Chinese character font migration system based on adversarial networks

Abstract

The invention provides a Chinese character font migration system based on adversarial networks. The system includes: a Chinese character migration module, which maps source fonts into generation target fonts, of which contents are the same as contents of the source fonts but the fonts are different, through a fully convolutional neural network, and a discriminator module, which utilizes a deep neural network-based discriminator network to carry out true / false font discrimination on the generation target fonts and real target fonts, namely gold standards, corresponding thereto, and constantly optimizes a Chinese character migration network by virtue of thinking of adversarial network training to enable the same to output more realistic generation target fonts. On the basis of the adversarial networks, the system can migrate a Chinese character of any printed font to another printed font, or even to a font corresponding to a handwriting font of a certain person.

Description

technical field [0001] The invention relates to the fields of computer vision and image processing, in particular to a Chinese character font migration system based on an adversarial network. Background technique [0002] As we all know, there are more than 7,000 Chinese characters, and 3,755 commonly used Chinese characters. To design a font, the designer needs to design every Chinese character under the font, and to design a calligrapher font also requires the calligrapher to write almost all the commonly used Chinese characters. Therefore, the design of Chinese character fonts is a very time-consuming and arduous task. To explore a more efficient design method: that is, how to only manually design some Chinese characters in a certain font, and automatically generate the remaining Chinese characters in this font, has great potential. practical significance. [0003] In recent years, deep learning (Deep Learning), which is characterized by deep neural networks, has been w...

AI Technical Summary

Problems solved by technology

For Chinese characters with many strokes and complex structure, it is difficult to properly decompose them, and for Chinese characters with few strokes, such decomposition is unnecessary, so these will directly affect the result of subsequent target font generation

Secondly, the preprocessing of the method based on Chinese character decomposition is very time-consuming, and there is a lot of prior knowledge since the decomposition process

Images