Rapid Non-destructive Detection of Foreign Bodies in Fish Based on Terahertz Imaging and Spectroscopy

• In order to improve the accuracy of the model and reduce the computational effort, three algorithms including CARS, UVE and SPA are used to extract the spectral features. • Three qualitative discriminant models including PLS-DA, LDA and SVM are established to detect and identify foreign bodies in fish. The model is optimized to obtain the best SVM model after CARS feature extraction. The accuracy of the prediction set reaches 99.56%. • The terahertz images of the sample in 0.1-4.0 THz are visualized and analyzed. It is found that the foreign bodies in the fish are clearly outlined, and the position, shape and size of the foreign bodies in the fish can be well distinguished. • The size, shape and location of foreign bodies in the image can be clearly determined based on the CARS algorithm compression data, and the amount of data is only about 10% of the original, reducing a lot of computing time, and realizing the visualization research of foreign bodies in fish by THZ technology. Food safety is a matter of social stability and healthy development of the national economy. The processing technology of fish complicated and tedious and it is inclined to have fish bone residues or mixed with various foreign bodies during the processing. It is difficult to detect these foreign bodies by traditional manual and visual detection methods, which poses a serious threat to the health of people. In this case, this paper aims to explore the feasibility of rapid and non-destructive detection of endogenous foreign bodies (fish bones) and exogenous foreign bodies (metal, plastic, wood toothpicks) in fish based on terahertz imaging and spectroscopy. Methods: Firstly, the transmission terahertz spectral images of fish samples are acquired, and the terahertz spectral information of the region of interest is extracted. Secondly, In order to improve the accuracy of the model and reduce the computational effort, three algorithms including Competitive Adaptive Reweighting Sampling (CARS), Uninformative Variable Elimination (UVE) and Successive Projections Algorithm (SPA) are used to extract the spectral features. Thirdly, three qualitative discriminant models including Partial Least Squares Discriminant Analysis (PLS-DA), Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) are established to detect and identify foreign bodies in fish. Finally, in order to realize the visual expression of Foreign Bodies, the terahertz images of fish are segmented by binarization threshold. Results: The model is optimized to obtain the best SVM model after CARS feature extraction with the accuracy rate of 99.56%. Meanwhile, the terahertz images of the samples at 0.1-4.0 THz are visualized and analyzed. It is found that the foreign bodies in fish are clearly outlined, and the shape and size of foreign bodies in fish can be well distinguished from terahertz images. Conclusion: This study has proved that the terahertz imaging and spectroscopy technology can achieve rapid and non-destructive detection of endogenous foreign bodies (fish bones) and exogenous foreign bodies (metal, plastic, wood toothpicks) in fish. It provides relevant basis and theoretical reference for rapid non-destructive detection of foreign bodies in food, which is of great significance for food process monitoring and quality control.