跳到主要导航 跳到搜索 跳到主要内容

Fake Generated Painting Detection Via Frequency Analysis

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

With the development of deep neural networks, digital fake paintings can be generated by various style transfer algorithms. To detect the fake generated paintings, we analyze the fake generated and real paintings in Fourier frequency domain and observe statistical differences and artifacts. Based on our observations, we propose Fake Generated Painting Detection via Frequency Analysis (FGPD-FA) by extracting three types of features in frequency domain. Besides, we also propose a digital fake painting detection database for assessing the proposed method. Experimental results demonstrate the excellence of the proposed method in different testing conditions.

源语言英语
主期刊名2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
出版商IEEE Computer Society
1256-1260
页数5
ISBN(电子版)9781728163956
DOI
出版状态已出版 - 10月 2020
活动2020 IEEE International Conference on Image Processing, ICIP 2020 - Virtual, Abu Dhabi, 阿拉伯联合酋长国
期限: 25 9月 202028 9月 2020

出版系列

姓名Proceedings - International Conference on Image Processing, ICIP
2020-October
ISSN(印刷版)1522-4880

会议

会议2020 IEEE International Conference on Image Processing, ICIP 2020
国家/地区阿拉伯联合酋长国
Virtual, Abu Dhabi
时期25/09/2028/09/20

指纹

探究 'Fake Generated Painting Detection Via Frequency Analysis' 的科研主题。它们共同构成独一无二的指纹。

引用此