Infrared and Laser Engineering, Volume. 49, Issue 10, 20200221(2020)
Raman mineral recognition method based on all-optical diffraction deep neural network
Fig. 1. Part of the spectrum data in dataset
Fig. 2. Network structure diagram
Fig. 3. Data preprocessing
Fig. 4. Detection area in the result image and identification area of different labels
Fig. 5. Structure diagram of optical diffractive neural network classification system
Fig. 6. Structure diagram of grating group
Fig. 7. Grating height discretization
Fig. 8. Two etching to achieve four steps
Fig. 9. Partial diagram of diffraction grating model
Fig. 10. Accuracy and error curve of train set
Fig. 11. Accuracy curve of train set and test set
Fig. 12. Confusion matrix of test results
Fig. 13. Height distribution of each layer of grating and the output image of each layer of grating after training. (a1)-(a6) Gratings; (b1)-(b6) Output of gratings; (c1)-(c3) Recognition
|
Get Citation
Copy Citation Text
Xu Zhang, Mingxin Yu, Lianqing Zhu, Yanlin He, Guangkai Sun. Raman mineral recognition method based on all-optical diffraction deep neural network[J]. Infrared and Laser Engineering, 2020, 49(10): 20200221
Category: Photoelectric measurement
Received: Apr. 10, 2020
Accepted: --
Published Online: Jul. 6, 2021
The Author Email: