Lin Wei, Fu Youhao, Xu Peiquan, Liu Shuo, Ma Daoyi, Jiang Zitian, Zang Siyang, Yao Heyang, Su Qin
Nanjing Agricultural University, Nanjing, China.
Jiangsu University of Science and Technology, Zhenjiang, China.
Data Brief. 2023 Jun 7;48:109300. doi: 10.1016/j.dib.2023.109300. eCollection 2023 Jun.
This paper presents a dataset with images of individual soybean seeds, which encompass : . Furthermore, Those images of individual soybeans were classified into five categories based on the Standard of Soybean Classification () [1]. The soybean images with the seeds in physical touch were captured by an industrial camera. Subsequently, individual soybean images (227227 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.
本文展示了一个包含单个大豆种子图像的数据集，其中包括： 。此外，那些单个大豆的图像根据大豆分类标准（）[1]被分为五类。有物理接触种子的大豆图像由工业相机拍摄。随后，使用分割精度超过98%的图像处理算法从大豆图像（3072×2048像素）中分割出单个大豆图像（227×227像素）。该数据集可用于研究大豆种子的分类或质量评估。
