Abstract
Visual inspection is a challenging and widely employed process in industries. In this work, an automated tire visual inspection system is proposed based on low rank matrix recovery. Deep Network is employed to perform texture segmentation which benefits low rank decomposition in both quality and computational efficiency. We propose a dual optimization method to improve convergence speed and matrix sparsity by incorporating the improvement of the soft-threshold shrinkage operator by the weight matrix M. We investigated how incremental multiplier affects the decomposition accuracy and the convergence speed of the algorithm. On this basis, image blocks were decomposed into low-rank matrix and sparse matrix in which defects were separated. Comparative experiments have been performed on our dataset. Experimental results validate the theoretical analysis. The method is promising in false alarm, robustness and running time based on multi-core processor distributed computing. It can be extended to other real-time industrial applications.
Similar content being viewed by others
References
Al Arif SMMR, Knapp K, Slabaugh G (2018) Fully automatic cervical vertebrae segmentation framework for X-ray images. Comput Meth Prog Bio 157:95–111
Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal 39(12):2481–2495
Bouwmans T, Zahzah EH (2014) Robust PCA via principal component pursuit: a review for a comparative evaluation in video surveillance. Comput Vis Image Und 122:22–34. https://doi.org/10.1016/j.cviu.2013.11.009
Candes EJ, Tao T (2010) The power of convex relaxation: near-optimal matrix completion. IEEE Trans Inform Theory 56(5):2053–2080
E. J. Candes, X. Li, Y. MA et al., “Robust principal component analysis?” J ACM, vol. 58, pp. 1–37, 2011.
Cao F, Cai M, Chu J et al (2016) A novel segmentation algorithm for nucleus in white blood cells based on low-rank representation. Neural Comput Appl 28(1):503–511
Cen Y, Zhao R, Cen L, Cui L et al (2015) Defect inspection for TFT-LCD images based on the low-rank matrix reconstruction. Neurocomputing 149:1206–1215
Chen L C, Zhu Y, Papandreou G, et al. (2018) “Encoder-decoder with atrous separable convolution for semantic image segmentation” ECCV, pp. 801–818
Chu W (2021) Studies on the effects of wiring density on chip package interaction and design optimization with machine learning[D]. The University of Texas at Austin
Eckstein J, Bertsekas D (1992) On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators. Math Program 55:293–318
Guo Q, Zhang C et al (2016) Defect detection in Tire X-ray images using weighted texture dissimilarity. J Sensors 2016:1–12
Jia Y, Liu L, Moon ZC (2021) Moon Impact Crater Detection Using Nested Attention Mechanism Based UNet++[J]. IEEE Access 9:44107–44116
Jin B, Cruz L, Goncalves N (2020) Deep facial diagnosis: deep transfer learning from face recognition to facial diagnosis. IEEE Access 8:123649–123661
Ju M et al (2019) IDGCP: image dehazing based on gamma correction prior. IEEE Trans Image Process 29:3104–3118
Ju M, Ding C, Ren W, Yang Y, Zhang D, Guo YJ (2021) Ide: image dehazing and exposure using an enhanced atmospheric scattering model. IEEE Trans Image Process 30:2180–2192
Li FY (2011) The study of an improved fuzzy edge detection algorithm in the radial tire quality detection. Adv Mater Res 317-319:968–971
Li P, Liang J, Shen X, Zhao M, Sui L (2019) Textile fabric defect detection based on low-rank representation. Multimed Tools Appl 78:99–124
Lin Z, Chen M, et al. (2013) “The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices,” arXiv:1009.5055
Lin, Z, Ganesh, A, Wright, J, Wu, L, Chen, M, Ma, Y (n.d.) “Fast convex optimization algorithms for exact recovery of a corrupted low-rank matrix,” SIAM J Optim
Liu G, Lin Z, Yan S, Sun J, Yu Y, Ma Y (2013) Robust recovery of subspace structures by low-rank representation. IEEE Trans Pattern Anal 35:171–184
Mo D, Wong W, Lai Z, Zhou J (2020) Weighted double-low-rank decomposition with application to fabric defect detection. IEEE Trans Autom Sci Eng:1–21
Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE T Pattern Anal 39(6):1137–1149
Ren R, Hung T, Tan KC (2018) A generic deep-learning-based approach for automated surface inspection. IEEE Trans Cybern 48(3):929–940
