[论文] [论文] Synthetic data generation framework for quality control automatio...

论文概要

研究领域: CV
作者: Korota Arsene Coulibaly, Mohamed Hamlich, Khalid Hmali
发布时间: 2026-07-24
arXiv: 2507.19313

中文摘要

印刷质量控制，特别是凹版印刷，仍然依赖缓慢、昂贵和主观的人工检查。自动化表面缺陷检测对于维持凹版印刷的高质量标准至关重要。深度学习模型为自动化提供了前景。然而，训练稳健的深度学习模型，如YOLO或视觉Transformer，受到真实工业缺陷图像极度稀缺的严重阻碍。为克服这一限制，本文介绍了一种专为凹版印刷质量控制量身定制的新型合成数据生成框架。所提出的管道自动生成特定印刷缺陷（褶皱、条纹、套印不准等）的高保真图像，并输出相应的边界框和注释。为验证该框架，生成了7533张图像的合成数据集，并用于训练最先进的目标检测模型RFDETR。实验结果表明，在我们的合成数据上训练的模型在真实工业测试样本上达到了80.9%的平均精度（mAP）。该框架为自动化印刷线缺陷检测提供了零成本、快速部署的解决方案，无需大量手动数据收集。

原文摘要

Quality control in printing, particularly in rotogravure printing, still depends on slow, costly, and subjective manual inspection. Automated surface defect detection is critical for maintaining high-quality standards in rotogravure printing. Deep learning models give prospects for automation. However, training robust deep learning models, such as YOLO or Vision Transformers, is heavily hindered by the extreme scarcity of real-world industrial defects images. To overcome this limitation, this paper introduces a novel synthetic data generation framework tailored for rotogravure printing quality control. The proposed pipeline automatically generates high-fidelity images of specific printing defects (creases, streaks, misregistration, etc.) and outputs corresponding bounding boxes and annotat...

自动采集于 2026-07-25

#论文 #arXiv #CV #小凯