent the complicated texture feature of fabric images using traditional single hand-crafted feature descriptors. To remedy the above two challenges, a novel fabric defect detection algorithm based on feature fusion and total variation regularized low-rank decomposition is proposed in this paper. Specifically, the first-order and second-order gradient features are extracted with a biologically inspired model, and then fused using Canonical Correlation Analysis (CCA) to more sufficiently characterize the fabric texture. Next, total variation regularization term is incorporated in low-rank decomposition model to separate fabric images into redundant background and sparse parts with less noise. Finally, the defects are inspected by segmenting the saliency map obtained from sparse matrix using threshold segmentation. The experiment results conducted on two datasets demonstrate that the proposed method has better performance and generalization comparing to the competing methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Algorithm 1
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Allili M, Baaziz N, Mejri M (2014) Texture modeling using contourlets and finite mixtures of generalized gaussian distributions and applications[J]. IEEE Trans Multimed 16(3):772–784

    Google Scholar 

  2. Beck A, Teboulle M (2009) A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J Imag Sci 2(1):183–202

    MathSciNet  Google Scholar 

  3. Behravan M, Tajeripour F, Azimifar Z, Boostani R (2011) Texton-based fabric defect detection and recognition[J]. Iran J Electr Comput Eng 10 (2):57–69

    Google Scholar 

  4. Bissi L, Baruffa G, Placidi P, et al. (2013) Automated defect detection in uniform and structured fabrics using Gabor filters and PCA[J]. J Vis Commun Image Represent 24(7):838–845

    Google Scholar 

  5. Cai JF, Cand SEJ, et al. (2010) A singular value thresholding algorithm for matrix completion[J]. Siam J Optim 20(4):1956–1982

    MathSciNet  Google Scholar 

  6. Cao J, Zhang J, Wen Z, et al. (2017) Fabric defect inspection using prior knowledge guided least squares regression[J]. Multimed Tools Appl 76 (3):4141–4157

    Google Scholar 

  7. Chang X, Gu C, Liang J, et al. (2018) Fabric defect detection based on pattern template correction[J]. Math Probl Eng 2018

  8. Chang Y, Yan L, Chen B, et al. (2020) Hyperspectral image restoration: where does the low-rank property exist[J]. IEEE Trans Geosci Remote Sens 59 (8):6869–6884

    Google Scholar 

  9. Choksi R, Van Gennip Y, Oberman A (2017) Anisotropic total variation regularized l1-approximation and denoising/deblurring of 2D bar codes[J]. Inverse Probl Imaging 5 (3):591–617

    Google Scholar 

  10. Ebadi SE, Izquierdo E (2017) Foreground segmentation with tree-structured sparse RPCA[J]. IEEE Trans Pattern Anal Mach Intell 40(9):2273–2280

    Google Scholar 

  11. Fan H, Chen Y, Guo Y, et al. (2017) Hyperspectral image restoration using low-rank tensor recovery[J]. IEEE J Sel Top Appl Earth Obs Remote Sens 10(10):4589–4604

    Google Scholar 

  12. Goldstein T, Osher S (2009) The split Bregman method for L1-regularized problems. SIAM J Imag Sci 2(2):323–343

    MathSciNet  Google Scholar 

  13. Golub GH (1987) A generalization of the Eckart-Young-Mirsky matrix approximation theorem[J]. Linear Algebra Appl 88(3):317–327

    MathSciNet  Google Scholar 

  14. Hamdi AA, Sayed MS, Fouad MM, et al. (2018) Unsupervised patterned fabric defect detection using texture filtering and K-means clustering[C]. Int Conf Innov Trends in Comput Eng:130–144

  15. Huang D, Zhu C, Wang Y, et al. (2014) HSOG: a novel local image descriptor based on histograms of the second-order gradients[J]. IEEE Trans Image Process Publ IEEE Signal Process Soc 23(11):4680

    MathSciNet  Google Scholar 

  16. Ju J, Xing J (2019) Moving object detection based on smoothing three frame difference method fused with RPCA[J]. Multimed Tools Appl 78 (21):29937–29951

    Google Scholar 

  17. Li C, Zhang Z, Wang Y, et al. (2015) Dither modulation of significant amplitude difference for wavelet based robust watermarking[J]. Neurocomputing 166:404–415

    Google Scholar 

  18. Li M, Cui S, Xie Z (2015) Application of Gaussian mixture model on defect detection of print fabric. J Tex Res 36(8):94–98

