Generation of Stylized Calligraphic Image Based on Generative Adversarial Network

WANG Xiao-hong, LU Hui, MA Xiang-cai

Packaging Engineering ›› 2020 ›› Issue (11) : 246-253.

PDF(2276 KB)
PDF(2276 KB)
Packaging Engineering ›› 2020 ›› Issue (11) : 246-253. DOI: 10.19554/j.cnki.1001-3563.2020.11.036

Generation of Stylized Calligraphic Image Based on Generative Adversarial Network

  • WANG Xiao-hong1, LU Hui2, MA Xiang-cai2
Author information +
History +

Abstract

The work aims to propose a method of extracting calligraphic image features and automatically generating stylized calligraphic image. Firstly, the variational auto-encoder was used to extract shape information of the character for the grayscale image of calligraphic works. At the same time, the calligraphic image was converted into the Lab color space and the stylistic feature was extracted through 4-layers convolutional neural network in L channel. Then, the stylistic feature was input to generator as conditions. Finally, the stylistic feature and shape information were used for joint training in generative adversarial network, which could generate Chinese characters with specific style. In addition, Calligraphy Character Generation Dataset (CCGD-2019) which contained several types of calligraphy character was constructed for model training in the process of experiment. A calligraphic character image generation model based on variational auto-encoding and generative adversarial network was proposed, which could automatically generate stylized calligraphic character images from standard characters or random noise. The results of subjective evaluation and Fréchet Inception Distance indicate that the recognition rate and the visual effect of generated characters reach the satisfactory effects.

Cite this article

Download Citations
WANG Xiao-hong, LU Hui, MA Xiang-cai. Generation of Stylized Calligraphic Image Based on Generative Adversarial Network[J]. Packaging Engineering. 2020(11): 246-253 https://doi.org/10.19554/j.cnki.1001-3563.2020.11.036
PDF(2276 KB)

Accesses

Citation

Detail

Sections
Recommended

/