Real-Time Anomaly Detection in Packaged Food X-Ray Images Using Supervised Learning

Physical contamination of food occurs when it comes into contact with foreign objects.Foreign objects can be introduced to food at any time during food delivery and packaging and can cause serious concerns such as broken teeth or choking.Therefore,a preventive method that can detect and remove foreign objects in advance is required.Several studies have attempted to detect defective products using deep learning networks.Because it is difficult to obtain foreign object-containing food data from industry,most studies on industrial anomaly detection have used unsupervised learning methods.This paper proposes a new method for real-time anomaly detection in packaged food products using a supervised learning network.In this study,a realistic X-ray image training dataset was constructed by augmenting foreign objects with normal product images in a cut-paste manner.Based on the augmented training dataset,we trained YOLOv4,a real-time object detection network,and detected foreign objects in the test data.We evaluated this method on images of pasta,snacks,pistachios,and red beans under the same conditions.The results show that the normal and defective products were classified with an accuracy of at least 94%for all packaged foods.For detecting foreign objects that are typically difficult to detect using the unsupervised learning and traditional methods,the proposed method achieved high-performance realtime anomaly detection.In addition,to eliminate the loss in high-resolution X-ray images,the false positive rate and accuracy could be lowered to 5%with patch-based training and a new post-processing algorithm.

Terahertz polarization sensing,chirality enhancement,and specific binding based on metasurface sensors for biochemical detection:a review[Invited]

Specific and highly-sensitive biochemical detection technology is particularly important in global epidemics and has critical applications in life science,medical diagnosis,and pharmaceutics.As a newly developed technology,the THz metamaterialbased sensing method is a promising technique for extremely sensitive biomolecular detection.However,due to the significant resonant peaks generated by THz metamaterials,the characteristic absorption peaks of the analyte are usually masked,making it difficult to distinguish enantiomers and specifically identify target biomolecules.Recently,new ways to overcome this limitation have become possible thanks to the emergence of chiral metasurfaces and the polarization sensing method.Additionally,functionalized metasurfaces modified by antibodies or other nanomaterials are also expected to achieve specific sensing with high sensitivity.In this review,we summarize the main advances in THz metamaterials-based sensing from a historical perspective as well as application in chiral recognition and specific detection.Specifically,we introduce the basic theory and key technology of THz polarization spectrum and chiral sensing for biochemical detection,and immune sensing based on biomolecular interaction is also discussed.We mainly focus on chiral recognition and specific sensing using THz metasurface sensors to cover the most recent advances in the topic,which is expected to break through the limitations of traditional THz absorption spectroscopy and chiral spectroscopy in the visible-infrared band and develop into an irreplaceable method for the characterization of biochemical substances.