    Google Scholar 

  19. Li C, Gao G, Liu Z, et al. (2017) Fabric defect detection algorithm based on histogram of oriented gradient and low-rank decomposition. J Tex Res 38(3):153–158

    Google Scholar 

  20. Li C, Gao G, Liu Z, et al. (2018) Fabric defect detection based on biological vision modeling[J]. IEEE Access 99:1–1

    Google Scholar 

  21. Li C, Liu C, Gao G, et al. (2018) Robust low-rank decomposition of multi-channel feature matrices for fabric defect detection[J]. Multimed Tools Appl 1–19

  22. Li C, Gao G, Liu Z, et al. (2019) Defect detection for patterned fabric images based on GHOG and low-rank decomposition[J]. IEEE Access 7:83962–83973

    Google Scholar 

  23. Li P, Liang J, Shen X, et al. (2019) Textile fabric defect detection based on low-rank representation. Multimed Tools Appl 78:99–124

    Google Scholar 

  24. Li C, Li J, Li Y, et al. (2021) Fabric defect detection in textile manufacturing: a survey of the state of the art[J]. Secur Commun Netw 2021

  25. Lu S, Ren X, Liu F (2014) Depth enhancement via low-rank matrix completion[C]. In: 2014 IEEE conference on computer vision and pattern recognition (CVPR). IEEE Computer Society, 3390–3397

  26. Micchelli CA, Shen L, Xu Y (2011) Proximity algorithms for image models: denoising[J]. Inverse Prob 27(4):045009

    MathSciNet  Google Scholar 

  27. Mo D, Wong WK, Lai Z, et al. (2020) Weighted double-low-rank decomposition with application to fabric defect detection[J]. IEEE Trans Autom Sci Eng 18(3):1170–1190

    Google Scholar 

  28. Ng MK, Ngan HYT, Yuan X, et al. (2014) Patterned fabric inspection and visualization by the method of image decomposition[J]. IEEE Trans Autom Sci Eng 11(3):943–947

    Google Scholar 

  29. Ngan HYT, Pang GKH, Yung NHC (2007) Patterned fabric defect detection using a motif-based approach[C]. IEEE Int Conf Image Process. IEEE:II-33-II-36

  30. Ngan HYT, Pang GKH, Yung NHC (2010) Ellipsoidal decision regions for motif-based patterned fabric defect detection[J]. Pattern Recogn 43 (6):2132–2144

    Google Scholar 

  31. Ngan HYT, Pang GKH, Yung NHC (2011) Automated fabric defect detection a review[J]. Image Vision Comput 29(7):442–458

    Google Scholar 

  32. Park Y, Kweon IS (2016) Ambiguous surface defect image classification of AMOLED displays in smartphones[J]. IEEE Trans Ind Inform 1–1

  33. Peng H, Li B, Ling H, et al. (2017) Salient object detection via structured matrix decomposition. IEEE Trans Pattern Anal Mach Intell 39(4):818 C 832

    Google Scholar 

  34. Qu T, Zou L, Zhang Q, et al. (2015) Defect detection on the fabric with complex texture via dual-scale over-complete dictionary[J]. J Text Inst Proc Abstr 107(6):743–756

    Google Scholar 

  35. Rudin LI, Osher S, Fatemi E (1992) Nonlinear total variation based noise removal algorithms[C]. In: 11th International conference of the center for nonlinear studies on experimental mathematics : computational issues in nonlinear science: computational issues in nonlinear science. Elsevier, pp 259–268

  36. Selver MA, Avsar V, Özdemir H (2014) Textural fabric defect detection using statistical texture transformations and gradient search[J]. J Text Inst 105 (9):998–1007

    Google Scholar 

  37. Shi M, Fu R, Guo Y, et al. (2011) Fabric defect detection using local contrast deviations[J]. Multimed Tools Appl 52(1):147–157

    Google Scholar 

  38. Sun QS, Zeng SG, Heng PA, et al. (2005) Feature fusion method based on canonical correlation analysis and handwritten character recognition[C]. In: Control, automation, robotics and vision conference, 2004. Icarcv 2004, vol 2. IEEE, pp 1547–1552

  39. Sun QS, Zeng SG, Liu Y, et al. (2005) A new method of feature fusion and its application in image recognition[J]. Pattern Recogn 38(12):2437–2448

    Google Scholar 

  40. Susan S, Sharma M (2017) Automatic texture defect detection using Gaussian mixture entropy modeling. Neurocomputing 239:232–237

