Corn seed dataset based on hyperspectral and RGB images

TL;DR

This paper introduces a dataset of corn seeds using hyperspectral and RGB images for phenotypic analysis and machine learning applications.

Contribution

The paper presents a new multimodal corn seed dataset with hyperspectral and RGB images for agricultural research.

Findings

The dataset includes 2400 corn seed samples across 12 varieties under controlled lab conditions.

Preprocessing steps ensured data quality for classification and phenotypic analysis.

The dataset supports precision agriculture and machine learning research.

Abstract

This study employed an HY-6010-S hyperspectral imaging system, covering a spectral range of 400–1000 nm, combined with an RGB industrial camera to acquire multimodal data. The dataset simulates phenotypic analysis scenarios of maize seeds under controlled laboratory conditions, with the ambient temperature maintained at 20–25°C. Comprehensive testing was conducted using 12 different maize varieties. Approximately 200 seed samples were collected per variety, resulting in a total sample size of about 2400, each subjected to hyperspectral and RGB image acquisition. Preprocessing steps included noise reduction, background removal, band selection, and modality alignment. To ensure the accuracy and reliability of the experimental data, HHIT software and Python were utilized for data processing. This dataset plays a significant role in seed variety classification, phenotypic analysis, precision agriculture, and machine learning applications.

Figures