Yunle Ding, Huiqin Wang, Ke Wang, Zhan Wang, Gang Zhen. Three dimensional-CNN Classification Method of Mural Multispectral Image Pigments Based on Multiscale Feature Fusion[J]. Laser & Optoelectronics Progress, 2022, 59(22): 2230001
- Laser & Optoelectronics Progress
- Vol. 59, Issue 22, 2230001 (2022)
Fig. 1. Schematic diagrams of 2D-CNN and 3D-CNN. (a) 2D-CNN; (b) 3D-CNN
Fig. 2. Residual learning
Fig. 3. Schematic diagrams of atrous convolution kernel. (a) r=1; (b) r=2; (c) r=3
Fig. 4. Sserial hole convolution module
Fig. 5. Multiscale feature fusion module
Fig. 6. Schematic of MFAC-Res3D-CNN
Fig. 7. Multispectral image acquisition system of murals
Fig. 8. Multispectral images of murals in each band
Fig. 9. Simulated mural. (a) Simulated mural image; (b) pseudo color image; (c) truth image
Fig. 10. Comparison of different network classification results. (a) Truth image; (b) SVM; (c) 2D-CNN; (d) Res-3D-CNN; (e) MFAC-Res3D-CNN
Fig. 11. Comparison of different network classification details. (a) Truth image; (b) SVM;(c) 2D-CNN; (d) Res-3D-CNN; (e) MFAC-Res3D-CNN
|
Table 1. Sample of multispectral image dataset of simulated murals
|
Table 2. Classification confusion matrix of article model
|
Table 3. Comparison of dataset classification accuracy results
|
Table 4. Comparison of training and testing time of different algorithms
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20