Color-patterned fabrics possess changeable patterns, low probability of defective samples, and various forms of defects. Therefore, the unsupervised inspection of color-patterned fabrics has gradually become a research hotspot in the field of fabric defect detection. However, due to the redundant information of skip connections in the network and the limitation of post-processing, the current reconstruction-based unsupervised fabric defect detection methods have difficulty in detecting some defects of color-patterned fabrics. In this article, we propose an Attention-Gate-based U-shaped Reconstruction Network (AGUR-Net) and a dual-threshold segmentation post-processing method. AGUR-Net consists of an encoder, an Atrous Spatial Pyramid Pooling module and an attention gate weighted fusion residual decoder. The encoder is used to obtain more representative features of the input image via EfficientNet-B2. The Atrous Spatial Pyramid Pooling module is used to enlarge the receptive field of the network and introduce multi-scale information into the decoder. The attention-gate-weighted residual fusion decoder is used to fuse the features of the encoder with the features of the decoder to obtain the reconstructed image. The dual-threshold segmentation post-processing is used to obtain the final defect detection results. Our method achieves a precision of 59.38%, a recall of 59.1%, an F1 of 54.31%, and an intersection-over-union ratio of 41.18% on the public dataset YDFID-1. The experimental results show that the proposed method can better detect and locate the defects of color-patterned fabrics compared with several other state-of-the-art unsupervised fabric defect detection methods.
LiuKZhengMLiuY, et al.
Deep autoencoder thermography for defect detection of carbon fiber composites. IEEE Trans Industr Inform2022.
2.
Gao S, Dai Y, Li Y, et al. Multiview Wasserstein generative adversarial network for imbalanced pearl classification. Meas Sci Technol 2022; 33(8): 085406.
3.
Liu K, Yu Q, Liu Y, et al. Convolutional graph thermography for subsurface defect detection in polymer composites. IEEE Trans Instrum Meas 2022; 71: 1–11.
4.
JingJZhangHWangJ, et al.
Fabric defect detection using Gabor filters and defect classification based on LBP and Tamura method. J Text I2013;
104: 18–27.
5.
LiuGLiF.Fabric defect detection based on low-rank decomposition with structural constraints. Vis Comput2021;
38: 639–653.
6.
WeiBHaoKTangX-s, et al.
Fabric defect detection based on faster RCNN. Artificial Intelligence on Fashion and Textiles2019: 45–51.
7.
Kou X, Liu S, Cheng K, et al. Development of a YOLOV3-based model for detecting defects on steel strip surface. Measurement 2021; 182: 109454.
8.
Liu Z, Cui J, Li C, et al. Fabric defect detection based on lightweight neural network. Chinese Conference on Pattern Recognition and Computer Vision 2019; 1: 528–539.
9.
LiuJWangCSuH, et al.
Multistage GAN for fabric defect detection. IEEE Trans Image Process2019;
29: 3388–3400.
10.
JingJWangZRätschM, et al.
Mobile-Unet: An efficient convolutional neural network for fabric defect detection. Text Res J2022;
92: 30–42.
11.
BergmannPFauserMSattleggerD, et al. Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In: 2020 IEEE/CVF conference on computer vision and pattern recognition, Seattle, USA, 14–19 June 2020, pp. 4183–4191. Piscataway, NJ: IEEE.
12.
ShiYYangJQiZ.Unsupervised anomaly segmentation via deep feature reconstruction. Neurocomputing2021;
424: 9–22.
13.
CaoYWanQShenW, et al.
Informative knowledge distillation for image anomaly segmentation. Knowledge-Based Systems2022;
248: 108846.
14.
ZhangHZhangWXiongW, et al.
Defect detection of yarn-dyed fabric based on memory denoising convolutional auto-encoder. Basic Sciences Journal of Textile Universities2022;
35: 64–71.
15.
BergmannPLöweSFauserM, et al.
Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv2018: 180702011.
16.
GongDLiuLLeV, et al. Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea (South), 27 October–2 November, 2019, pp. 1705–1714. Piscataway, NJ: IEEE.
17.
WeiWDengDZengL, et al.
Real-time implementation of fabric defect detection based on variational automatic encoder with structure similarity. J Real Time Image Process2020;
18: 807–823.
18.
AkcaySAtapour-AbarghoueiABreckonTP. Ganomaly: Semi-supervised anomaly detection via adversarial training. In: Asian conference on computer vision, Perth, Australia, 02–06 December, 2018, pp. 622–637. Berlin: Springer.
19.
HuGHuangJWangQ, et al.
Unsupervised fabric defect detection based on a deep convolutional generative adversarial network. Text Res J2020;
90: 247–270.
20.
XiaXPanXLiN, et al.
GAN-based anomaly detection: A review. Neurocomputing 2022; 493: 497–535.
21.
ZhangHQiaoGLuS, et al.
