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.