Beer-Lambert Guided Representation Learning for Unsupervised Anomaly Detection in Sub-THz Food Inspection Images
This work addresses the need for reliable foreign material detection in food manufacturing by adapting anomaly detection to Sub-THz imaging, but the improvement is incremental.
The paper proposes a Beer-Lambert guided representation learning framework for unsupervised anomaly detection in Sub-THz food inspection images, achieving improved detection performance over baseline methods on the Inline-Food-Inspection-THz dataset.
Food manufacturing requires reliable inspection systems to detect foreign material contamination and maintain product safety. Sub-THz transmission imaging provides material-dependent attenuation characteristics that are useful for detecting low-density contaminants in food products. However, existing unsupervised anomaly detection methods mainly rely on RGB-pretrained visual representations, which may not adequately capture the transmission behavior of Sub-THz images. This paper proposes a Beer-Lambert guided representation learning framework for unsupervised anomaly detection in Sub-THz food inspection images. The proposed method introduces an attenuation decomposition module as an auxiliary regularization module that constrains student representations through attenuation reconstruction during training. In addition to the conventional one-class setting, we introduce a Leave-One-Food-Out protocol to evaluate generalization capability under unseen food categories. Experimental results on the Inline-Food-Inspection-THz dataset show that the proposed method improves overall anomaly detection performance over the baseline method.