Cereals provide humans with essential nutrients, and its quality assessment has attracted widespread attention. Infrared (IR) spectroscopy (IRS) and hyperspectral imaging (HSI), as powerful nondestructive testing technologies, are widely used in the quality monitoring of food and agricultural products. Artificial intelligence (AI) plays a crucial role in data mining, especially in recent years, a new generation of AI represented by deep learning (DL) has made breakthroughs in analyzing spectral data of food and agricultural products. The combination of IRS/HSI and AI further promotes the development of quality evaluation of cereals. This paper comprehensively reviews the advances of IRS and HSI combined with AI in the detection of cereals quality. The aim is to present a complete review topic as it touches the background knowledge, instrumentation, spectral data processing (including preprocessing, feature extraction and modeling), spectral interpretation, etc. To suit this goal, principles of IRS and HSI, as well as basic concepts related to AI are first introduced, followed by a critical evaluation of representative reports integrating IRS and HSI with AI. Finally, the advantages, challenges and future trends of IRS and HSI combined with AI are further discussed, so as to provide constructive suggestions and guidance for researchers.

Nondestructive identification of wheat grains in different states plays an important role in improving the quality of wheat products. This study investigated the possibility of using hyperspectral imaging techniques to discriminate healthy wheat grain, germinated wheat grain, mildewed wheat grain, and shriveled wheat grain (wheat grain infected with fusarium head blight). Both sides of individual wheat kernels were subjected to hyperspectral imaging (866.4–1701.0 nm) to acquire hyperspectral cube data. Spectral data were preprocessed by using standardization and multiple scattering correction. In addition, the principal component loading method was used to extract the characteristic wavelengths of both sides of wheat grains. The sample is divided into calibration set, test set, and validation set. The data of the calibration set are used to train the partial least squares discriminant analysis model, K-nearest neighbor model, and the support vector machine model, and the test set data are used to test the model. The results show that spectral data of both sides can achieve good classification results, while the reverse spectral data perform better. By comparing with each other, the support vector machine model is selected as the best classification model. Finally, using two hyperspectral images (reverse side) that are not involved in training and testing to verify the accuracy of the established support vector machine model, and the classification effect maps of the four wheat grains were visualized. The results indicate that nondestructive classification of wheat grains in different states is feasible based on hyperspectral imaging technology.

The moisture content of barley seeds is directly related to the quality of barley seeds. Rapid and nondestructive testing of the moisture content of barley seeds has an important significance for agricultural production. In this study, the moisture content of barley seeds was determined nondestructively using hyperspectral imaging technology at 417–1000 nm. Both sides of each barley seed were subjected to hyperspectral imaging to acquire hyperspectral cube data. The spectral data were pretreated by five preprocessing methods (standard normal variate, multiple scattering correction, Savitzky–Golay smoothing, normalization and first derivative). The support vector regression model and partial least squares regression model were established to determine moisture content in barley seeds based on full wavelengths. The results indicated that the dorsal spectral data pretreated by multiple scattering correction yielded better results. In order to simplify modeling process and improve calculation speed of the model, the feature wavelengths were selected by two effective wavelengths selection methods (competitive adaptive reweighted sampling and successive projections algorithm). Subsequently, the support vector regression model and partial least squares regression model were established based on these selected feature wavelengths. Comparing the results of models, the support vector regression model based on the feature wavelengths selected by successive projections algorithm generated a satisfied effect with determination coefficient of 0.937, root mean square error of 0.0154% for calibration set and determination coefficient of 0.883, root mean square error of 0.0198% and residual prediction deviation of 2.596 for prediction set. The obtained results in this study indicated that applying hyperspectral imaging technology to measure moisture content in barley seeds was feasible. Finally, the visualization of moisture content distribution was generated. All these results provided a theoretical basis for the on-line determination of moisture content in barley seeds in the future.

In this study, a hyperspectral imaging system of 866.4–1701.0 nm was selected and combined with multivariate methods to identify wheat kernels with different concentrations of omethoate on the surface. In order to obtain the optimal model combination, three preprocessing methods (standard normal variate (SNV), Savitzky–Golay first derivative (SG1), and multivariate scatter correction (MSC)), three feature extraction algorithms (successive projections algorithm (SPA), random frog (RF), and neighborhood component analysis (NCA)), and three classifier models (decision tree (DT), k-nearest neighbor (KNN), and support vector machine (SVM)) were applied to make a comparison. Firstly, based on the full wavelengths modeling analysis, it was found that the spectral data after MSC processing performed best in the three classifier models. Secondly, three feature extraction algorithms were used to extract the feature wavelength of MSC processed data and based on feature wavelengths modeling analysis. As a result, the MSC–NCA–SVM model performed best and was selected as the best model. Finally, in order to verify the reliability of the selected model, the hyperspectral image was substituted into the MSC–NCA–SVM model and the object-wise method was used to visualize the image classification. The overall classification accuracy of the four types of wheat kernels reached 98.75%, which indicates that the selected model is reliable.

Seeds in the drying process due to improper control of process and temperature often cause heat damage to affect seed vigor. How to quickly and nondestructively identify seeds that are heat-damaged plays a key role in agricultural production. In this study, the electric heating constant temperature blast drying oven was used to simulate the drying process of rice seeds and heated for different time (Untreated, 1 h/60 °C, 3 h/60 °C, 5 h/60 °C, 7 h/60 °C, 9 h/60 °C, 11 h/60 °C). The hyperspectral images of rice seeds with different degrees of heat damage were obtained by using a hyperspectral imaging system of 866.4–1701.0 nm. Three preprocessing methods (Savitzky-Golay first derivative, standard normal variate, and multivariate scatter correction) were used to preprocess the original spectral data, three feature extraction algorithms (second derivative, successive projections algorithm, and neighborhood component analysis) were used to extract the feature wavelengths, and three classifier models (k-nearest neighbor, support vector machine, and naive Bayes) were used for modeling analysis. After multivariate data analysis, the multivariate scatter correction-neighborhood component analysis-naive Bayes model performed best and was selected as the best model. Finally, the hyperspectral images of the verification set were visualized based on the object-wise method to show the intuitive classification effect. The results show that the hyperspectral imaging technology is an effective tool for quickly identifying and visualizing rice seeds with different degrees of heat damage.