Tea Category Identification Using Wavelet Signal Reconstruction of Hyperspectral Imagery and Machine Learning

Abstract

Accurately distinguishing the types of tea is of great significance to the pricing, production, and processing of tea. The similarity of the internal spectral characteristics and appearance characteristics of different types of tea greatly limits further research on tea identification. However, wavelet transform can simultaneously extract time domain and frequency domain features, which is a powerful tool in the field of image signal processing. To address this gap, a method for tea recognition based on a lightweight convolutional neural network and support vector machine (L-CNN-SVM) was proposed, aiming to realize tea recognition using wavelet feature figures generated by wavelet time-frequency signal decomposition and reconstruction. Firstly, the redundant discrete wavelet transform was used to decompose the wavelet components of the hyperspectral images of the three teas (black tea, green tea, and yellow tea), which were used to construct the datasets. Secondly, improve the lightweight CNN model to generate a tea recognition model. Finally, compare and evaluate the recognition results of different models. The results demonstrated that the results of tea recognition based on the L-CNN-SVM method outperformed MobileNet v2+RF, MobileNet v2+KNN, MobileNet v2+AdaBoost, AlexNet, and MobileNet v2. For the recognition results of the three teas using reconstruction of wavelet components LL + HL + LH, the overall accuracy rate reached 98.7%, which was 4.7%, 3.4%, 1.4%, and 2.0% higher than that of LH + HL + HH, LL + HH + HH, LL + LL + HH, and LL + LL + LL. This research can provide new inspiration and technical support for grade and quality assessment of cross-category tea.

Estimating Leaf Nitrogen Content in Wheat Using Multimodal Features Extracted from Canopy Spectra

“…Second, the obtained features are optimized using different methods (including random forest and correlation analysis methods), aiming to improve the prediction accuracy of the model. Finally, the prediction models of nitrogen content in the wheat leaves were constructed by using the optimal characteristics, including support vector regression (SVR), partial least squares regression (PLSR), and the particle swarm optimization-support vector regression (PSO-SVR) model, which were evaluated using coefficient of determination (R 2 ), root mean squared error (RMSE), and mean absolute error (MAE) [56,57]. The specific steps of this study are as follows: First, the spectral data of the wheat canopy were obtained and the band features, spectral features, and convolution features were further extracted.…”

Hyperspectral image construction in different spectral bands of tea leafs for identifying the tea type using O-ConvNet-RF model

“…The beverage commonly referred to as tea, which is scientifically identified as Camellia Sinensis, is widely consumed and has been acknowledged for its medicinal and health-promoting properties. In recent years, there has been an upward trend in global tea production [1], [2]. The production of tea encompasses a range of tea varieties derived from distinct tea plant species and subjected to various processing techniques, resulting in a wide array of quality criteria.…”

The Effects of Rock Zones and Tea Tree Varieties on the Growth and Quality of Wuyi Rock Tea Based on the OPLS-DA Model and Machine Learning

“…Machine learning plays an important role in the classification and determination of unknown samples and is often used to discriminate between samples of unknown origins [11]. Simulation by machine learning can objectively categorize tea samples and determine the differences in tea quality and origin more accurately [12,13]. Therefore, it has been widely used in the classification and determination of unknown samples.…”