A rapid and nondestructive method is greatly important for the classification of aflatoxin B1 (AFB1) concentration of single maize kernel to satisfy the ever-growing needs of consumers for food safety. A novel method for classification of AFB1 concentration of single maize kernel was developed on the basis of the near-infrared (NIR) hyperspectral imaging (1100–2000 nm). Four groups of AFB1 samples with different concentrations (10, 20, 50, and 100 ppb) and one group of control samples were prepared, which were preprocessed with Savitzky–Golay (SG) smoothing and first derivative (FD) algorithms for their raw NIR spectra. A key wavelength selection method, combining the variance and order of average spectral intensity, was proposed on the basis of pretreated spectra. Moreover, principal component analysis (PCA) was conducted to reduce the dimensionality of hyperspectral data. Finally, a classification model for AFB1 concentrations was developed through linear discriminant analysis (LDA), combined with five key wavelengths and the first three PCs. The results show that the proposed method achieved an ideal performance for classifying AFB1 concentrations in a single maize kernel with overall accuracy, with an F1-score and Kappa values of 95.56%, 0.9554, and 0.9444, respectively, as well as the test accuracy yield of 88.67% for independent validation samples. The combinations of variance and order of average spectral intensity can be used for key wavelength selection which, combined with PCA, can achieve an ideal dimensionality reduction effect for model development. The findings of this study have positive significance for the classification of AFB1 concentration of maize kernels.

The viability of Zea mays seed plays a critical role in determining the yield of corn. Therefore, developing a fast and non-destructive method is essential for rapid and large-scale seed viability detection and is of great significance for agriculture, breeding, and germplasm preservation. In this study, hyperspectral imaging (HSI) technology was used to obtain images and spectral information of maize seeds with different aging stages. To reduce data input and improve model detection speed while obtaining more stable prediction results, successive projections algorithm (SPA) was used to extract key wavelengths that characterize seed viability, then key wavelength images of maize seed were divided into small blocks with 5 pixels ×5 pixels and fed into a multi-scale 3D convolutional neural network (3DCNN) for further optimizing the discrimination possibility of single-seed viability. The final discriminant result of single-seed viability was determined by comprehensively evaluating the result of all small blocks belonging to the same seed with the voting algorithm. The results showed that the multi-scale 3DCNN model achieved an accuracy of 90.67% for the discrimination of single-seed viability on the test set. Furthermore, an effort to reduce labor and avoid the misclassification caused by human subjective factors, a YOLOv7 model and a Mask R-CNN model were constructed respectively for germination judgment and bud length detection in this study, the result showed that mean average precision (mAP) of YOLOv7 model could reach 99.7%, and the determination coefficient of Mask R-CNN model was 0.98. Overall, this study provided a feasible solution for detecting maize seed viability using HSI technology and multi-scale 3DCNN, which was crucial for large-scale screening of viable seeds. This study provided theoretical support for improving planting quality and crop yield.

Maize is susceptible to mold infection during growth and storage due to its large embryo and high moisture content. Therefore, it is essential to distinguish the moldy sample from healthy groups to prevent the spread of mold and avoid huger economic losses. Catalase is a metabolite in the growth of microorganisms; hence, all maize samples were accurately divided into four moldy grades (health, mild, moderate, and severe levels) by determining their catalase activity. The visible and shortwave near-infrared (Vis-SWNIR) and longwave near-infrared (LWNIR) hyperspectral images were investigated to jointly identify the moldy levels of maize. Spectra and texture information of each maize sample were extracted and used to build the classification models of maize with different moldy levels in pixel-level fusion and feature-level fusion. The result showed that the feature-level fusion of spectral and texture within Vis-SWNIR and LWNIR regions achieved the best results, overall prediction accuracy reached 95.00% for each moldy level, all healthy maize was correctly classified, and none of the moldy samples were misclassified as healthy level. This study illustrated that two hyperspectral image systems, with complementary spectral ranges, combined with feature selection and data fusion strategies, could be used synergistically to improve the classification accuracy of maize with different moldy levels.