This study aims to utilize hyperspectral imaging technology combined with machine learning methods for the authenticity identification and classification of Anoectochilus roxburghii and its counterfeit species. Hyperspectral data were collected from the front and back leaves of nine species of Goldthread and two counterfeit species (Bloodleaf and Spotted-leaf), followed by classification using a variety of machine learning models, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), Linear Discriminant Analysis (LDA), and Convolutional Neural Networks (CNN). The experimental results demonstrated that the SVM model achieved 100% classification accuracy for distinguishing Goldthread from its counterfeit species, effectively capturing the spectral differences between the front and back leaves. In contrast, traditional machine learning models showed varied performance, with SVM proving superior due to its ability to handle high-dimensional feature spaces. The introduction of a multi-view spectral fusion CNN model, which integrates spectral data from both the front and back leaves, further enhanced classification accuracy, achieving a perfect classification rate of 100%. This approach highlights the potential of hyperspectral imaging and machine learning in plant authenticity identification and provides a new perspective for the detection of counterfeit species.

Adulteration detection in medicinal plant powders remains a critical challenge in quality control. In this study, we propose a hyperspectral imaging (HSI)-based method combined with deep learning models to quantitatively analyze adulteration levels in Anoectochilus roxburghii powder. After preprocessing the spectral data using raw, first-order, and second-order Savitzky–Golay derivatives, we systematically evaluated the performance of traditional machine learning models (Random Forest, Support Vector Regression, Partial Least Squares Regression) and deep learning architectures. While traditional models achieved reasonable accuracy (R² up to 0.885), their performance was limited by feature extraction and generalization ability. A single-channel convolutional neural network (CNN) utilizing individual spectral representations improved performance marginally (maximum R² = 0.882), but still failed to fully capture the multi-scale spectral features. To overcome this, we developed a multi-channel CNN that simultaneously integrates raw, SG-1, and SG-2 spectra, effectively leveraging complementary spectral information. This architecture achieved a significantly higher prediction accuracy (R² = 0.964, MSE = 0.005), demonstrating superior robustness and generalization. The findings highlight the potential of multi-channel deep learning models in enhancing quantitative adulteration detection and ensuring the authenticity of herbal products.

Hyperspectral imaging has emerged as a powerful tool for food quality assessment, yet most existing methods rely on supervised classification and require prior knowledge of adulterant categories. This study applies a non-targeted screening approach based on a deep spectral autoencoder to detect adulterants in Fritillaria. While autoencoder-based anomaly detection has been established in other hyperspectral domains, its application to congeneric species discrimination and exogenous adulterant screening in Fritillaria has not been systematically explored. A deep spectral autoencoder was constructed and trained exclusively on pure samples to learn the intrinsic spectral distribution of authentic materials. During inference, reconstruction error was used as an anomaly score, and samples deviating from the learned spectral manifold were identified as suspicious. Spectral data augmentation and band trimming were applied to enhance model robustness, while the anomaly threshold was determined solely from the distribution of pure samples. The proposed method achieved strong discrimination performance, with an area under the receiver operating characteristic curve (AUC) of 0.9903 and high detection rates across multiple adulterant types. Typical exogenous adulterants such as starch and talc powder were completely detected, while congeneric species also showed high detection sensitivity despite their spectral similarity to authentic samples. Latent space visualization and residual spectral analysis further revealed clear separation patterns and interpretable spectral deviations. These results demonstrate the proof-of-concept viability of the proposed non-targeted framework for open-set screening of adulteration risks. However, the authentic samples used for training originated from a single source, and only a limited set of anomaly types was tested. Therefore, the current model should be regarded as an early proof-of-concept only, not as a ready-to-deploy screening tool. Further validation with diverse authentic samples and a wider range of adulterants under realistic variability is necessary before the method can be considered a practical strategy for quality control.

Quercetin, a key flavonoid in Anoectochilus roxburghii (Wall.) Lindl., plays an important role in determining the pharmacological value of this medicinal herb. However, traditional methods for quercetin quantification are destructive and time-consuming, limiting their application in real-time quality monitoring. This study investigates the hyperspectral response characteristics of quercetin using near-infrared hyperspectral imaging and establishes a feature-based model to explore its detectability in A. roxburghii leaves. We scanned standard quercetin solutions of known concentration under the same imaging conditions as the leaves to produce a dilution series. Feature-selection methods used included the successive projections algorithm (SPA), Pearson correlation, and competitive adaptive reweighted sampling (CARS). A 1D convolutional neural network (1D-CNN) trained on SPA-selected wavelengths yielded the best prediction performance. These key wavelengths—particularly the 923 nm band—showed strong theoretical and statistical relevance to quercetin’s molecular absorption. When applied to plant leaf spectra, the standard-trained model produced continuous predicted quercetin values that effectively distinguished cultivars with varying flavonoid contents. PCA visualization and ROC-based classification confirmed spectral transferability and potential for functional evaluation. This study demonstrates a non-destructive, spatially resolved, and biochemically interpretable strategy for identifying bioactive markers in plant tissues, offering a methodological basis for future hyperspectral inversion studies and intelligent quality assessment in herbal medicine.