Guideline for Non‐Destructive Testing of Agricultural Product Quality Using Spectral Imaging Technology
Year: 2025
Type: article
Abstract: ABSTRACT This research guide focuses on the application of spectral imaging technology in the detection of fruit and vegetable quality, and expounds its core advantages as a non‐destructive technology for detecting fruit and vegetable quality. The technology mainly integrates spectroscopy and imaging technology to obtain a three‐dimensional data cube containing spatial and spectral information, so as to achieve precise detection of fruit and vegetable surface damage, sugar content, hardness, pesticide residue, nutritional components and internal defects. Existing research data show that the accuracy of hyperspectral imaging (HSI) and near‐infrared spectroscopy (NIRS) related technologies in apple bruise detection exceeds 90%; the prediction error of watermelon sugar content is ≤ 0.72 Brix; and the classification accuracy of pesticide residues in Gannan navel oranges is higher than 85%. The advantages of spectral imaging technology in detecting fruit and vegetable quality are reflected in its non‐destructiveness, which can effectively avoid destructive sampling; it can realize high‐throughput detection; and it has multi‐parameter analysis capability, which can simultaneously detect soluble solids content (SSC), acidity, hardness and other indicators in fruits and vegetables. This guide introduces the specific operation process of spectral imaging technology for detecting fruit and vegetable quality, mainly covering the selection of detection equipment, data collection and preprocessing, feature extraction and model establishment. This guide will provide scientific and efficient technical solutions and insights for modern agricultural quality detection.
DOI: 10.1002/agf2.70000
Authors: Jiangao Qiu, Xirui Zhang, Jie Guo, Jianbo Xiao, Lina Zhang, Shaohua Fu, Ruiwu Xu, Chao Cao
Language: English
Subfield: Analytical Chemistry
Field: Chemistry
Domain: Physical Sciences
SDG: Zero hunger
Open Access status: hybrid
Funder: Hainan University
OpenAlex ID: W4415120875
