Identification of soybean varieties based on hyperspectral imaging technology and one‐dimensional convolutional neural network

Abstract Variety identification of seeds is essential to ensure the purity and yield of the variety. A model based on hyperspectral imaging technology and one‐dimensional convolutional neural network (1D CNN) was proposed to distinguish soybean seed varieties in this article. A total of 3,600 soybean seeds (900 seeds per variety) of hyperspectral images in the spectral range of 866.4–1,701.0 nm were collected. Traditional machine learning models (k‐nearest neighbor, support vector machines, partial least squares discriminant analysis) and 1D CNN model were established based on different numbers of sample sets. The 1D CNN model was the most stable and had the highest classification accuracy, higher than 98%. Fivefold cross validation was used to evaluate the model, and the model achieved an accuracy of more than 95% in both the training set and the validation set. Finally, the t‐distributed stochastic neighbor embedding was used to visualize the feature values extracted by 1D CNN. The research results demonstrated that the 1D CNN model maintained good classification performance in soybean seed classification and had good application prospects in hyperspectral imaging technology. Practical Applications Variety identification of soybean seeds is essential to ensure the purity and yield of the variety. Different soybean varieties have different genetic purity, physical purity, germination ability and vigor, which are related to quality attributes, such as nutritional value, stress resistance, and final yield. In the past, most soybeans were identified using traditional machine learning algorithms combined with near‐infrared hyperspectral imaging technology to build models. This requires a series of operations, such as smoothing preprocessing and dimensionality reduction on hyperspectral data. These steps are too cumbersome and are not conducive to online hyperspectral monitoring systems. The results of this study show that it is feasible to use one‐dimensional convolutional neural network combined with hyperspectral technology to identify soybean seeds, and it also provides a new idea for building an online detection system in the future.