Font style migration and transformation method based on Manchu character pictures

Abstract

The font style transfer transformation method based on Manchu character images belongs to the field of image processing, and solves the problem of greatly reducing the time and labor costs spent on processing a large number of Manchu character images. The key point is to train the Manchu font style transfer model step by step: Using the Manchu character training data set to train the model to learn Manchu characters; using the Manchu font style transfer data set to retrain the model to realize Manchu font style transfer learning, the effect is to save a lot of time and labor costs.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a method for processing Manchu font styles. Background technique [0002] Most of the existing styles of Manchu fonts are transformed by inputting Manchu characters into text editing software according to Roman transliteration, and then using various existing Manchu fonts to transform them. It takes a high time cost to read and write, and the operator needs to have a certain ability to identify Manchu, and Manchu, as an endangered language, has a very limited number of people who can read, write, and identify Manchu. Therefore, training a highly versatile generative adversarial network model to transfer the font style of Manchu characters from the image level can save a lot of time and labor costs. Contents of the invention [0003] The present invention mainly implements a generative confrontation network model capable of learning the transfer process between Manchu font style...

AI Technical Summary

Problems solved by technology

[0002] Most of the existing styles of Manchu fonts are transformed by inputting Manchu characters into text editing software according to Roman transliteration, and then using various existing Manchu fonts to transform them. It takes a lot of time to read and write, and the operator needs to have a certain ability to identify Manchu, and Manchu, as an endangered language, has a very limited number of people who can read, write, and identify Manchu.

Images