    Google Scholar 

  41. Tolba AS (2011) Fast defect detection in homogeneous flat surface products[J]. Expert Syst Appl 38(10):12339–12347

    Google Scholar 

  42. Tong L, Wong WK, Kwong CK (2017) Fabric defect detection for apparel industry: a nonlocal sparse representation approach[J]. IEEE Access 5 (99):5947–5964

    Google Scholar 

  43. Tsang CSC, Ngan HYT, Pang GKH (2016) Fabric inspection based on the Elo rating method[J]. Pattern Recogn 51(4):378–394

    Google Scholar 

  44. Wang J, Li Q, Gan J, et al. (2019) Surface defect detection via entity sparsity pursuit with intrinsic priors[J]. IEEE Trans Ind Inf 16(1):141–150

    Google Scholar 

  45. Wang S, Xia K, Wang L, et al. (2020) Improved RPCA method via non-convex regularisation for image denoising[J]. IET Signal Process 14(5):269–277

    Google Scholar 

  46. Wang J, Xu G, Li C, et al. (2021) Surface defects detection using non-convex total variation regularized RPCA with kernelization[J]. IEEE Trans Instrum Meas 70:1–13

    Google Scholar 

  47. Weng D, Wang Y, Gong M, et al. (2015) DERF: distinctive efficient robust features from the biological modeling of the p ganglion cells[J]. IEEE Trans Image Process 24(8):2287–2302

    MathSciNet  Google Scholar 

  48. Workgroup on Texture Analysis of DFG, TILDA Textile Texture Database, [online] Available: http://lmb.informatik.uni-freiburg.de/research/dfg-texture/tilde. Accessed 19 Feb 2023

  49. Wu Y (2012) A unified approach to salient object detection via low rank matrix recovery[C]. In: IEEE conference on computer vision and pattern recognition. IEEE Computer Society, pp 853–860

  50. Xia D, Jiang G, Li Y, et al. (2016) Warp-knitted fabric defect segmentation based on non-subsampled Contourlet transform[J]. J Text Inst Proc Abstr 108(2):239–245

    Google Scholar 

  51. Yapi D, Allili M (2017) Automatic fabric defect detection using learning-based local textural distributions in the contourlet domain. IEEE Trans Autom Sci Eng 99:1–13

    Google Scholar 

  52. Zhou J, Semenovich D, Sowmya A, et al. (2013) Sparse dictionary reconstruction for textile defect detection[C]. Int Conf Mach Learn Appl IEEE 21–26

  53. Zhou J, Wang J (2013) Fabric defect detection using adaptive dictionaries[J]. Text Res J 83(17): 1846–1859

    Google Scholar 

  54. Zhoufeng L, Lei Y, Chunlei L, et al. (2017) Fabric defect detection based on feature fusion and low-rank decomposition[J]. Cotton Text Technol 45 (10):1–4

    Google Scholar 

  55. Zhu L, Fu CW, Brown MS, et al. (2017) A non-local low-rank framework for ultrasound speckle reduction[C]. Proc IEEE Conf Comput Vision Pattern Recognit 5650–5658

  56. Zhu L, Fu CW, Jin Y, et al. (2016) Non-Local sparse and low-rank regularization for structure-preserving image smoothing[C]. Comput Graph Forum 35(7):217–226

    Google Scholar 

Download references

Acknowledgements

This work was supported by NSFC (No. U1804157, 62072489, 61772576), Henan science and technology innovation team (CXTD2017091), IRTSTHN (21IRTSTHN013), ZhongYuan Science and Technology Innovation Leading Talent Program(214200510013), Program for Interdisciplinary direction in Zhongyuan University of Technology, and Postgraduate Research & Practice Innovation Program of Jiangsu Province under Grant KYCX21_0202.

Author information

Authors and Affiliations

  1. College of Distance Learning, ZhengZhou University, ZhengZhou, 450007, China

    Hongling Zhao

  2. College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China

    Junpu Wang

  3. School of Electronic and Information Engineering, Zhongyuan University of Technology, ZhengZhou, 450007, China

    Chunlei Li & Ruimin Yang

  4. Department of Computer Science, University of York, York, YO105DD, UK

    Pengcheng Liu

Authors
  1. Hongling Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Junpu Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chunlei Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Pengcheng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ruimin Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Chunlei Li or Pengcheng Liu.

Ethics declarations

Conflict of Interests

The authors declare that they have no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhao, H., Wang, J., Li, C. et al. Fabric defect detection via feature fusion and total variation regularized low-rank decomposition. Multimed Tools Appl 83, 609–633 (2024). https://doi.org/10.1007/s11042-023-14754-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-14754-x

Keywords

Search

Navigation