Calligraphy and Painting Identification 3D-CNN Model Based on Hyperspectral Image MNF Dimensionality Reduction

<div>Out comparison of the convolution layer of the 3D-CNN authenticity identification model. (a) Input layer: first nine channels of MNF images (Qi Baishi’s true painting in the upper figure/Qi Baishi’s fake painting in the following figure). (b) Output feature images of the fourth convolution layer (Qi Baishi’s true painting in the upper figure/Qi Baishi’s fake painting in the following figure).</div>

Computational Intelligence and Neuroscience

fig10

Figure 10

Figure 10: Calligraphy and Painting Identification 3D-CNN Model Based on Hyperspectral Image MNF Dimensionality Reduction 