Industrial image anomaly detection based on multi Gaussian discriminant model and robust core set

作者：Ran Wei, Zhengyang Li, Lei Geng, Muheiti Wuken, YanBei Liu · 发表于：Measurement Science and Technology · 年份：2024 · DOI：10.1088/1361-6501/ad6c76 · 被引用次数：6 · 研究领域：Anomaly Detection Techniques and Applications、Data-Driven Disease Surveillance、Vibrio bacteria research studies

Abstract To address the issue of false positive (FP) detections in image anomaly detection caused by the loss of low-frequency features when dealing with high-dimensional feature distributions, we propose the multi-layer Gaussian discriminant anomaly detection model (MGAD). This model utilizes distance metrics based on multiple normal distributions to perform anomaly detection. By mining multi-layer feature combinations from normal samples and incorporating a Gaussian mixture model strategy for pixel-by-pixel probability density estimation, a weighting mechanism is designed to emphasize the role of low-frequency features in Gaussian space. This approach effectively models data collections that do not follow a single normal distribution as a mixture of several Gaussian distributions, thereby reducing false detections. Additionally, we propose a method for calculating the minimum Mahalanobis distance based on the estimation of the minimum covariance determinant. By identifying a subset with the smallest covariance matrix determinant, this method enhances the robust estimation of the data’s central position and spread, thereby reducing the impact of outliers. On the MVTec-AD dataset, MGAD demonstrates outstanding performance with an anomaly detection area under the receiver operating characteristic curve (AUROC) of 98.8%, the anomaly localization AUROC of 98.2%, and the per-class true negative rate for normal samples of 93.1%. Compared with the state-of-the-art models, MGAD impr...