Integration of deep generative Anomaly Detection algorithm in high-speed industrial line
This work provides a solution for improving the accuracy and throughput of visual inspection in pharmaceutical manufacturing, which currently suffers from operator variability and limited throughput.
This paper addresses the challenge of high-accuracy visual inspection in pharmaceutical production by developing a semi-supervised anomaly detection framework. The framework, based on a generative adversarial architecture, achieves high detection performance within a 500 ms acquisition slot on a high-speed Blow-Fill-Seal line.
Industrial visual inspection in pharmaceutical production requires high accuracy under strict constraints on cycle time, hardware footprint, and operational cost. Manual inline inspection is still common, but it is affected by operator variability and limited throughput. Classical rule-based computer vision pipelines are often rigid and difficult to scale to highly variable production scenarios. To address these limitations, we present a semi-supervised anomaly detection framework based on a generative adversarial architecture with a residual autoencoder and a dense bottleneck, specifically designed for online deployment on a high-speed Blow-Fill-Seal (BFS) line. The model is trained only on nominal samples and detects anomalies through reconstruction residuals, providing both classification and spatial localization via heatmaps. The training set contains 2,815,200 grayscale patches. Experiments on a real industrial test kit show high detection performance while satisfying timing constraints compatible with a 500 ms acquisition slot.