Font generation method and device based on multi-task discriminator generative adversarial network

Abstract

The invention discloses a font generation method and device based on a multi-task discriminator generative adversarial network, and the method comprises the steps: taking a font image created by a user as a style image, inputting the style image into a generative adversarial network obtained through pre-training, and obtaining a font library, wherein the training process of the generative adversarial network comprises the following steps: taking a training sample and a sample style image as input of a generator, and obtaining a target image output by the generator; inputting the target image and the sample font image into a first discriminator, and adjusting a loss function of the first discriminator by taking the difference between the font content of the target image and the font content of the sample font image as a training target; and inputting the target image and the sample style image into a second discriminator, and adjusting a loss function of the second discriminator by taking a difference between a font style of the target image and a font style of the sample style image as a training target. By means of the scheme, the error rate of font generation can be reduced under the condition that it is guaranteed that the fonts do not deviate from the font styles.

Description

technical field [0001] The present application relates to the field of font creation, and in particular to a font generation method and device based on a multi-task discriminator generation confrontation network. Background technique [0002] Text is the main carrier of information dissemination. Now, with the continuous improvement of my country's informatization, the majority of Internet users have further expanded their demand for information processing. Based on the writing work of Chinese characters, pleasing fonts can often promote the author's creativity. However, the creation of fonts is a very complicated process. First, the creator needs to design several Chinese characters, and then expand to all Chinese characters, and it is necessary to keep all Chinese characters in the same style. Because the quantity of Chinese characters is very huge, so making a font library of complete Chinese characters will bring very huge workload to the creator. [0003] At present, ...

AI Technical Summary

Problems solved by technology

[0005] 2. The font style of the generated font is not strong enough and deviates from the font style created by the creator

Images