Attention-based feature fusion generative adversarial network for yarn-dyed fabric defect detection. Text Res J2022.
22.
PangGShenCCaoL, et al.
Deep learning for anomaly detection: A review. ACM Comput Surv2021;
54: 1–38.
23.
ZhangHTanQLuS, et al.
Yarn-dyed shirt piece defect detection based on an unsupervised reconstruction model of the U-shaped denoising convolutional auto-encoder. Journal of Xidian University2021;
48: 123–130.
24.
ChanC-HPangGKH.Fabric defect detection by Fourier analysis. IEEE Trans Ind Appl2000;
36: 1267–1276.
25.
WuYZhouJAkankwasaNT, et al.
Fabric texture representation using the stable learned discrete cosine transform dictionary. Text Res J2017;
89: 294–310.
26.
LiMWanSDengZ, et al.
Fabric defect detection based on saliency histogram features. Comput Intell2019;
35: 517–534.
27.
JeyarajPRNadarERS.Effective textile quality processing and an accurate inspection system using the advanced deep learning technique. Text Res J2020;
90: 971–980.
28.
MeiSYangHYinZ.An unsupervised-learning-based approach for automated defect inspection on textured surfaces. IEEE Trans Instrum Meas2018;
67: 1266–1277.
29.
ZhangHTangWZhangL, et al.
Defect detection of yarn-dyed shirts based on denoising convolutional self-encoder. Data Driven Control and Learning Systems (DDCLS). 2019: 1263–1268.
30.
SimonyanKZissermanA.Very deep convolutional networks for large-scale image recognition. arXiv2014: 14091556.
31.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, USA, 26 June–1 July, 2016, pp. 770–778. Piscataway, NJ: IEEE.
32.
SandlerMHowardAZhuM, et al. Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, USA. Piscataway, 18–22 June, 2018, pp. 4510–4520. NJ: IEEE.
33.
TanMLeQ. Efficientnet: Rethinking model scaling for convolutional neural networks. In: International conference on machine learning, Long Beach, USA, 10 Jun–15 Jun, 2019, pp. 6105–6614. New York, NY: ACM.
34.
DosovitskiyABeyerLKolesnikovA, et al.
An image is worth 16x16 words: Transformers for image recognition at scale. arXiv2020: 201011929.
35.
LiuZLinYCaoY, et al. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, Canada, 10–17 October, 2021, pp. 10012–10022. Piscataway, NJ: IEEE.
36.
WangWXieELiX, et al. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, Canada, 10–17 October, 2021, pp. 568–578. Piscataway, NJ: IEEE.
37.
DaiZLiuHLeQV, et al.
Coatnet: Marrying convolution and attention for all data sizes. Adv Neural Inf Process Syst2021;
34: 3965–3977.
38.
SrinivasALinT-YParmarN, et al. Bottleneck transformers for visual recognition. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Online, 19–25 June, 2021, pp. 16159–16529. Piscataway, NJ: IEEE.
ChenL-CZhuYPapandreouG, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European conference on computer vision, Munich, Germany, 8–14 September, 2018, pp. 801–818. Berlin: Springer.
41.
HeKZhangXRenS, et al. Identity mappings in deep residual networks. In: European conference on computer vision, Amsterdam, Netherlands, 10–16 October, 2016, pp. 630–645. Berlin: Springer.
42.
OktayOSchlemperJFolgocLL, et al.
Attention U-Net: Learning where to look for the pancreas, Amsterdam, Netherlands, 4–6 July, 2018.
43.
BahdanauDChoKBengioY.Neural machine translation by jointly learning to align and translate. arXiv2014: 14090473.
44.
SmithLNTopinN.Super-convergence: Very fast training of neural networks using large learning rates. Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications. 2019: 1100612, pp. 369–386.
45.
LaiWSHuangJBAhujaN, et al.
Fast and accurate image super-resolution with deep Laplacian pyramid networks. IEEE Trans Pattern Anal Mach Intell2019;
41: 2599–2613.
46.
WangZBovikACSheikhHR, et al.
Image quality assessment: From error visibility to structural similarity. IEEE Trans Image Process2004;
13: 600–612.
47.
ZavrtanikVKristanMSkočajD. Reconstruction by inpainting for visual anomaly detection. Pattern Recogn2021;
112: 107706.
BergmannPFauserMSattleggerD, et al. MVTec AD – a comprehensive real-world dataset for unsupervised anomaly detection. In: IEEE/CVF conference on computer vision and pattern recognition, Long Beach, USA, 16–20 June, 2019, pp. 9584–9592. Piscataway, NJ: IEEE.
50.
SchleglTSeeböckPWaldsteinSM, et al. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: International conference on information processing in medical imaging, Boone, NC, USA. June 25–30, 2017, pp.146–157. Berlin: Springer.
