Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

A sample of the data set and its contents.

More »

Fig 1 Expand

Fig 2.

The VGG16 network can be used as the architecture of the feature extraction network.

More »

Fig 2 Expand

Table 1.

Performance of three networks combined with Siamese networks.

More »

Table 1 Expand

Fig 3.

The two images are compared against each other.

More »

Fig 3 Expand

Fig 4.

The architecture of the Siamese network.

More »

Fig 4 Expand

Table 2.

Experimental results of data augmentation accuracy.

More »

Table 2 Expand

Fig 5.

The Siamese network with the VGG16 network as the backbone feature extraction network predicts the evolution rules flow of Chinese characters.

More »

Fig 5 Expand

Fig 6.

After feature extraction by the VGG16 network, a multi-dimensional feature is obtained and its similarity is measured.

More »

Fig 6 Expand

Fig 7.

The accuracy rate of our training set.

More »

Fig 7 Expand

Fig 8.

Detailed examples are given for four evolutionary rules.

More »

Fig 8 Expand

Table 3.

The similarity of Chinese characters corresponds to the 4 evolution rules respectively.

More »

Table 3 Expand

Fig 9.

Accuracy between adjacent periods.

More »

Fig 9 Expand