Mechanical-harvest Soybean Images Dataset

Soybean is the world's main grain and oil crop. The crushing rate and impurity rate are important indicators for measuring the quality of mechanized soybean harvesting. The online monitoring of soybean crushing rate and impurity rate based on deep learning has become a current research hotspot. This dataset is a set of soybean sample images derived from the mechanized harvesting process. This dataset can be used for training, validation, and testing of deep learning models. The dataset provides 40 original soybean sample images. In order to enrich the dataset, the original images were enhanced by scaling, rotating, flipping, filtering, and adding noise, expanding to 800 images. This dataset stores various parts of data in the VOC2007 dataset format. The folder size of the dataset is 328MB.