Chinese character skeleton automatic synthesis method and large-scale Chinese font library automatic generation method

Abstract

The present invention discloses a method for automatically synthesizing Chinese character skeletons and a method for automatically generating large-scale Chinese fonts. Chinese characters are regarded as a sequence of points (that is, writing tracks), and the process is performed by constructing a cyclic neural network model FontRNN with a monotonic attention mechanism. The automatic synthesis of Chinese character skeletons learns and synthesizes other Chinese characters with the same style from a small number of training samples to realize the automatic synthesis of Chinese character skeletons. The present invention can overcome the deficiencies of existing Chinese character synthesis techniques such as fuzzy synthetic Chinese characters, missing strokes, and structural errors, and the model of the present invention can learn how to synthesize thousands of other Chinese characters with the same style from only a few hundred training samples. Therefore, the present invention can greatly reduce the cost of making a large-scale Chinese character library, and has great practical application value.

Description

technical field [0001] The invention relates to a method for automatically synthesizing Chinese character skeletons based on a cyclic neural network and an automatic generation method for a large-scale Chinese character library. The cyclic neural network is used to model a small number of Chinese character trajectories in the form of a sequence, and a large number of Chinese characters of the same style are automatically generated, which belongs to artificial Intelligence, computer graphics processing technology field. Background technique [0002] With the continuous improvement of people's living standards in our country, people's demand for personalized fonts is increasing. However, due to the diversity of Chinese characters, for example, the national standard GB18030-2000 contains 27533 Chinese characters, and even the daily-used national standard GB 2312 contains 6763 Chinese characters, and the structure of Chinese characters is often intricate, so it is necessary to u...

AI Technical Summary

Problems solved by technology

However, the model based on convolutional neural network only pays attention to the image-level features of Chinese characters, and completely ignores the important stroke order information inherent in Chinese characters, so the synthesized Chinese characters will inevitably have problems such as blurring, missing strokes, and structural errors.

Images