arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.20132cs.CVcs.LG
收藏

玻璃瓶印刷工业质量控制中的机器学习

Machine Learning in Industrial Quality Control of Glass Bottle Prints

Technische Hochschule Nürnberg Georg Simon Ohm(纽伦堡乔治·西蒙·欧姆应用技术大学)

Maximilian Bundscherer, Thomas H. Schmitt, Tobias Bocklet

AI总结:

本文针对玻璃瓶印刷工业质量控制问题,提出并评估了基于传统图像特征与监督分类以及基于微调预训练 CNN 的两种机器学习方法,分别达到 84% 和 87% 的准确率,并利用 Grad-Cam 定位缺陷区域以辅助优化制造过程。

摘要:

在玻璃瓶的工业制造中,瓶身印刷的质量控制是必要的,因为众多因素可能对印刷过程产生负面影响。尽管玻璃存在反射或与制造相关的偏差,仍必须检测出瓶身印刷中哪怕微小的缺陷。与我们的中型工业合作伙伴合作,我们开发并评估了两种基于机器学习(ML)的瓶身印刷质量控制方法,这些方法也可用于这一具有挑战性的场景。我们的第一种方法利用不同的滤波器来抑制反射(例如 Sobel 或 Canny)以及用于图像比较的图像质量指标(例如 MSE 或 SSIM)作为不同监督分类模型(例如 SVM 或 k-Neighbors)的特征,最终获得了 84% 的准确率。图像基于 ORB 算法进行对齐,这使我们能够估计印刷图案的旋转角度,该旋转角度可作为制造过程中异常的指标。在我们的第二种方法中,我们对不同的预训练 CNN 模型(例如 ResNet 或 VGG)进行了微调以用于二分类,最终获得了 87% 的准确率。利用 Grad-Cam 在我们微调后的 ResNet-34 上,我们能够定位并可视化频繁出现缺陷的瓶身印刷区域。该方法使我们能够提供可用于优化实际制造过程的见解。本文还描述了我们的一般方法以及我们在实践中遇到的数据收集挑战,包括在持续生产过程中进行数据收集、无监督预筛选和标注。

英文摘要:

In industrial manufacturing of glass bottles, quality control of bottle prints is necessary as numerous factors can negatively affect the printing process. Even minor defects in the bottle prints must be detected despite reflections in the glass or manufacturing-related deviations. In cooperation with our medium-sized industrial partner, two ML-based approaches for quality control of these bottle prints were developed and evaluated, which can also be used in this challenging scenario. Our first approach utilized different filters to supress reflections (e.g. Sobel or Canny) and image quality metrics for image comparison (e.g. MSE or SSIM) as features for different supervised classification models (e.g. SVM or k-Neighbors), which resulted in an accuracy of 84%. The images were aligned based on the ORB algorithm, which allowed us to estimate the rotations of the prints, which may serve as an indicator for anomalies in the manufacturing process. In our second approach, we fine-tuned different pre-trained CNN models (e.g. ResNet or VGG) for binary classification, which resulted in an accuracy of 87%. Utilizing Grad-Cam on our fine-tuned ResNet-34, we were able to localize and visualize frequently defective bottle print regions. This method allowed us to provide insights that could be used to optimize the actual manufacturing process. This paper also describes our general approach and the challenges we encountered in practice with data collection during ongoing production, unsupervised preselection, and labeling.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