基于纹理知识引导的跨域织物缺陷检测

doi:10.19678/j.issn.1000-3428.0069995

摘要/Abstract

摘要：

织物缺陷目标检测在纺织生产过程中是不可或缺的关键步骤。然而, 在实际情况下获取大量标注数据是十分困难的。无监督域自适应方法为该问题提供了有效的解决方案, 能够在没有目标域数据标注的情况下提升模型性能。然而, 现有的方法虽然在经典数据集上表现出色, 但在应用于更复杂、纹理更丰富的织物缺陷检测任务中时, 模型性能会明显下降。为了解决该问题, 提出一种基于纹理知识引导(TKG)的跨域织物缺陷检测方法, 旨在增强目标检测迁移模型在织物图像上的检测性能。TKG方法包含纹理增强模块、联合注意力模块和一致-对抗模块3个关键部分。纹理增强模块通过傅里叶变换来增强输入图像中的纹理信息, 使得模型能够更好地捕捉到复杂的纹理特征; 联合注意力模块引入一种注意力机制, 能够捕获更为全面的纹理和结构信息, 通过自适应地调整不同区域和通道的权重, 增强模型对关键纹理和缺陷区域的关注; 一致-对抗模块通过一致性训练和对抗性训练增强模型对目标域数据的适应性, 提升模型在目标域的检测性能。实验结果表明, 相较于对比方法, TKG方法在织物缺陷目标检测任务中表现出显著的优越性, 在斜纹到平纹的跨域检测实验中, TKG方法在mAP@0.5指标上实现了最高3.1百分点的性能提升, 体现了该方法在实际织物生产环境数据中优秀的跨域缺陷检测能力。

关键词: 目标检测, 域自适应, 织物缺陷, 纹理增强, 频域信息

Abstract:

Detection of fabric defects is an indispensable step in textile production. However, obtaining large amounts of annotated data in practical situations is difficult. The unsupervised domain adaptation method provides an effective solution to this problem, which can improve the model performance without target domain data annotation. However, although existing methods perform well on classical datasets, their model performance decreases significantly when applied to more complex and textured fabric defect detection tasks. To address this issue, a Texture Knowledge Guided (TKG) cross-domain fabric defect detection method is proposed to enhance the detection performance of the object detection transfer model on fabric images. The TKG method comprises three key components: texture enhancement, joint attention, and consistency-adversarial modules. The texture enhancement module enhances the texture information in the input image via Fourier transform, enabling the model to better capture complex texture features. The joint attention module introduces an attention mechanism that can capture more comprehensive texture and structural information. By adaptively adjusting the weights of different regions and channels, it enhances the attention of the model to key textures and defect areas. The consistency-adversarial module enhances the adaptability of the model to target domain data via consensus training and adversarial training, improving the detection performance of the model in the target domain. The experimental results show that compared with the comparative methods, the TKG method exhibits significant superiority in fabric defect target detection tasks. In the cross-domain detection experiment from twill to plain weave, the TKG method achieves a performance improvement of up to 3.1 percentage points in mAP@0.5, reflecting the excellent cross-domain defect detection capability of this method using actual fabric production environment data.

Key words: object detection, domain adaptation, fabric defect, texture enhancement, frequency domain information

李叔罡, 李爽, 刘驰. 基于纹理知识引导的跨域织物缺陷检测[J]. 计算机工程, 2026, 52(1): 166-175.

LI Shugang, LI Shuang, LIU Chi. Cross-Domain Fabric Defect Detection Guided by Texture Knowledge[J]. Computer Engineering, 2026, 52(1): 166-175.

https://www.ecice06.com/CN/Y2026/V52/I1/166

图/表 12

图1 TKG方法整体框架

Fig.1 The overall framework of TKG

图2 不同数据集图像间高频信息差异的可视化结果

Fig.2 Visualized results of differences in high-frequency information between images from different datasets