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. LNCS 9351:234–241
Sun J, Li C, Wu XJ, Palade V, Fang W (2019) An effective method of weld defect detection and classification based on machine vision. IEEE Trans Ind Inform 15:6322–6333
Tang G, Nehorai A (2011) “Robust principal component analysis based on low-rank and block-sparse matrix decomposition,” CISS
Tao M, Yuan X (2011) Recovering low-rank and sparse components of matrices from incomplete and noisy observations. SIAM J Optim 21(1):57–81
Wang Q, Gao J, Yuan Y (2017) Embedding structured contour and location prior in siamesed fully convolutional networks for road detection. IEEE Trans Intell Transp Syst 19(1):230–241
Wang Q, Han T, Qin Z, et al. (2020) “Multitask attention network for lane detection and fitting,”. IEEE Trans Neural Netw Learn Syst
Wright J, Peng Y, Ma Y, Ganesh A, Rao S (2009) “Robust principal component analysis: exact recovery of corrupted low-rank matrices by convex optimization,” Neural Inf Process Syst, NIPS
Xiang Y, Zhang C, Guo Q (2014) “A Dictionary-based Method for Tire Defect Detection,” in Proc IEEE Int Conf Infor Automat, pp. 519–523
Yang B, Zhou L (2015) Robust foreground detection using block-based RPCA. Optik 126:4586–4590
Yin X, Chen Y, Bouferguene A, Zaman H, al-Hussein M, Kurach L (2020) A deep learning-based framework for an automated defect detection system for sewer pipes[J]. Autom Constr 109:102967
Zhang Y, Li T, Li Q (2013) Defect detection for tire laser shearography image using curvelet transform based edge detector. Opt Laser Technol 7:64–71
Zhang Y, Li T, Li QL (2013) Detection of foreign bodies and bubble defects in Tire radiography images based on Total variation and edge detection. Chin Phys Lett 8:256–307
Zhang Y, Lefebvre D, Li Q (2017) Automatic detection of defects in Tire radiographic images. IEEE Trans Autom Sci Eng 14(3):1378–1386
Zhang Y, Cui XH, Liu Y, Bin Y (2018) Tire Defects Classification Using Convolution Architecture for Fast Feature Embedding. Int J Comput Int Sys 11:1056–1066
Zhang J, Wang H, Tian Y et al (2020) An accurate fuzzy measure-based detection method for various types of defects on strip steel surfaces. Comput Ind 122:103231
Zhang X et al (2020) Pyramid channel-based feature attention network for image dehazing. Comput Vis Image Underst 197:103003
Zhang X, Jiang R, Wang T, Luo W (2021) Single image Dehazing via dual-path recurrent network. IEEE Trans Image Process 30:5211–5222
Zhao G, Qin S (2018) High-Precision Detection of Defects of Tire Texture Through X-ray Imaging Based on Local Inverse Difference Moment Features. Sensors 18(8):2524
Zhao M, Liu Q, Jha A, et al. (2021) "VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning,". arXiv preprint arXiv:2106.11480
Zhao M, Jha A, Liu Q, Millis BA, Mahadevan-Jansen A, Lu L, Landman BA, Tyska MJ, Huo Y (2021) Faster mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and tracking. Med Image Anal 71:102048
Zheng Z, Zhang S, Yu B, Li Q, Zhang Y (2020) Defect inspection in Tire radiographic image using concise semantic segmentation. IEEE Access 8:112674–112687
Zheng Z, Shen J, Shao Y, Zhang J, Tian C, Yu B, Zhang Y (2021) Tire defect classification using a deep convolutional sparse-coding network[J]. Meas Sci Technol 32(5):055401
Zheng Z, Zhang S, Shen J, Shao Y, Zhang Y (2021) A two-stage CNN for automated Tire defect inspection in radiographic image. Meas Sci Technol 32:115403
Zhou Z, Li X, Wright J, Candes E, Ma Y (2010) “Stable principal component pursuit,” IEEE ISIT Proceed, pp. 1518–1522
Zhu J, Min Q, Wu J, Tian GY (2018) Probability of detection or Eddy current pulsed thermography of angular defect quantification. IEEE Trans Ind Inform 14(12):5658–5666
Acknowledgements
This work was supported by the Natural Science Foundation of Shandong Province No. ZR2019MEE066 and partly by No. ZR2018MC007.
Author information
Authors and Affiliations
Corresponding author
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.
About this article
Cite this article
Li, G., Zheng, Z., Shao, Y. et al. Automated Tire visual inspection based on low rank matrix recovery. Multimed Tools Appl 82, 24227–24246 (2023). https://doi.org/10.1007/s11042-023-14467-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-14467-1