Integration of deep generative Anomaly Detection algorithm in high-speed industrial line

TL;DR

This paper introduces a semi-supervised deep generative anomaly detection method tailored for high-speed industrial lines, achieving high accuracy and real-time performance in pharmaceutical visual inspection tasks.

Contribution

It presents a novel generative adversarial framework with a residual autoencoder for online anomaly detection, optimized for high-speed industrial environments.

Findings

High detection accuracy on real industrial data

Operates within 500 ms timing constraints

Effective spatial localization of anomalies

Abstract

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.