图3 每类织物缺陷的示例

Fig.3 Examples of defects for each type of fabric

图4 TKG方法检测结果可视化

Fig.4 Visualization of the detection results using TKG

图5 模型超参数分析

Fig.5 Analysis of model hyperparameters

图6 检测结果Top-K误差分析

Fig.6 Analysis of Top-K errors in detection results

参考文献 39

1	SHI L, SONG J Q, GAO Y F, et al. YOLO-GFD: a fast and accurate fabric defect detection model[C]//Proceedings of the 4th International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE). Washington D.C., USA: IEEE Press, 2023: 229-233.
2	DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). Washington D.C., USA: IEEE Press, 2005: 886-893.
3	LI S , LI S G , XIE M X , et al. End-to-end transferable anomaly detection via multi-spectral cross-domain representation alignment. IEEE Transactions on Knowledge and Data Engineering, 2023, 35 (12): 12194- 12207. doi: 10.1109/TKDE.2021.3118111
4	TORRALBA A, EFROS A A. Unbiased look at dataset bias[C]//Proceedings of the CVPR 2011. Washington D.C., USA: IEEE Press, 2011: 1521-1528.
5	PAN S J , YANG Q . A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 2010, 22 (10): 1345- 1359. doi: 10.1109/TKDE.2009.191
6	CHEN Y H, LI W, SAKARIDIS C, et al. Domain adaptive Faster R-CNN for object detection in the wild[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2018: 3339-3348.
7	HE M Z, WANG Y L, WU J X, et al. Cross domain object detection by target-perceived dual branch distillation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2022: 9560-9570.
8	INOUE N, FURUTA R, YAMASAKI T, et al. Cross-domain weakly-supervised object detection through progressive domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2018: 5001-5009.
9	JIANG J, CHEN B, WANG J, et al. Decoupled adaptation for cross-domain object detection[C]//Proceedings of the International Conference on Learning Representations. Washington D.C., USA: IEEE Press, 2022: 15-22.
10	RASHEED A , ZAFAR B , RASHEED A , et al. Fabric defect detection using computer vision techniques: a comprehensive review. Mathematical Problems in Engineering, 2020, 2020, 8189403.
11	JIANG L M, DAI B, WU W, et al. Focal frequency loss for image reconstruction and synthesis[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2021: 13899-13909.
12	XU Z J , ZHOU H X . Deep frequency principle towards understanding why deeper learning is faster. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35 (12): 10541- 10550. doi: 10.1609/aaai.v35i12.17261
13	CAI Z W, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2018: 6154-6162.
14	HE K M, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2017: 2980-2988.
15	LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2017: 936-944.
16	REN S Q , HE K M , GIRSHICK R , et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
17	方康, 黄琴, 王克琪, 等. 基于改进YOLOX的多光谱行人检测算法. 小型微型计算机系统, 2024, 45 (1): 185- 191.
	FANG K , HUANG Q , WANG K Q , et al. Multispectral pedestrian detection based on improved YOLOX. Journal of Chinese Computer Systems, 2024, 45 (1): 185- 191.
18	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2017: 2999-3007.
19	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[EB/OL]. [2024-03-05]. https://www.cs.unc.edu/~wliu/papers/ssd.pdf.
20	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2024-03-05]. https://www.semanticscholar.org/paper/YOLOv3%3A-An-Incremental-Improvement-Redmon-Farhadi/ebc96892b9bcbf007be9a1d7844e4b09fde9d961.
21	ZHU X, SU W, LU L, et al. Deformable DETR: deformable transformers for end-to-end object detection[EB/OL]. [2024-03-05]. https://www.weijiesu.com/research/Deformable-DETR/deformable_detr_iclr_presentation.pdf.
22	CHEN S F, SUN P Z, SONG Y B, et al. DiffusionDet: diffusion model for object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2023: 19773-19786.
23	GONG K X, LI S, LI S G, et al. Improving transferability for domain adaptive detection transformers[C]//Proceedings of the 30th ACM International Conference on Multimedia. New York, USA: ACM Press, 2022: 1543-1551.
24	SAITO K, USHIKU Y, HARADA T, et al. Strong-weak distribution alignment for adaptive object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2019: 6949-6958.
25	VIBASHAN V S, OZA P, PATEL V M. Instance relation graph guided source-free domain adaptive object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2023: 3520-3530.
26	魏琢艺, 罗迈, 李文兵, 等. 基于多源域适应的单细胞智能分类. 计算机工程, 2024, 50 (6): 48- 55. doi: 10.19678/j.issn.1000-3428.0067378
	WEI Z Y , LUO M , LI W B , et al. Intelligent single-cell classification based on multisource domain adaptation. Computer Engineering, 2024, 50 (6): 48- 55. doi: 10.19678/j.issn.1000-3428.0067378
27	YU J Z, LIU J M, WEI X B, et al. MTTrans: cross-domain object detection with mean teacher transformer[EB/OL]. [2024-03-05]. https://arxiv.org/abs/2205.01643.
28	ZHANG H , LUO G Y , LI J L , et al. C2FDA: coarse-to-fine domain adaptation for traffic object detection. IEEE Transactions on Intelligent Transportation Systems, 2022, 23 (8): 12633- 12647. doi: 10.1109/TITS.2021.3115823
29	ZHENG Y T, HUANG D, LIU S T, et al. Cross-domain object detection through coarse-to-fine feature adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 13763-13772.
30	RAMAMONJISON R, BANITALEBI-DEHKORDI A, KANG X Y, et al. SimROD: a simple adaptation method for robust object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2021: 3550-3559.
31	CHENG Z, LUO X, SHI Y Q, et al. Fabric defect detection algorithm based on YOLOv3 transfer learning[C]//Proceedings of the International Conference on Frontiers of Electronics, Information and Computation Technologies. Washington D.C., USA: IEEE Press, 2021: 1-7.
32	ZHAO J, ZHOU S, ZHENG Q, et al. Fabric defect detection based on transfer learning and improved Faster R-CNN[EB/OL]. [2024-03-05]. https://aircconline.com/ijaia/V12N4/12421ijaia02.pdf.
33	DI L , DENG S S , LIANG J Z , et al. Context receptive field and adaptive feature fusion for fabric defect detection. Soft Computing, 2023, 27 (18): 13421- 13434. doi: 10.1007/s00500-022-07675-8
34	LU B Y , HUANG B Q . A texture-aware one-stage fabric defect detection network with adaptive feature fusion and multi-task training. Journal of Intelligent Manufacturing, 2024, 35 (3): 1267- 1280. doi: 10.1007/s10845-023-02105-4
35	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//Proceedings of the International Conference on Learning Representations. Washington D.C., USA: IEEE Press, 2015: 23-30.
36	GANIN Y, LEMPITSKY V. Unsupervised domain adaptation by backpropagation[C]//Proceedings of the International Conference on Machine Learning. Washington D.C., USA: IEEE Press, 2015: 1180-1189.
37	BRIGHAM E. The fast Fourier transform and its applications[EB/OL]. [2024-03-05]. https://ieeexplore.ieee.org/document/4320436.
38	DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2009: 248-255.
39	HE Z W, ZHANG L. Multi-adversarial Faster-RCNN for unrestricted object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2019: 6667-6676.

