论文标题
现实世界中的工业数据集中检测异常检测的综合评分
Composite Score for Anomaly Detection in Imbalanced Real-World Industrial Dataset
论文作者
论文摘要
近年来，工业部门已发展为第四次革命。质量控制域对用于计算机视觉异常检测的高级机器学习特别感兴趣。然而，必须面对几个挑战，包括不平衡的数据集，图像复杂性和零false阴性（ZFN）约束，以确保高质量的要求。本文说明了工业合作伙伴的用例，在该案件中，印刷电路板组件（PCBA）图像首先是通过量化了对普通产品培训的矢量量化生成对抗网络（VQGAN）重建的。然后，在一些正常和异常的图像上提取了几个多级指标，通过重建差异突出了异常。最后，由于提取的指标，分类器经过培训可以建立复合异常得分。这种三步方法是在公共MVTEC-AD数据集和伙伴PCBA数据集上执行的，在ZFN约束下，它的定期准确度为95.69％和87.93％。
In recent years, the industrial sector has evolved towards its fourth revolution. The quality control domain is particularly interested in advanced machine learning for computer vision anomaly detection. Nevertheless, several challenges have to be faced, including imbalanced datasets, the image complexity, and the zero-false-negative (ZFN) constraint to guarantee the high-quality requirement. This paper illustrates a use case for an industrial partner, where Printed Circuit Board Assembly (PCBA) images are first reconstructed with a Vector Quantized Generative Adversarial Network (VQGAN) trained on normal products. Then, several multi-level metrics are extracted on a few normal and abnormal images, highlighting anomalies through reconstruction differences. Finally, a classifer is trained to build a composite anomaly score thanks to the metrics extracted. This three-step approach is performed on the public MVTec-AD datasets and on the partner PCBA dataset, where it achieves a regular accuracy of 95.69% and 87.93% under the ZFN constraint.
