期刊论文

Zhao, Huihuang(happyday.huihuang@gmail.com)

英文

Computers & Electrical Engineering

0045-7906

2021

95

107338

10.1016/j.compeleceng.2021.107338

This work is supported by National Natural Science Foundation of China (No. 61772179 ), the Hunan Provincial Natural Science Foundation of China (No. 2019JJ40005, 2020JJ4152), Scientific Research Fund of Hunan Provincial Education Department (No. 18A333). the Double First-Class University Project of Hunan Province (No. Xiangjiaotong [2018]469), Postgraduate Research and Innovation Projects of Hunan Province (No. Xiangjiaotong [2019]248-998), the science and technology innovation Program of Hunan Province (No.2016TP1020), Hengyang guided science and technology projects and Application-oriented Special Disciplines (No. Hengkefa [2018]60-31), Postgraduate Scientific Research Innovation Project of Hunan Province(CX20190998), Degree & Postgraduate Education Reform Project of Hunan Province (2019JGYB266,2020JGZD072), Industry University Research Innovation Foundation of Ministry of Education Science and Technology Development Center (2020QT09), Hengyang technology innovation guidance projects(Hengcaijiaozhi [2020]-67), Postgraduate Teaching Platform Project of Hunan Province(Xiangjiaotong [2019]370-321). We also thank Gatys et al. [9] , Goodfellow et al. [19] , Wang et al. [13] and Zhu et al. [14] for sharing their codes, and NVIDIA for the GPU donation.

本校为第一机构

A novel method for generating color portraits from sketch images using the edge constraint algorithm and generative adversarial networks (GANs) is proposed in this paper. In converting sketches into color portraits, the details of portrait output by GANs are often blurred and unrealistic. A new method with edge constraint is proposed in this work to address this issue. The image generated from generator network and its edge generated from the followed edge network are combined and provided to the discriminator for authenticity identification. E...