Food and Fermentation Industries >

2026 , Vol. 52 >Issue 4: 261 - 270

DOI: https://doi.org/10.13995/j.cnki.11-1802/ts.042706

Quality prediction and geographical indication identification of Koktiyerek grape based on hyperspectral imaging technology

  • CUI Xiwei ,
  • HUANG Kaiwen ,
  • JIANG Tao ,
  • LIU Zhigang ,
  • LIU Yan ,
  • LIU Hai ,
  • YU Hang
Expand
  • 1(Am Incorporation for Metrology and Testing Technology Services, Suzhou 215000, China)
    2(School of Food Science and Technology, Jiangnan University, Wuxi 214122, China)

Received date: 2025-03-14

  Revised date: 2025-07-28

  Online published: 2026-03-17

Fold

Abstract

As a geographical indication product, the quality characteristics of Koktiyerek grapes are closely related to their production environment.To achieve rapid, non-destructive quality evaluation and geographical indication protection, this study utilised hyperspectral imaging technology to develop a multi-task analysis method for predicting the quality of Koketireke grapes and identifying geographical indication products.The study collected hyperspectral data in the 400-1 000 nm from grape samples in the Koketireke geographical indication production area and surrounding non-geographical indication production areas in Xinjiang.Spectral preprocessing was performed using methods such as filtering and smoothing, first-order derivatives, second-order derivatives, baseline calibration, standard normalisation, and multi-spectral scattering correction to optimise data quality.Partial least squares regression was used to select the optimal preprocessing method and construct quality prediction models for soluble solids content (SSC) and total acidity (TA).Among these, baseline correction (BSL) preprocessing yielded the best results.The test set R-square (R2) for the SSC quality prediction model was 0.890 2, with a root mean square error (RMSE) of 0.689 8%, and the test set R2 for the TA quality prediction model was 0.768 9, with a RMSE of 0.105 0%.For the task of identifying geographical indication products, partial least squares discriminant analysis was used to construct a geographical indication product identification model.The model with Savitzky-Golay smoothing (SG) pre-processing performed best, with R2X=0.987, R2Y=0.825, and a model prediction index (Q2) of 0.810, ultimately achieving a discrimination accuracy rate of 95%.This study combined chemometric models with hyperspectral imaging technology to simultaneously achieve quality prediction and geographical indication identification for Koktiyerk grapes, providing an active technical solution for the protection of agricultural product geographical indications and non-destructive quality detection of fruits.

Key words： hyperspectral imaging; geographical indication products; quality prediction; spectral pretreatment; Koktiyerek grapes

Cite this article

CUI Xiwei , HUANG Kaiwen , JIANG Tao , LIU Zhigang , LIU Yan , LIU Hai , YU Hang . Quality prediction and geographical indication identification of Koktiyerek grape based on hyperspectral imaging technology[J]. Food and Fermentation Industries, 2026 , 52(4) : 261 -270 . DOI: 10.13995/j.cnki.11-1802/ts.042706

References

[1] 李记明. 关于葡萄品质的评价指标[J].中外葡萄与葡萄酒, 1999(1):54-57.
LI J M.Evaluation index for grape quality[J].Sino-Overseas Grapevine & Wine, 1999(1):54-57.
[2] 吴清松. 三文鱼产地溯源与品质属性的高光谱成像检测方法研究[D].雅安:四川农业大学, 2024.
WU Q S.Research on hyperspectral imaging detection method for salmon origin traceability and quality attributes[D].Ya′an:Sichuan:Agricultural University, 2024.
[3] 黄琦. 基于高光谱成像技术与机器学习的花生产地溯源与含水率无损检测研究[D].金华:浙江师范大学, 2023.
HUANG Q.Research on hyperspectral imaging technology and machine learning for peanut origin traceability and moisture content nondestructive detection[D].Jinhua:Zhejiang Normal University, 2023.
[4] 董聪颖, 杨天意, 陈谦, 等.高光谱成像技术在苹果品质无损检测中的应用[J].果树学报, 2024, 41(12):2582-2594.
DONG C Y, YANG T Y, CHEN Q, et al.Application of hyperspectral imaging technology in non-destructive detection of apple quality[J].Journal of Fruit Science, 2024, 41(12):2582-2594.
[5] 吴叶兰, 管慧宁, 廉小亲, 等.基于高光谱成像和Att-BiGRU-RNN的柑橘病叶分类[J].农业机械学报, 2023, 54(1):216-223.
WU Y L, GUAN H N, LIAN X Q, et al.Classification of Citrus diseased leaves based on hyperspectral and att-BiGRU-RNN[J].Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(1):216-223.
[6] 吕海涛, 吴文君, 廖声熙, 等.三类云南普洱茶树的地基光谱反射特征及其差异分析[J].茶叶科学, 2021, 41(2):184-192.
LYU H T, WU W J, LIAO S X, et al.Analysis of ground-based spectral reflection characteristics and differences of three types of Yunnan Puer tea[J].Journal of Tea Science, 2021, 41(2):184-192.
[7] 文静, 马雯, 张昂, 等. 高光谱技术在葡萄品质无损检测应用上的研究进展. 食品科学, 2024, 45(21):357-367.
WEN J, MA W, ZHANG A, et al. Research progress on the application of hyperspectral technology for non-destructive testing of grape quality. Food Science, 2024, 45(21):357-367.
[8] 杨杰. 葡萄内部品质的高光谱成像检测研究[D].石河子:石河子大学, 2016.
YANG J.Research on hyperspectral imaging detection of grape internal quality[D].Shihezi:Shihezi University, 2016.
[9] 昝佳睿, 刘翠玲, 凌彩金, 等.基于高光谱技术的红茶茶多酚可视化研究[J].食品安全质量检测学报, 2023, 14(5):37-44.
ZAN J R, LIU C L, LING C J, et al.Study on visualization of black tea polyphenols based on hyperspectral technology[J].Journal of Food Safety & Quality, 2023, 14(5):37-44.
[10] 曾柯宜, 刘禹彤, 张倩, 等.基于多模态融合的玉米种子成熟度的无损检测[J].食品安全质量检测学报, 2025, 16(2):171-177.
ZENG K Y, LIU Y T, ZHANG Q, et al.Non-destructive detection of Zea mays L.seed maturity based on multimodal fusion[J].Journal of Food Safety & Quality, 2025, 16(2):171-177.
[11] XIAO Q L, TANG W T, ZHANG C, et al.Spectral preprocessing combined with deep transfer learning to evaluate chlorophyll content in cotton leaves[J].Plant Phenomics, 2022, 2022:9813841.
[12] 张小超, 吴静珠, 徐云.近红外光谱分析技术及其在现代农业中的应用[M].北京:电子工业出版社, 2012.
ZHANG X C, WU J Z, XU Y.Near-Infrared Spectroscopy Analysis Technology and Its Application in Modern Agriculture[M].Beijing:Publishing House of Electronics Industry, 2012.
[13] 廖少敏. 基于高光谱成像技术的苹果内外品质无损检测的方法研究[D].南昌:华东交通大学, 2024.
LIAO S M.Research on nondestructive detection methods for apple internal and external quality based on hyperspectral imaging technology[D].Nanchang:East China Jiaotong University, 2024.
[14] HUANG Y P, XIONG J, JIANG X S, et al.Assessment of firmness and soluble solids content of peaches by spatially resolved spectroscopy with a spectral difference technique[J].Computers and Electronics in Agriculture, 2022, 200:107212.
[15] 袁伟东, 姜洪喆, 杨诗雨, 等.基于高光谱成像技术的宁夏枸杞产地溯源鉴别[J].食品科学, 2024, 45(6):254-260.
YUAN W D, JIANG H Z, YANG S Y, et al.Geographical origin identification of Lycium barbarum fruit using hyperspectral imaging technology[J].Food Science, 2024, 45(6):254-260.
[16] PEÑUELAS J, FILELLA I.Visible and near-infrared reflectance techniques for diagnosing plant physiological status[J].Trends in plant science, 1998, 3(4):151-156.
[17] XIE C Q, YANG C, HE Y.Hyperspectral imaging for classification of healthy and gray mold diseased tomato leaves with different infection severities[J].Computers and Electronics in Agriculture, 2017, 135:154-162.
[18] 何代弟. 基于深度学习的苹果溯源方法研究[D].阿拉尔市:塔里木大学, 2024.
HE D D.Research on apple traceability method based on deep learning[D].Aral:Tarim University, 2024.
[19] 王昳昀, 马芸芸, 杨冕清, 等.基于高光谱成像技术和自适应增强网络的水蜜桃产地溯源[J].食品安全质量检测学报, 2024, 15(23):77-87.
WANG Y Y, MA Y Y, YANG M Q, et al.Origin tracing of Prunus persica based on hyperspectral imaging technology and adaptive boosting[J].Journal of Food Safety & Quality, 2024,15(23):77-87.
[20] 孙晓荣, 张晨光, 刘翠玲, 等.基于高光谱成像技术的板栗产地溯源[J].食品安全质量检测学报, 2023, 14(18):59-65.
SUN X R, ZHANG C G, LIU C L, et al.Origin tracing of Castanea mollissima based on hyperspectral imaging technology[J].Journal of Food Safety & Quality, 2023, 14(18):59-65.
[21] SEMYALO D, KWON O, WAKHOLI C, et al.Nondestructive online measurement of pineapple maturity and soluble solids content using visible and near-infrared spectral analysis[J].Postharvest Biology and Technology, 2024, 209:112706.
[22] 刘丽, 杨天意, 董聪颖, 等.米良1号猕猴桃贮藏过程中糖酸含量估测模型的构建[J].果树学报, 2025, 42(1):216-226.
LIU L, YANG T Y, DONG C Y, et al.Construction of a sugar and acid content estimation model for Miliang-1 kiwifruit during storage[J].Journal of Fruit Science, 2025,42(1):216-226.
[23] 雷大涛, 罗华平, 高峰, 等. 基于偏振高光谱成像的南疆冬枣品质检测. 食品研究与开发, 2025, 46(2):172-177.
LEI D T, LUO H P, GAO F, et al. Quality detection of winter jujube from south Xinjiang based on polarized hyperspectral imaging. Food Research and Development, 2025, 46(2):172-177.
[24] ZAUKUU J Z, NKANSAH A A, MENSAH E T, et al.Non-destructive authentication of melon seed (Cucumeropsis mannii) powder using a pocket-sized near-infrared (NIR) spectrophotometer with multiple spectral preprocessing[J].Journal of Food Composition and Analysis, 2024, 134:106425.
[25] 刘宝花. 基于高光谱成像技术的鲜食葡萄内部品质无损检测研究[D].济南:山东农业大学, 2020.
LIU B H.Research on nondestructive detection of internal quality of table grapes based on hyperspectral imaging technology[D].Jinan:Shandong Agricultural University, 2020.
[26] 陈慧轩. 高光谱成像技术在枳壳快速识别及其化学成分含量预测的研究[D].镇江:江苏大学, 2022.
CHEN H X.Research on rapid identification of fructus aurantii and prediction of its chemical component contents based on hyperspectral imaging technology[D].Zhengjiang:Jiangsu University, 2022.
[27] JIANG T, ZUO W D, DING J J, et al.Machine learning driven benchtop Vis/NIR spectroscopy for online detection of hybrid Citrus quality[J].Food Research International, 2025, 201:115617.
[28] SALVADOR-REYES R, TERESA PEDROSA SILVA CLERICI M, MARTíNEZ-VILLALUENGA C.Enhancing the nutritional and bioactive benefits of faba bean flour by combining preprocessing and thermoplastic extrusion:A comprehensive study on digestion-resistant peptides[J].Food Research International, 2024, 183:114231.
[29] 禹洁, 周佳, 黄韡, 等. 基于稳定同位素与矿物元素的蜂蜜产地溯源判别模型的构建. 食品安全质量检测学报, 2024, 15(18):84-93.
YU J, ZHOU J, HUANG W, et al. Construction of honey origin traceability discriminant model based on stable isotopes and mineral elements. Journal of Food Safety & Quality, 2024, 15(18):84-93.
Options
Outlines

/

〈 〉

Powered by Beijing Magtech Co. Ltd,.