基于GAN-Data数据增强与FD-DETR的织物疵点检测方法

陈孟元; 张坦坦; 唐哲

doi:10.12263/DZXB.20250899

您当前的位置：

首页 >

文章列表页 >

基于GAN-Data数据增强与FD-DETR的织物疵点检测方法

学术论文 | 更新时间：2026-06-04

- 基于GAN-Data数据增强与FD-DETR的织物疵点检测方法
- Fabric Defect Detection Method Based on GAN-Data Augmentation and Improved RT-DETR
- 电子学报 2026年54卷第1期页码：417-432
- 作者机构：
  
  安徽工程大学高端装备先进感知与智能控制教育部重点实验室，安徽芜湖 241000
- 作者简介：
  
  [ "陈孟元男，1984年1月出生于安徽省芜湖市。现为安徽工程大学电气工程学院教授、博士生导师，安徽省学术和技术带头人后备人选，安徽省高校杰出青年基金获得者，第一完成人获得安徽省科学技术进步奖一等奖。主要研究方向为移动机器人视觉SLAM与智能制造技术。E-mail: mychen@ahpu.edu.cn" ]
  [ "张坦坦男，2000年5月出生于安徽省宿州市。现为安徽工程大学电子信息专业硕士研究生。主要研究方向为风格迁移与缺陷检测。E-mail: 2230342256@stu.ahpu.edu.cn" ]
  [ "唐哲男，2000年6月出生于安徽省宿州市。现为安徽工程大学电子信息专业硕士研究生。主要研究方向为图像处理。E-mail: 2230342287@stu.ahpu.edu.cn" ]
- 基金信息：
  
  安徽省重点研究与开发计划项目(202304a05020073);安徽省高校杰出青年科研项目(2022AH020065);安徽省高校哲学社会科学研究项目(2023AH050881)
- DOI：10.12263/DZXB.20250899
  中图分类号： TP751.1;TP183
- 收稿：2026-01-06，
  
  录用：2026-01-24，
  
  纸质出版：2026-01-25
- 稿件说明：
移动端阅览
陈孟元, 张坦坦, 唐哲. 基于GAN-Data数据增强与FD-DETR的织物疵点检测方法[J]. 电子学报, 2026, 54(01): 417-432.

CHEN Mengyuan, ZHANG Tantan, TANG Zhe. Fabric Defect Detection Method Based on GAN-Data Augmentation and Improved RT-DETR[J]. Acta Electronica Sinica, 2026, 54(01): 417-432.
陈孟元, 张坦坦, 唐哲. 基于GAN-Data数据增强与FD-DETR的织物疵点检测方法[J]. 电子学报, 2026, 54(01): 417-432. DOI：10.12263/DZXB.20250899

CHEN Mengyuan, ZHANG Tantan, TANG Zhe. Fabric Defect Detection Method Based on GAN-Data Augmentation and Improved RT-DETR[J]. Acta Electronica Sinica, 2026, 54(01): 417-432. DOI：10.12263/DZXB.20250899

摘要

针对纺织工业实际生产中织物疵点样本获取困难且数量稀缺导致深度学习模型应用受限的问题，本文提出了一种将上游数据增强与下游检测模型深度优化相结合的织物疵点检测方法。本文在上游数据增强阶段基于循环生成对抗网络（Cycle-consistent Generative Adversarial Network，Cycle-GAN）提出GAN-Data生成网络，该网络利用掩码（Mask）引导机制实现了疵点特征与背景纹理的解耦处理，在精准控制生成位置的同时解决了基准模型中疵点分布随机性过大的问题。为了应对织物疵点尺度差异显著的挑战，GAN-Data设计了增强疵点生成模块（Enhanced Defect Generation Module，EDGM），通过四个并行的多尺度膨胀卷积分支使感受野能够灵活覆盖从1~17像素的范围，实现了对点状、线状、块状及大面积疵点的自适应特征提取。同时，本文针对背景纹理失真问题引入了基于VGG19网络的纹理保持损失函数，确保了非疵点区域周期性纹理的完整性。在下游优化阶段，本文在RT-DETR的基础上构建了FD-DETR检测网络，在主干网络嵌入了基于Prewitt算子的四方向边缘增强模块以强化弱疵点轮廓捕获能力，并设计了稀疏注意力机制（Sparse Attention-based Intra-scale Feature Interaction，SparseAIFI），通过融合局部窗口、跨步采样及块级模式降低模型复杂度。此外，FD-DETR引入了长宽比感知IoU损失函数（Aspect Ratio Aware-Intersection over Union，ARA-IoU），通过中心距离归一化与自适应权重机制优化了不规则疵点的定位精度。实验部分结合了MVTec AD公开数据集、Industrial Textile Dataset（ITD）数据集及真实生产线自建数据集进行了多维度验证。本文首先在MVTec AD公开数据集上通过结构相似性指标（Structural Similarity Index Measure，SSIM）、峰值信噪比（Peak Signal-to-Noise Ratio，PSNR）及弗雷歇初始距离（Fréchet Inception Distance，FID）等指标验证了GAN-Data生成的图像质量优于主流方法，并通过工业织物数据集（Industrial Textile Dataset，ITD）验证了模型在多材质背景下的跨域泛化能力。随后，通过在多个数据集上的对比实验证明，以GAN-Data增强数据训练的FD-DETR模型在织物疵点识别上显著领先。最后，通过协同优化实验的F1分数曲线分析证实，相较于单一改进，GAN-Data与FD-DETR的结合在小样本场景下具有更快的收敛速度与更高的性能上限，验证了上下游协同路线的可行性。

Abstract

To address the limitations of deep learning models in the textile industry caused by the scarcity of fabric defect samples

this paper proposes a method combining upstream data augmentation with downstream detection model deep optimization. In actual production

the extreme scarcity of defect samples results in a “small-sample dilemma” that hinders model training. During the upstream stage

a GAN-Data generative network is designed based on the cycle-consistent generative adversarial network (Cycle-GAN) architecture. This network utilizes a mask-guided mechanism to decouple defect features from background textures

ensuring precise positioning and resolving distribution randomness. To handle significant scale variations

GAN-Data incorporates an enhanced defect generation module (EDGM)

which employs parallel multi-scale dilated convolution branches to achieve adaptive feature extraction for various defect types. Furthermore

a texture-preservation loss function based on the VGG19 network and Gram Matrix constraints is introduced to maintain the integrity of periodic fabric textures in non-defect regions. In the downstream stage

the FD-DETR detection network is constructed. Its backbone embeds a four-directional edge enhancement module based on the Prewitt operator to strengthen the capture of weak defect contours. To improve efficiency

a sparse attention-based intra-scale feature interaction (SparseAIFI) mechanism is designed

which effectively reduces the computational complexity by fusing local window

striped sampling

and block-level sparse patterns. Additionally

an aspect ratio aware-IoU (ARA-IoU) loss function is introduced to optimize the localization accuracy for irregular defects through center distance normalization and an adaptive weighting mechanism.The method is validated using the MVTec AD dataset

the industrial textile dataset (ITD)

and a self-built production line dataset. Initial evaluations using the structural similarity index measure (SSIM)

peak signal-to-noise ratio (PSNR)

and Fréchet inception distance (FID) demonstrate that GAN-Data achieves superior image quality and cross-domain generalization. Subsequent comparative experiments show that the FD-DETR model trained with GAN-augmented data significantly improves detection accuracy while meeting industrial requirements. Finally

collaborative optimization experiments confirm that integrating GAN-Data and FD-DETR achieves faster convergence and higher performance ceilings than single-stage improvements. In conclusion

this bidirectional synergistic route provides an efficient solution for fabric defect detection under small-sample conditions.

关键词

Keywords

references

王斌 , 李敏 , 雷承霖 , 等 . 基于深度学习的织物疵点检测研究进展 [J ] . 纺织学报 , 2023 , 44 ( 1 ): 219 - 227 . DOI: 10.13475/j.fzxb.20211105509 http://dx.doi.org/10.13475/j.fzxb.20211105509

Wang Bin , Li Min , Lei Chenglin , et al . Research progress in fabric defect detection based on deep learning [J ] . Journal of Textile Research , 2023 , 44 ( 1 ): 219 - 227 . (in Chinese) . DOI: 10.13475/j.fzxb.20211105509 http://dx.doi.org/10.13475/j.fzxb.20211105509

葛轶洲 , 刘恒 , 王言 , 等 . 小样本困境下的深度学习图像识别综述 [J ] . 软件学报 , 2022 , 33 ( 1 ): 193 - 210 .

Ge Yizhou , Liu Heng , Wang Yan , et al . Survey on deep learning image recognition in dilemma of small samples [J ] . Journal of Software , 2022 , 33 ( 1 ): 193 - 210 . (in Chinese)

Cheng Ling , Zhao Lianying , Chen Li , et al . Digital image processing of cotton yarn seriplane [C ] // 2010 International Conference on Computer and Information Application . Piscataway : IEEE , 2010 : 274 - 277 . DOI: 10.1109/iccia.2010.6141590 http://dx.doi.org/10.1109/iccia.2010.6141590

Goodfellow I , Pouget-Abadie J , Mirza M , et al . Generative adversarial networks [J ] . Communications of the ACM , 2020 , 63 ( 11 ): 139 - 144 . DOI: 10.1145/3422622 http://dx.doi.org/10.1145/3422622

王伟 , 张静宜 , 温玉辉 , 等 . 基于神经网络的图像风格迁移算法综述 [J ] . 电子学报 , 2025 , 53 ( 5 ): 1692 - 1712 .

Wang Wei , Zhang Jingyi , Wen Yuhui , et al . Neural network based image style transfer: A survey [J ] . Acta Electronica Sinica , 2025 , 53 ( 5 ): 1692 - 1712 . (in Chinese)

Zhu J Y , Park T , Isola P , et al . Unpaired image-to-image translation using cycle-consistent adversarial networks [C ] // 2017 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 2242 - 2251 . DOI: 10.1109/iccv.2017.244 http://dx.doi.org/10.1109/iccv.2017.244

李云红 , 张蕾涛 , 李丽敏 , 等 . 基于CycleGAN-IA方法和M-ConvNext网络的苹果叶片病害图像识别 [J ] . 农业机械学报 , 2024 , 55 ( 4 ): 204 - 212 .

Li Yunhong , Zhang Leitao , Li Limin , et al . Image recognition of apple leaf disease based on CycleGAN-IA method and M-ConvNext network [J ] . Transactions of the Chinese Society for Agricultural Machinery , 2024 , 55 ( 4 ): 204 - 212 . (in Chinese)

牛玉贞 , 张凌昕 , 兰杰 , 等 . 基于分频式生成对抗网络的非成对水下图像增强 [J ] . 电子学报 , 2025 , 53 ( 2 ): 527 - 544 .

Niu Yuzhen , Zhang Lingxin , Lan Jie , Lan J , et al . FD-GAN: Frequency-decomposed generative adversarial network for unpaired underwater image enhancement [J ] . Acta Electronica Sinica , 2025 , 53 ( 2 ): 527 - 544 . (in Chinese)

Duan Yuxuan , Hong Yan , Niu Li , et al . Few-shot defect image generation via defect-aware feature manipulation [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 1 ): 571 - 578 . DOI: 10.1609/aaai.v37i1.25132 http://dx.doi.org/10.1609/aaai.v37i1.25132

Zhang Cheng , Wang Yuanhao , Vicente F , et al . FabricDiffusion: High-fidelity texture transfer for 3D garments generation from in-the-wild images [C ] // SIGGRAPH Asia 2024 Conference Papers . New York : ACM , 2024 : 1 - 12 . DOI: 10.1145/3680528.3687637 http://dx.doi.org/10.1145/3680528.3687637

秦嘉奇 , 江泽涛 , 雷晓春 . 基于ICFIE-YOLO的低照度图像目标检测方法 [J ] . 电子学报 , 2025 , 53 ( 2 ): 514 - 526 .

Qin Jiaqi , Jiang Zetao , Lei Xiaochun . Low illumination image object detection method based on ICFIE-YOLO [J ] . Acta Electronica Sinica , 2025 , 53 ( 2 ): 514 - 526 . (in Chinese)

邵延华 , 张铎 , 楚红雨 , 等 . 基于深度学习的YOLO目标检测综述 [J ] . 电子与信息学报 , 2022 , 44 ( 10 ): 3697 - 3708 . DOI: 10.11999/JEIT210790 http://dx.doi.org/10.11999/JEIT210790

Shao Yanhua , Zhang Duo , Chu Hongyu , Chu H Y , et al . A review of YOLO object detection based on deep learning [J ] . Journal of Electronics & Information Technology , 2022 , 44 ( 10 ): 3697 - 3708 . (in Chinese) . DOI: 10.11999/JEIT210790 http://dx.doi.org/10.11999/JEIT210790

