您好，欢迎访问福建省农业科学院 机构知识库！
福建省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Effective Identification of Variety and Origin of Chenpi Using Hyperspectral Imaging Assisted with Chemometric Models

文献类型： 外文期刊

作者： Liu, Hangxiu 1 ; Wang, Youyou 1 ; Wang, Yiheng 1 ; Wang, Jingyi 1 ; Hu, Hanqing 6 ; Zhong, Xinyi 1 ; Yuan, Qingjun 2 ; Yang, Jian 1 ;

作者机构： 1.China Acad Chinese Med Sci, Natl Resource Ctr Chinese Mat Med, State Key Lab Qual Ensurance & Sustainable Use Dao, Beijing 100700, Peoples R China

2.China Acad Chinese Med Sci, Inst Tradit Chinese Med Hlth Ind, Jiangxi Prov Key Lab Sustainable Utilizat Tradit C, Nanchang 330115, Peoples R China

3.China Acad Chinese Med Sci, Dexing Res & Training Ctr Chinese Med Sci, Dexing 334213, Peoples R China

4.Jiangxi Hlth Ind Inst Tradit Chinese Med, Nanchang 330115, Peoples R China

5.Res Ctr Qual Evaluat Dao di Herbs, Nanchang 330000, Peoples R China

6.Fujian Acad Agr Sci, Fruit Res Inst, Fuzhou 350013, Peoples R China

关键词： Chenpi; variety and origin; rapid identification; hyperspectral imaging; machine learning

期刊名称：FOODS （ 影响因子：5.1； 五年影响因子：5.6 ）

ISSN：

年卷期： 2025 年 14 卷 11 期

页码：

收录情况： SCI

摘要： Geographical origins and varietal characteristics can significantly affect the quality of Citri Reticulatae Pericarpium (Chenpi), making rapid and accurate identification essential for consumer protection. To overcome the inefficiency and high cost of conventional detection methods, this study proposed a nondestructive approach that integrates hyperspectral imaging (HSI) with deep learning to classify Chenpi varieties and their geographical origins. Hyperspectral data were collected from 15 Chenpi varieties (citrus peel) across 13 major production regions in China using three dataset configurations: exocarp-facing-upward (Z), endocarp-facing-upward (F), and a fused dataset combining random orientations (ZF). Convolutional neural networks (CNNs) were developed and compared with conventional machine learning models, including partial least-squares discriminant analysis (PLS-DA), support vector machines (SVMs), and a multilayer perceptron (MLP). The CNN model achieved 96.39% accuracy for varietal classification with the ZF dataset, while the Z-PLSDA model optimized with second derivative (D2) preprocessing and competitive adaptive reweighted sampling (CARS) feature selection attained 91.67% accuracy in geographical origin discrimination. Feature wavelength selection strategies, such as CARS, simplified the model complexity while maintaining a classification performance comparable to that of the full-spectrum models. These findings demonstrated that HSI combined with deep learning could provide a rapid, nondestructive, and cost-effective solution for Chenpi quality assessment and origin traceability.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：福建省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台