Some interesting method like style transfer, GAN, deep neural networks for Chinese character and calligraphic image processing

1. Classification for 30 different Fonts

Dataset: Extract code: lqp2

Part of the dataset

Fonts classification by GoogLeNet

Loss Test accuracy Confusion matrix

Feature visualizing

2. Style transfer for calligraphic image

Content image dataset:

Style fusion


The method of this application, we just simply use pix2pix to generate another style of Chinese character.

Dataset: extract code: 2vku

3. Calligraphic image denoising

4. Chinese character inpainting


These great calligraphy works are written by my teacher Prof. Zhang.


  1. Mingtao Guo 2. Xinran Wen


[1]. Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9.

[2]. Dumoulin V, Shlens J, Kudlur M. A learned representation for artistic style[J]. Proc. of ICLR, 2017, 2.

[3]. Isola P, Zhu J Y, Zhou T, et al. Image-to-image translation with conditional adversarial networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1125-1134.

[4]. Johnson J, Alahi A, Fei-Fei L. Perceptual losses for real-time style transfer and super-resolution[C]//European conference on computer vision. Springer, Cham, 2016: 694-711.

Code reference

[1]. Style transfer for calligraphic image:

[2]. zi2zi:

[3]. Calligraphic image denoising: