基于生成式样本合成的工件缺陷样本数据增强

李晋芳; 肖立宝; 何明桐; 莫建清

doi:10.12052/gdutxb.240056

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于生成式样本合成的工件缺陷样本数据增强

计算机科学与技术 | 更新时间：2026-05-27

- 基于生成式样本合成的工件缺陷样本数据增强
- Method for Data Augmentation of Workpiece Defect Samples Based on Generative Sample Synthesis
- 广东工业大学学报 2025年42卷第3期页码：27-35
- 作者机构：
  
  广东工业大学机电工程学院,广东,广州,510006
- 作者简介：
  
  李晋芳(1975–)，女，副教授，博士，主要研究方向为虚拟现实，E-mail：lijinfang@gdut.edu.cn
  莫建清(1979–)，男，讲师，博士，主要研究方向为虚拟现实，E-mail：momolon@gdut.edu.cn
- 基金信息：
  
  国家重点研发项目(2018YFB1004902);广州市科技计划项目(2023A03J0724);广州市科技计划重点研发项目(202206010130)
- DOI：10.12052/gdutxb.240056
  中图分类号： TP3-05
- 纸质出版：2025
- 稿件说明：
移动端阅览
李晋芳, 肖立宝, 何明桐, 等. 基于生成式样本合成的工件缺陷样本数据增强[J]. 广东工业大学学报, 2025, 42(3): 27–35.

Li Jinfang, Xiao Libao, He Mingtong, et al. Method for Data Augmentation of Workpiece Defect Samples Based on Generative Sample Synthesis[J]. 2025, 42(3): 27-35.
李晋芳, 肖立宝, 何明桐, 等. 基于生成式样本合成的工件缺陷样本数据增强[J]. 广东工业大学学报, 2025, 42(3): 27–35. DOI： 10.12052/gdutxb.240056

Li Jinfang, Xiao Libao, He Mingtong, et al. Method for Data Augmentation of Workpiece Defect Samples Based on Generative Sample Synthesis[J]. 2025, 42(3): 27-35. DOI： 10.12052/gdutxb.240056.

摘要

针对深度学习模型在工业缺陷视觉检测领域中因样本稀缺而难以较好训练的问题，本文提出一种融合生成对抗网络(Generative Adversarial Network

GAN) 和基于物理的渲染(Physically Based Rendering

PBR) 流程的生成式样本合成方法用于数据增强。该方法以ConSinGAN为缺陷特征扩增模型，并通过引入坐标注意力机制(Coordinate Attention

CA) 来优化鉴别器，使其能更精确识别图像中的缺陷特征。同时调整损失函数，引入重构损失与多尺度结构相似度损失的加权组合以缓解小样本训练中的梯度消失问题并提高生成质量。采用PBR流程输出扩增样本，首先为待扩增样本的工件构建三维模型，然后利用泊松融合将扩增的缺陷特征与原始模型贴图融合，最后在虚拟生产环境中通过虚拟相机渲染输出工件缺陷样本。在公共数据集下的实验结果表明该方法可以对给定的工件缺陷小样本进行有效的数据增强。

Abstract

To address the problem of severe lack of defect data in workpieces to train the deep-learning-based defect visual detection systems

this paper introduces a generative sample synthesis method that integrates generative adversarial networks (GAN) with a physical-based rendering (PBR) pipeline for data augmentation. The method employs ConSinGAN as the defect feature generation model and enhances the discriminator by incorporating a coordinate attention (CA) mechanism

enabling more precise identification of defect features in images. Additionally

the loss function is adjusted by introducing a weighted combination of reconstruction loss and multi-scale structural similarity loss to alleviate the gradient vanishing in small sample training and improve the quality of generated samples. The PBR pipeline is used to output the augmented samples

which first constructs a 3D model for the workpiece to be augmented

and then use poisson blending to merge the generated defect features with the original model texture. Finally

defect samples of the workpiece are rendered in a simulated production environment using a virtual camera. Experimental results on public datasets demonstrate the effectiveness of the proposed method in augmenting small samples of workpiece defects.

关键词

Keywords

references

WANG H J, YANG C H, LYU Q. Review of metal surface defect detection methods based on machine vision[J]. Mirco/Nano Electronics and Intelligent Manufacturing, 2022, 4(4): 71-81.

JIN Y G, ZHANG T, YANG Y N, et al . Review of product defect detection methods based on deep learning[J ] . Journal of Dalian Minzu University, 2020, 22(5): 420-427.

LUO D L, CAI Y X, YANG Z H, et al . Survey on industrial defect detection with deep learning[J ] . Scientia Sinica Informationis, 2022, 52(6): 1002-1039

MUMUNI A, MUMUNI F. Data augmentation: a comprehensive survey of modern approaches[J]. Array, 2022, 16: 100258.

GOODFELLOW I, POPUGET-ABADIE J, MIRZA M, et al . Generative adversarial networks[J ] . Communications of the ACM, 2020, 63(11): 139-144.

SUN S K, FAN J, SUN Z Q, et al . Survey of image data augmentation techniques based on deep learning[J ] . Computer Science, 2024, 51(1): 150-167.

ZHUANG C Q, LI J W. Industrial defect detection of plastic labels based on YOLOv5 and generative adversarial networks[J]. Computer Measurement Control, 2023, 31(7): 91-98.

LUO Y T, DUAN C, JIANG P F, et al . An improved industrial defect data augmentation method based on pix2pix[J ] . Computer Engineering Science, 2022, 44(12): 2206-2212.

PHILLIP I, ZHU J Y, ZHOU T H, et al . Image-to-image translation with conditional adversarial networks[C ] //2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Honolulu: IEEE, 2017: 5967-5976.

LIU J H, WANG C Y, SU H, et al . Multistage GAN for fabric defect detection[J ] . IEEE Transactions on Image Processing, 2019, 29: 3388-3400.

YAN Y D, SUN J D, YAO C, et al . CT image data amplification based on generative adversarial network[J ] . Computer Systems Applications, 2022, 31(12): 78-86.

TAMAR R S, TALI D, TOMER M. SinGAN: learning a generative model from a single natural image[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Seoul: IEEE, 2019: 4569-4579.

HINZ T, FISHER M, WANG O, et al . Improved techniques for training single-image gans[C ] //2021 IEEE Winter Conference on Applications of Computer Vision (WACV) . Waikoloa: IEEE, 2021: 1299-1308.

PENG Y F, DENG J N, WANG G. Remote sensing image data enhancement based on improved SinGAN[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(3): 387-396.

ZHAO X F, XIA Y T, XU Y B, et al . Joint data augmentation method for ground infrared target[J ] . Laser Infrared, 2023, 53(7): 1117-1124.

HUANG Q N, ZHU W G, LIU Y, et al . SAR ship target expansion based on multiscale GAN network[J ] . Ordnance Industry Automation, 2022, 41(7): 47-52.

ZHANG H, GOODFELLOW I, METAXAS D, et al . Self-attention generative adversarial networks[J ] . Proceedings of Machine Learning Research, 2019, 97: 7354-7363.

HU J, SHEN L, SUN G, et al . Squeeze-and-excitation networks[C ] //2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141.

WOO S, PARK J, LEE J Y, et al . CBAM: convolutional block attention module[C ] //Computer Vision - ECCV 2018: 15th European Conference. Munich: Springer, 2018: 3-19.

HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Nashville: IEEE, 2021: 13708-13717.

ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein generative adversarial networks[J]. Proceedings of Machine Learning Research, 2017, 70: 214-223.

GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV) . Santiago: IEEE, 2015: 1440-1448.

WANG Z, SIMONCELLI E P, BOVIK A C. Multiscale structural similarity for image quality assessment[C]//The Thrity-Seventh Asilomar Conference on Signals, Systems Computers. Pacific Grove: IEEE, 2003: 1398-1402.

JIANG Y W, JIANG Z H. On the application of PBR method in virtual reality technology[J]. Journal of Heihe University, 2022, 13(6): 178-180.

PEREZ P, GANGNET M, BLAKE A. Poisson image editing[J]. ACM Transactions on Graphics, 2003, 22(3): 313-318.

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

基于注意力机制的无监督GAN多聚焦图像融合

基于深度学习的轻量化道路交通锥目标检测算法

基于扩散生成的两阶段工业异常检测方法

基于生成对抗网络的低光照图像增强算法

基于高效时序建模的RGB-T跟踪