On-site rapid detection of aging of Pericarpium Citri Reticulatae using multispectral imaging

Abstract

Pericarpium Citri Reticulatae is a traditional Chinese medicine with high medicinal value, and its storage age has a great impact on its ethno-pharmaceutical relevance. At present, there is a situation in the market place where Pericarpium Citri Reticulatae with short storage age is fraudulently sold as Pericarpium Citri Reticulatae with long storage age, and some unaged orange peels dyed with tea are sold as Pericarpium Citri Reticulatae at a high price. In this study, a rapid, on-site method for identifying the storage age of Xinhui Pericarpium Citri Reticulatae based on spectral imaging technology was described. The image features and spectral features were extracted respectively from the surface reflection spectral images of Pericarpium Citri Reticulatae, and a machine learning model was established to identify the storage age. This study explored the classification effect of the combination of different spectral pre-processing methods and machine learning models, and finally selected the combination of standard normal variate (SNV) and random forest (RF) models, to achieve 95% accuracy on the test dataset, showing excellent generalization performance. The result shows that the spectral imaging technology can rapidly identify the storage age of Xinhui Pericarpium Citri Reticulatae in real time, which has a great application prospect in the detection of the properties of medicinal materials.