Chinese character font generation method based on conditional generative adversarial network

Abstract

The invention discloses a Chinese character font generation method based on a conditional generative adversarial network, which is characterized by comprising the following steps of: 1, preparing fontdata; 2, constructing a generative adversarial network by adopting an encoder and decoder structure as a generator and a convolutional neural network as a discriminator; 3, training the generative adversarial network by using the standard font picture and the target font picture data set to obtain a trained adversarial generative network, and storing parameters after training; 4, sequentially inputting the complete standard fonts into the trained generator of the adversarial generation network, and inputting corresponding complete target fonts by the trained generator of the adversarial generation network; and 5, constructing a model rating system, and rating font generation quality of the model. According to the method, the generative adversarial network is trained through a small numberof target fonts, and the complete standard fonts are generated into other residual target font pictures, so that a complete target font library file is obtained.

Description

technical field [0001] The invention relates to a method for generating Chinese character fonts, in particular to a method for generating Chinese character fonts against a network based on conditions. Background technique [0002] With the development of economy and society, people will come into contact with more and more fonts in their daily life, but most of these fonts are designed by professional teams. The design of fonts is a very time-consuming work, and only contains 26 The English font library of each letter is different. The commonly used character set GB2312 is composed of 6763 Chinese characters. In addition, due to the complex structure and various shapes of Chinese characters, it also increases the difficulty of making the Chinese font library. At present, the production of Chinese fonts mostly depends on manual experience and design. Even if a professional font designer designs a complete set of fonts, it will take 2-3 years. The degree of automation is very ...

AI Technical Summary

Problems solved by technology

However, the effect of this method to generate fonts is not good, and the user needs to provide a large number of target fonts

Images