Soybean Seeds

The dataset includes five-type of individual soybean seed images, totaling 5513: intact, spotted, immature, broken, and skin-damaged. Furthermore, there are over 1000 images of soybean seeds in each category. Those images of individual soybeans were classified into five categories based on the Standard of Soybean Classification (GB1352-2009). The soybean images with the seeds in physical touch were captured by an industrial camera. Subsequently, individual soybean images (227×227 pixels) were divided from the soybean images (3072×2048 pixels) using an image-processing algorithm with a segmentation accuracy of over 98%. The dataset can serve to study the classification or quality assessment of soybean seeds.