Nowadays, the development of the food industry and economic recovery have driven escalating consumer demands for high-quality, nutritious, and safe food products, and spectroscopic technologies are increasingly prominent as essential tools for food quality inspection. Concurrently, the rapid rise of artificial intelligence (AI) has created new opportunities for food quality detection. As a critical branch of AI, deep learning synergizes with spectroscopic technologies to enhance spectral data processing accuracy, enable real-time decision making, and address challenges from complex matrices and spectral noise. This review summarizes six cutting-edge nondestructive spectroscopic and imaging technologies, near-infrared/mid-infrared spectroscopy, Raman spectroscopy, fluorescence spectroscopy, hyperspectral imaging (spanning the UV, visible, and NIR regions, to simultaneously capture both spatial distribution and spectral signatures of sample constituents), terahertz spectroscopy, and nuclear magnetic resonance (NMR), along with their transformative applications. We systematically elucidate the fundamental principles and distinctive merits of each technological approach, with a particular focus on their deep learning-based integration with spectral fusion techniques and hybrid spectral-heterogeneous fusion methodologies. Our analysis reveals that the synergy between spectroscopic technologies and deep learning demonstrates unparalleled superiority in speed, precision, and non-invasiveness. Future research should prioritize three directions: multimodal integration of spectroscopic technologies, edge computing in portable devices, and AI-driven applications, ultimately establishing a high-precision and sustainable food quality inspection system spanning from production to consumption.

Peanut kernels, known for their high nutritional value and palatability, are classified as nut food. In this study, peanut kernel samples from six distinct cities in Shandong Province, China, were examined to categorize and trace their origins. Near-infrared (NIR) spectra of samples were captured using a portable NIR-M-R2 spectrometer. After the application of Savitzky-Golay (SG) filtering, the classification was attempted using principal component analysis (PCA) plus linear discrimination analysis (LDA). Additionally, maximum uncertainty linear discriminant analysis (MLDA) was applied for comparison. A specific number of eigenvectors could respectively maximize the classification accuracies, 81.48% for PCA + LDA and 76.54% for MLDA. In order to further improve the classification accuracies, Adaboost-MLDA was proposed to develop a stronger classifier. This method, after 18 iterations, achieved remarkable effects, achieving a high accuracy of 95.06%. In a similar vein, the enhancement with preprocessing techniques multiplicative scatter correction (MSC) + SG and standard normal variate (SNV) + SG raised accuracies to 98.77% and 97.53%, respectively. The results of classifying first-order and second-order derivative spectra using Adaboost-MLDA were also described, achieving accuracies near 100%. The experiment demonstrates that integrating Adaboost with NIR spectroscopy offers a highly accurate method for peanut kernel classification, promising for practical applications in food quality control.

The quality of chrysanthemum tea has a great connection with its variety. Different types of chrysanthemum tea have very different efficacies and functions. Moreover, the discrimination of chrysanthemum tea varieties is a significant issue in the tea industry. Therefore, to correctly and non-destructively categorize chrysanthemum tea samples, this study attempted to design a novel feature extraction method based on the fuzzy set theory and improved direct linear discriminant analysis (IDLDA), called fuzzy IDLDA (FIDLDA), for extracting the discriminant features from the near-infrared (NIR) spectral data of chrysanthemum tea. To start with, a portable NIR spectrometer was used to collect NIR data for five varieties of chrysanthemum tea, totaling 400 samples. Secondly, the raw NIR spectra were processed by four different pretreatment methods to reduce noise and redundant data. Thirdly, NIR data dimensionality reduction was performed by principal component analysis (PCA). Fourthly, feature extraction from the NIR spectra was performed by linear discriminant analysis (LDA), IDLDA, and FIDLDA. Finally, the K-nearest neighbor (KNN) algorithm was applied to evaluate the classification accuracy of the discrimination system. The experimental results show that the discrimination accuracies of LDA, IDLDA, and FIDLDA could reach 87.2%, 94.4%, and 99.2%, respectively. Therefore, the combination of near-infrared spectroscopy and FIDLDA has great application potential and prospects in the field of nondestructive discrimination of chrysanthemum tea varieties.

Milk is a kind of dairy product with high nutritive value. Tracing the origin of milk can uphold the interests of consumers as well as the stability of the dairy market. In this study, a fuzzy direct linear discriminant analysis (FDLDA) is proposed to extract the near-infrared spectral information of milk by combining fuzzy set theory with direct linear discriminant analysis (DLDA). First, spectral data of the milk samples were collected by a portable NIR spectrometer. Then, the data were preprocessed by Savitzky–Golay (SG) and standard normal variables (SNV) to reduce noise, and the dimensionality of the spectral data was decreased by principal component analysis (PCA). Furthermore, linear discriminant analysis (LDA), DLDA, and FDLDA were employed to transform the spectral data into feature space. Finally, the k-nearest neighbor (KNN) classifier, extreme learning machine (ELM) and naïve Bayes classifier were used for classification. The results of the study showed that the classification accuracy of FDLDA was higher than DLDA when the KNN classifier was used. The highest recognition accuracy of FDLDA, DLDA, and LDA could reach 97.33%, 94.67%, and 94.67%. The classification accuracy of FDLDA was also higher than DLDA when using ELM and naïve Bayes classifiers, but the highest recognition accuracy was 88.24% and 92.00%, respectively. Therefore, the KNN classifier outperformed the ELM and naïve Bayes classifiers. This study demonstrated that combining FDLDA, DLDA, and LDA with NIR spectroscopy as an effective method for determining the origin of milk.

The grade of tea is closely related to tea quality, so the identification of tea grade is an important task. In order to improve the identification capability of the tea grade system, a fuzzy maximum uncertainty linear discriminant analysis (FMLDA) methodology was proposed based on maximum uncertainty linear discriminant analysis (MLDA). Based on FMLDA, a tea grade recognition system was established for the grade recognition of Chunmee tea. The process of this system is as follows: firstly, the near-infrared (NIR) spectra of Chunmee tea were collected using a Fourier transform NIR spectrometer. Next, the spectra were preprocessed using standard normal variables (SNV). Then, direct linear discriminant analysis (DLDA), maximum uncertainty linear discriminant analysis (MLDA), and FMLDA were used for feature extraction of the spectra, respectively. Finally, the k-nearest neighbor (KNN) classifier was applied to classify the spectra. The k in KNN and the fuzzy coefficient, m, were discussed in the experiment. The experimental results showed that when k = 1 and m = 2.7 or 2.8, the accuracy of the FMLDA could reach 98.15%, which was better than the other two feature extraction methods. Therefore, FMLDA combined with NIR technology is an effective method in the identification of tea grade.

The quality of milk is tightly linked to its brand. A famous brand of milk always has good quality. Therefore, this study seeks to design a new fuzzy feature extraction method, called fuzzy improved null linear discriminant analysis (FiNLDA), to cluster the spectra of collected milk for identifying milk brands. To elevate the classification accuracy, FiNLDA was applied to process the near-infrared (NIR) spectra of milk acquired by the portable near-infrared spectrometer. The principal component analysis and Savitzky–Golay (SG) filtering algorithm were employed to lower dimensionality and eliminate noise in this system, respectively. Thereafter, improved null linear discriminant analysis (iNLDA) and FiNLDA were applied to attain the discriminant information of the NIR spectra. At last, the K-nearest neighbor classifier was utilized for assessing the performance of the identification system. The results indicated that the maximum classification accuracies of LDA, iNLDA and FiNLDA were 74.7%, 88% and 94.67%, respectively. Accordingly, the portable NIR spectrometer in combination with FiNLDA can classify milk brands correctly and effectively.