性格(数学)
修补
计算机科学
人工智能
图像(数学)
GSM演进的增强数据速率
领域(数学)
过程(计算)
对抗制
图像复原
深度学习
生成对抗网络
模式识别(心理学)
生成语法
计算机视觉
图像处理
数学
操作系统
纯数学
几何学
出处
期刊:2020 International Conference on Culture-oriented Science & Technology (ICCST)
日期:2020-10-01
被引量:1
标识
DOI:10.1109/iccst50977.2020.00032
摘要
Image inpainting technology plays an important role in the process of digitalizing ancient literature. It helps to recover the partially missing or stained characters. Recently the Generative Adversarial Network (GAN) has shown remarkable success in the field of image inpainting. In this paper, we propose a new GAN model using the idea of edge recovery and optimize this model with spatial attenuation mask and conditional labelling to improve performance. Experiments show better results than the previous works in character image inpainting.
科研通智能强力驱动
Strongly Powered by AbleSci AI