Automatic generation method for handwritten Chinese font library based on deep neutral network

Abstract

The invention discloses an automatic generation method for a handwritten Chinese font library based on a deep neutral network. The method is characterized in that font characteristics are reconstructed through a small number of handwritten Chinese characters; a font style migration network is established; and font style characteristics of font forms not handwritten by a user are estimated throughthe font style migration network, font form contents of a reference font are combined with a handwriting style of the user to achieve migration to a target handwriting style, and target font form pictures are generated, so that the complete handwritten Chinese font library is obtained. The method provided by the invention has the advantages that the method is an end-to-end generation method, and high-quality Chinese font forms are generated without extraction of strokes or components of Chinese characters or manual intervention, so that the handwritten font library creation efficiency is greatly improved, the generation of a personalized font library becomes simple and convenient, the requirement of ordinary people for the personalized handwritten font library can be met, and the development progress of the personalized font library can be accelerated.

Description

technical field [0001] The invention relates to computer graphics processing technology and artificial intelligence technology, in particular to a method for automatically generating a handwritten Chinese character library based on a deep neural network. Background technique [0002] With the rapid development of the mobile Internet, people's desire to pursue beauty and personalization is becoming stronger and stronger. Although the standard fonts such as KaiTi and SongTi are convenient to use, they lack individuality. The popularity of social media such as Weibo, WeChat and QQ has made young people want to use their own handwriting to express their individuality. At the same time, more and more calligraphy lovers hope to use their own personalized handwriting to write electronic documents on electronic mobile devices such as computers and mobile phones, and communicate with each other, so as to achieve the effect of "seeing characters as if seeing people". In addition, pe...

AI Technical Summary

Problems solved by technology

The "Rewrite" method described in the literature (YuchenTian.2016.Rewrite:Neural Style Transfer For Chinese Fonts.(2016).RetrievedNov 23,2016from https: / / github.com / kaonashi-tyc / Rewrite) designs a trickle-like network structure, can generate relatively standard fonts, but users need to write thousands of Chinese characters, and the generation effect is not good for the situation where the writing is scribbled and the style of the reference font is greatly different

Literature (Zhouhui Lian, Bo Zhao, and Jianguo Xiao.2016.Automatic generation of largescale handwriting fonts viastyle learning.In Proc.SIGGRAPH ASIA 2016TB.ACM,12.) generates a complete Chinese font library by modeling the writing style, but this method requires Automatic extraction of strokes or parts in advance

The zi2zi method described in the literature (YuchenTian.2017.zi2zi: Master Chinese Calligraphy with Conditional AdversarialNetworks.(2017). Retrieved Jun 3, 2017from https: / / github.com / kaonashi-tyc / zi2zi) is based on conditional generation against the network and U- net structure, using the method of confrontation training to synthesize Chinese character pictures of a specific style, but it still has blurred and false edges, and the quality of the generated glyphs is not high, which cannot meet the needs of practical applications

Images