7 × 227 pixels) from the soybean images (3072×2048 pixels). Finally, the individual soybean images were saved in JPG format. Data source location Nanjing Agricultural University, Nanjing, China Data accessibility Repository name: Soybean Seeds Data identification number: https://doi.org/10.17632/v6vzvfszj6.6 Direct URL to data: https://data.mendeley.com/datasets/v6vzvfszj6 Instructions for accessing these data: Download the data from Soybean Seeds repository in ZIP formats. Value of the Data • The soybean image dataset can meet the practical requirement of assessing soybean quality. Because those individual soybean images in our dataset were classified based on the Standard of Soybean Classi
Open resource ↗10.17632/v6vzvfszj6.6 · lines:1-64Unverified paper record
Soybean image dataset for classification.
Data in brief · 7 Jun 2023 · 10.1016/j.dib.2023.109300
Abstract
This paper presents a dataset with 5513 images of individual soybean seeds, which encompass five categories : (Ⅰ) Intact, (Ⅱ) Immature, (Ⅲ) Skin-damaged, (Ⅳ) Spotted, and (Ⅴ) Broken . 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 ) [1]. 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.
Plant phenotyping relevance
大豆種子の画像データセットを構築し、画像分割アルゴリズムと品質カテゴリ分類を提示しており、植物器官の状態・品質を画像から抽出する方法が中心です。
abstractThis paper presents a dataset with 5513 images of individual soybean seeds
abstractindividual 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%.
abstractThe dataset can serve to study the classification or quality assessment of soybean seeds.
Code and data availability
The paper is a data descriptor for a public soybean seed image dataset (5513 images, five quality classes) deposited in Mendeley Data, with explicit direct URL and DOI, directly reproducing the paper's phenotyping measurements.
This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.