BiSID-5k: A Bimodal Image Dataset for Seed Classification from the Visible and Near-Infrared Spectrum

The success of deep learning in image classification has been largely underpinned by large-scale datasets, such as ImageNet, which have significantly advanced multi-class classification for RGB and grayscale images. However, datasets that capture spectral information beyond the visible spectrum remain scarce, despite their high potential, especially in agriculture, medicine, and remote sensing. To address this gap in the agricultural domain, we present BiSID-5k, a thoroughly curated bimodal seed image dataset comprising paired RGB and hyperspectral images for 10 plant species, making it one of the largest bimodal seed datasets available. We describe the methodology for data collection and preprocessing and benchmark several deep learning models on the dataset to evaluate their multi-class classification performance. By contributing a high-quality dataset, BiSID-5k offers a valuable resource for studying spectral, spatial, and morphological properties of seeds, opening new avenues for research and applications.

深度学习在图像分类领域的成功，很大程度上依托于大规模数据集（如ImageNet），这些数据集极大推动了RGB图像与灰度图像的多分类任务发展。然而，能够捕捉可见光波段以外光谱信息的数据集依然稀缺，尽管其在农业、医学与遥感等领域拥有极高应用潜力。为填补农业领域的这一研究空白，我们推出了BiSID-5k——一款经过全面精心整理的双模态（bimodal）种子图像数据集，包含10种植物的配对RGB图像与高光谱（hyperspectral）图像，是目前已公开的规模最大的双模态种子数据集之一。我们详细阐述了该数据集的采集与预处理流程，并在该数据集上对多款深度学习模型开展基准测试，以评估它们的多分类性能。通过贡献这一高质量数据集，BiSID-5k为研究种子的光谱、空间与形态学特性提供了宝贵资源，为相关研究与应用开辟了全新方向。

搜集汇总

背景与挑战

背景概述

BiSID-5k是一个双模态图像数据集，用于可见光和近红外光谱下的种子分类，包含约996.73 GB的数据文件。该数据集由多位研究者合作完成，由莱比锡大学发布，可通过特定URI和DOI访问。