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

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.