Jade Identification Using Ultraviolet Spectroscopy Based on the SpectraViT Model Incorporating CNN and Transformer
Source abstract
Abstract
Jade is a highly valuable and diverse gemstone, and its spectral characteristics can be used to identify its quality and type. We propose a jade ultraviolet (UV) spectrum recognition model based on deep learning, called SpectraViT, aiming to improve the accuracy and efficiency of jade identification. The algorithm combines residual modules to extract local features and transformers to capture global dependencies of jade’s UV spectrum, and finally classifying jade using fully connected layers. Experiments were conducted on a UV spectrum dataset containing four types of jade (natural diamond, cultivated diamond (CVD/HPHT), and moissanite). The results show that the algorithm can effectively identify different types of jade, achieving an accuracy of 99.24%, surpassing traditional algorithms based on Support Vector Machines (SVM) and Partial Least Squares Discriminant Analysis (PLS_DA), as well as other deep learning methods. This paper also provides a reference solution for other spectral analysis problems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Geochemistry and Geologic Mapping · Mineralogy and Gemology Studies · Cultural Heritage Materials Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen 518060, China
Funding
National Natural Science Foundation of China
References (31)
Show source-provided references
1. Overview of Gemstones
2. Recent advances of chemometric calibration methods in modern spectroscopy: Algorithms, strategy, and related issues10.1016/j.trac.2022.116648 ↗
3. (2023). Gems Testing—Ultraviolet-Visible Absorbtion Spectroscopy (Standard No. GB/T 42645-2023).
4. Song, G., Wu, J., Jian, H., Li, J., and Liu, L. (2013, January 27–30). Rapid Detection Technology for Gems and Jewelry Based on Ultraviolet-Visible Reflection Spectroscopy. Proceedings of the the 2013 Proceedings of the China Jewelry and Ornament Academic Exchange Conference, NGTC, Wuhan, China.
5. The evolution of chemometrics10.1016/S0003-2670(03)00944-9 ↗
6. Dadon, A., Mandelmilch, M., Ben-Dor, E., and Sheffer, E. (2019). Sequential PCA-based Classification of Mediterranean Forest Plants using Airborne Hyperspectral Remote Sensing. Remote Sens., 11.10.3390/rs11232800 ↗
7. Determination of microplastics by FTIR spectroscopy based on quaternion parallel feature fusion and support vector machine10.1016/j.chemolab.2023.105018 ↗
8. Spectral classification analysis of recycling plastics of small household appliances based on infrared spectroscopy10.1016/j.vibspec.2023.103636 ↗
9. Deep learning for vibrational spectral analysis: Recent progress and a practical guide10.1016/j.aca.2019.06.012 ↗
10. Using deep learning to predict soil properties from regional spectral data10.1016/j.geodrs.2018.e00198 ↗
11. SpectraTr: A novel deep learning model for qualitative analysis of drug spectroscopy based on transformer structure10.1142/S1793545822500213 ↗
12. Deep learning methods for oral cancer detection using Raman spectroscopy10.1016/j.vibspec.2023.103522 ↗
13. Convolutional neural networks for vibrational spectroscopic data analysis10.1016/j.aca.2016.12.010 ↗
14. DeepSpectra: An end-to-end deep learning approach for quantitative spectral analysis10.1016/j.aca.2019.01.002 ↗
15. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
16. Comparison of linear and nonlinear calibration models based on near infrared (NIR) spectroscopy data for gasoline properties prediction10.1016/j.chemolab.2007.04.006 ↗
17. Investigation into maize seed disease identification based on deep learning and multi-source spectral information fusion techniques10.1016/j.jfca.2023.105254 ↗
18. Geographical discrimination of Asian red pepper powders using 1H NMR spectroscopy and deep learning-based convolution neural networks10.1016/j.foodchem.2023.138082 ↗
19. (2021). Fast detection of cumin and fennel using NIR spectroscopy combined with deep learning algorithms. Optik, 242, 167080.10.1016/j.ijleo.2021.167080 ↗
20. Wu, Y., Zhu, X., Huang, Q., Zhang, Y., Evans, J., and He, S. (2023). Predicting the Quality of Tangerines Using the GCNN-LSTM-AT Network Based on Vis–NIR Spectroscopy. Appl. Sci., 13.10.3390/app13148221 ↗
21. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L.U., and Polosukhin, I. (2017, January 4–9). Attention is All you Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
22. Sun, J., Xie, J., and Zhou, H. (2021, January 10–12). EEG Classification with Transformer-Based Models. Proceedings of the 2021 IEEE 3rd Global Conference on Life Sciences and Technologies (LifeTech), Kyoto, Japan.10.1109/LifeTech52111.2021.9391844 ↗
23. A Novel Algorithmic Structure of EEG Channel Attention Combined with Swin Transformer for Motor Patterns Classification10.1109/TNSRE.2023.3297654 ↗
24. Zeynali, M., Seyedarabi, H., and Afrouzian, R. (2023). Classification of EEG signals using Transformer based deep learning and ensemble models. Biomed. Signal Process. Control, 86.10.1016/j.bspc.2023.105130 ↗
25. A lightweight CNN-transformer model for learning traveling salesman problems10.1007/s10489-024-05603-x ↗
26. EEG-based seizure prediction via Transformer guided CNN10.1016/j.measurement.2022.111948 ↗
27. Cubic-spline interpolation. 110.1109/5289.911175 ↗
28. Zhao, Y., Zhang, X., Feng, W., and Xu, J. (2022). Deep Learning Classification by ResNet-18 Based on the Real Spectral Dataset from Multispectral Remote Sensing Images. Remote Sens., 14.10.3390/rs14194883 ↗
29. Sinha, D., and El-Sharkawy, M. (2019, January 10–12). Thin MobileNet: An Enhanced MobileNet Architecture. Proceedings of the 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), New York, NY, USA.10.1109/UEMCON47517.2019.8993089 ↗
30. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning10.1016/j.neunet.2017.12.012 ↗
31. Shu, H., Tang, H., Zhang, H., and Zheng, W. (2019). Data for: Spectra Data Classification with Kernel Extreme Learning. Mendeley Date V1.