[1]	田青, 郁江森, 刘祥, 李燕芝, 申珺妤. 基于过渡桥接机制的对抗性开放集领域自适应[J]. 计算机工程, 2026, 52(1): 116-125.
[2]	邹少华, 刘笑嶂, 李修来. 融合交叉注意力和双特征交互的红外船舶目标检测模型[J]. 计算机工程, 2026, 52(1): 390-399.
[3]	刘杰, 黄晓辉, 郭敬博. 基于YOLOv8的轻量级田间棉花品级检测[J]. 计算机工程, 2026, 52(1): 400-413.
[4]	黄金贵, 刘朋, 唐文胜. MMD-YOLOv7:黑暗条件下车辆检测方法[J]. 计算机工程, 2025, 51(9): 340-349.
[5]	朱思远, 李佳圣, 邹丹平, 何迪, 郁文贤. 基于半监督学习的非结构化道路缺陷检测算法[J]. 计算机工程, 2025, 51(9): 14-24.
[6]	马淦, 谷雨, 彭冬亮. 结合改进YOLOv5s和动态数据增强的海面舰船检测[J]. 计算机工程, 2025, 51(9): 294-305.
[7]	王舒梦, 徐慧英, 朱信忠, 黄晓, 宋杰, 李毅. 基于改进YOLOv8n的航拍轻量化小目标检测算法: PECS-YOLO[J]. 计算机工程, 2025, 51(9): 280-293.
[8]	倪源松, 韩军, 邹小燕, 胡广怡, 王文帅. 两阶段自适应分块输电线路螺栓缺陷检测方法[J]. 计算机工程, 2025, 51(8): 281-291.
[9]	苗茹, 李祎, 周珂, 张俨娜, 常然然, 孟更. 一种改进的Faster R-CNN遥感图像多目标检测模型研究[J]. 计算机工程, 2025, 51(8): 292-304.
[10]	宋杰, 徐慧英, 朱信忠, 黄晓, 陈晨, 王泽宇. 基于YOLOv8改进的跌倒检测算法: OEF-YOLO[J]. 计算机工程, 2025, 51(7): 127-139.
[11]	欧阳昱中, 韩锐, 刘驰. 边缘侧领域自适应中长尾视觉识别技术研究[J]. 计算机工程, 2025, 51(7): 171-179.
[12]	刘旭东, 杨绪兵. L1-OCSVM模型设计及其在林业目标检测中的应用[J]. 计算机工程, 2025, 51(7): 375-384.
[13]	刘春霞, 孟吉星, 潘理虎, 龚大立. 融合RGB与IR图像的遥感小目标检测方法[J]. 计算机工程, 2025, 51(7): 326-338.
[14]	张佳承, 韦锦, 陈义时. 改进YOLOv8的实时轻量化鲁棒绿篱检测算法[J]. 计算机工程, 2025, 51(7): 362-374.
[15]	栾孟娜, 郑秋梅, 王风华. 基于DMC-YOLO的交通标志实时检测算法[J]. 计算机工程, 2025, 51(7): 90-99.

选择文件类型/文献管理软件名称

选择包含的内容