Carion N , Massa F , Synnaeve G , et al . End-to-end object detection with transformers [C ] // Computer Vision - ECCV 2020 . Cham : Springer , 2020 : 213 - 229 . DOI: 10.1007/978-3-030-58452-8_13 http://dx.doi.org/10.1007/978-3-030-58452-8_13

CHEN Songle , SUN Hongbo , WU Yuxin , et al . A helmet detection algorithm based on transformers with deformable attention module [J ] . Chinese Journal of Electronics , 2025 , 34 ( 1 ): 229 - 241 . DOI: 10.23919/cje.2023.00.346 http://dx.doi.org/10.23919/cje.2023.00.346

Zhao Yian , Lv Wenyu , Xu Shangliang , et al . DETRs beat YOLOs on real-time object detection [C ] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 16965 - 16974 . DOI: 10.1109/cvpr52733.2024.01605 http://dx.doi.org/10.1109/cvpr52733.2024.01605

Lin T Y , Dollár P , Girshick R , et al . Feature pyramid networks for object detection [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2017 : 936 - 944 . DOI: 10.1109/cvpr.2017.106 http://dx.doi.org/10.1109/cvpr.2017.106

Woo S , Park J , Lee J Y , et al . CBAM: Convolutional block attention module [M ] // Computer Vision - ECCV 2018 . Cham : Springer International Publishing , 2018 : 3 - 19 . DOI: 10.1007/978-3-030-01234-2_1 http://dx.doi.org/10.1007/978-3-030-01234-2_1

Motamedi M , Sakharnykh N , Kaldewey T . A data-centric approach for training deep neural networks with less data [PP/OL ] . V2.arXiv ( 2021-10-29 )[ 2026-01-06 ] . https://doi.org/10.48550/arXiv.2110.03613 https://doi.org/10.48550/arXiv.2110.03613 .

Bergmann P , Fauser M , Sattlegger D , et al . MVTec AD: A comprehensive real-world dataset for unsupervised anomaly detection [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2019 . DOI: 10.1109/cvpr.2019.00982 http://dx.doi.org/10.1109/cvpr.2019.00982 .

Simon T . Industrial textile dataset [DS/OL ] . IEEE Dataport ( 2025-7-19 )[ 2026-01-06 ] . https://ieee-dataport.org/documents/industrialtextiledataset https://ieee-dataport.org/documents/industrialtextiledataset . DOI: 10.1109/mm.2026.3682319 http://dx.doi.org/10.1109/mm.2026.3682319

Wang Tianyu , Yang Xin , Xu Ke , et al . Spatial attentive single-image deraining with a high quality real rain dataset [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2019 : 12262 - 12271 . DOI: 10.1109/cvpr.2019.01255 http://dx.doi.org/10.1109/cvpr.2019.01255

Huynh-Thu Q , Ghanbari M . Scope of validity of PSNR in image/video quality assessment [J ] . Electronics Letters , 2008 , 44 ( 13 ): 800 - 801 . DOI: 10.1049/el:20080522 http://dx.doi.org/10.1049/el:20080522

Zhang R , Isola P , Efros A A , et al . The unreasonable effectiveness of deep features as a perceptual metric [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 586 - 595 . DOI: 10.1109/cvpr.2018.00068 http://dx.doi.org/10.1109/cvpr.2018.00068

Heusel M , Ramsauer H , Unterthiner T , et al . GANs trained by a two time-scale update rule converge to a local Nash equilibrium [J ] . Neural Information Processing Systems , 2017 , 30 : 6629 - 6640 .

Jiang Peiyuan , Dajiang Ergu , Liu Fangyao , et al . A review of yolo algorithm developments [J ] . Procedia Computer Science , 2022 , 199 : 1066 - 1073 . DOI: 10.1016/j.procs.2022.01.135 http://dx.doi.org/10.1016/j.procs.2022.01.135

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于深度学习的单帧图像超分辨率重建综述

基于深度对抗学习潜在表示分布的异常检测模型

衰减解耦机制的图像分类网络

Spatial-FineDef：融合多尺度感知与自适应增强的风电机组叶片小缺陷检测方法

基于注意力惩罚和自适应学习的场景图增强联合多模态方面情感分析