In situ nondestructive identification of citrus fruit ripeness via hyperspectral imaging technology

Abstract Rapid and accurate assessment of the citrus ripening stage in the field is important for determining harvest timing and improving industrial economic efficiency; however, the lack of effective nondestructive detection methods in the current orchard leads to flaws in ripening stage assessmen...

Full description

Saved in:
Bibliographic Details
Main Authors: Qi Wang, Jinzhu Lu, Yuanhong Wang, Fajun Miao, Senping Liu, Qiyang Shui, Junfeng Gao, Yingwang Gao
Format: Article
Language:English
Published: BMC 2025-06-01
Series:Plant Methods
Subjects:
Online Access:https://doi.org/10.1186/s13007-025-01354-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434336751779840
author Qi Wang
Jinzhu Lu
Yuanhong Wang
Fajun Miao
Senping Liu
Qiyang Shui
Junfeng Gao
Yingwang Gao
author_facet Qi Wang
Jinzhu Lu
Yuanhong Wang
Fajun Miao
Senping Liu
Qiyang Shui
Junfeng Gao
Yingwang Gao
author_sort Qi Wang
collection DOAJ
description Abstract Rapid and accurate assessment of the citrus ripening stage in the field is important for determining harvest timing and improving industrial economic efficiency; however, the lack of effective nondestructive detection methods in the current orchard leads to flaws in ripening stage assessment, which affects harvesting decisions. To solve this problem, this study utilized hyperspectral technology to collect data from 22 fruit trees in an orchard (in the range of 400–1000 nm) and explored the effectiveness of five regions of interest selection methods (x-axis, y-axis, four-quadrant, threshold segmentation, and raw) for the delineation of the citrus ripening stage. The data quality was enhanced via wavelet transform (WT)-multiple scattering correction (MSC) preprocessing, and the effective wavelengths were extracted via the successive projections algorithm (SPA). On the basis of these wavelengths, backpropagation neural network (BP) and convolutional neural network (CNN) models were built for maturity prediction. The results show that the x-axis region of interest selection method outperforms the other methods, and the SPA-BP model based on this method performs best. An accuracy of 99.19% for the correction set and 100% for the prediction set was achieved when only 0.03% of the wavelength was used. This groundbreaking study highlights the significant potential of hyperspectral technology for in situ assessment of citrus ripening stages. Furthermore, it offers crucial technical support and serves as a valuable reference for the advancement of precision agriculture.
format Article
id doaj-art-2a90ead1df104fc7b823e363647d56dd
institution Kabale University
issn 1746-4811
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series Plant Methods
spelling doaj-art-2a90ead1df104fc7b823e363647d56dd2025-08-20T03:26:43ZengBMCPlant Methods1746-48112025-06-0121111310.1186/s13007-025-01354-zIn situ nondestructive identification of citrus fruit ripeness via hyperspectral imaging technologyQi Wang0Jinzhu Lu1Yuanhong Wang2Fajun Miao3Senping Liu4Qiyang Shui5Junfeng Gao6Yingwang Gao7Modern Agricultural Equipment Research Institute, Xihua UniversitySchool of Mechanical Engineering, Xihua UniversityModern Agricultural Equipment Research Institute, Xihua UniversityModern Agricultural Equipment Research Institute, Xihua UniversityModern Agricultural Equipment Research Institute, Xihua UniversityModern Agricultural Equipment Research Institute, Xihua UniversityDepartment of Computer Science, University of AberdeenUK Agri-Tech CentreAbstract Rapid and accurate assessment of the citrus ripening stage in the field is important for determining harvest timing and improving industrial economic efficiency; however, the lack of effective nondestructive detection methods in the current orchard leads to flaws in ripening stage assessment, which affects harvesting decisions. To solve this problem, this study utilized hyperspectral technology to collect data from 22 fruit trees in an orchard (in the range of 400–1000 nm) and explored the effectiveness of five regions of interest selection methods (x-axis, y-axis, four-quadrant, threshold segmentation, and raw) for the delineation of the citrus ripening stage. The data quality was enhanced via wavelet transform (WT)-multiple scattering correction (MSC) preprocessing, and the effective wavelengths were extracted via the successive projections algorithm (SPA). On the basis of these wavelengths, backpropagation neural network (BP) and convolutional neural network (CNN) models were built for maturity prediction. The results show that the x-axis region of interest selection method outperforms the other methods, and the SPA-BP model based on this method performs best. An accuracy of 99.19% for the correction set and 100% for the prediction set was achieved when only 0.03% of the wavelength was used. This groundbreaking study highlights the significant potential of hyperspectral technology for in situ assessment of citrus ripening stages. Furthermore, it offers crucial technical support and serves as a valuable reference for the advancement of precision agriculture.https://doi.org/10.1186/s13007-025-01354-z‘Shiranui’ mandarinHyperspectralRegion of interestRipening stageSuccessive projections algorithm
spellingShingle Qi Wang
Jinzhu Lu
Yuanhong Wang
Fajun Miao
Senping Liu
Qiyang Shui
Junfeng Gao
Yingwang Gao
In situ nondestructive identification of citrus fruit ripeness via hyperspectral imaging technology
Plant Methods
‘Shiranui’ mandarin
Hyperspectral
Region of interest
Ripening stage
Successive projections algorithm
title In situ nondestructive identification of citrus fruit ripeness via hyperspectral imaging technology
title_full In situ nondestructive identification of citrus fruit ripeness via hyperspectral imaging technology
title_fullStr In situ nondestructive identification of citrus fruit ripeness via hyperspectral imaging technology
title_full_unstemmed In situ nondestructive identification of citrus fruit ripeness via hyperspectral imaging technology
title_short In situ nondestructive identification of citrus fruit ripeness via hyperspectral imaging technology
title_sort in situ nondestructive identification of citrus fruit ripeness via hyperspectral imaging technology
topic ‘Shiranui’ mandarin
Hyperspectral
Region of interest
Ripening stage
Successive projections algorithm
url https://doi.org/10.1186/s13007-025-01354-z
work_keys_str_mv AT qiwang insitunondestructiveidentificationofcitrusfruitripenessviahyperspectralimagingtechnology
AT jinzhulu insitunondestructiveidentificationofcitrusfruitripenessviahyperspectralimagingtechnology
AT yuanhongwang insitunondestructiveidentificationofcitrusfruitripenessviahyperspectralimagingtechnology
AT fajunmiao insitunondestructiveidentificationofcitrusfruitripenessviahyperspectralimagingtechnology
AT senpingliu insitunondestructiveidentificationofcitrusfruitripenessviahyperspectralimagingtechnology
AT qiyangshui insitunondestructiveidentificationofcitrusfruitripenessviahyperspectralimagingtechnology
AT junfenggao insitunondestructiveidentificationofcitrusfruitripenessviahyperspectralimagingtechnology
AT yingwanggao insitunondestructiveidentificationofcitrusfruitripenessviahyperspectralimagingtechnology