期刊
CMC-COMPUTERS MATERIALS & CONTINUA
卷 65, 期 1, 页码 929-943出版社
TECH SCIENCE PRESS
DOI: 10.32604/cmc.2020.06569
关键词
Median filtering forensics; quaternion convolution layer; quaternion pooling layer; color image
资金
- Natural Science Foundation of China [61702235, 61772281, U1636219, U1636117, 61502241, 61272421, 61232016, 61402235, 61572258]
- National Key R\&D Program of China [2016YFB0801303, 2016QY 01W0105]
- plan for Scientific Talent of Henan Province [2018JR0018]
- Natural Science Foundation of Jiangsu Province, China [BK20141006]
- Natural Science Foundation of the Universities in Jiangsu Province [14KJB520024]
- PAPD fund
- CICAEET fund
Median filtering is a nonlinear signal processing technique and has an advantage in the field of image anti-forensics. Therefore, more attention has been paid to the forensics research of median filtering. In this paper, a median filtering forensics method based on quaternion convolutional neural network (QCNN) is proposed. The median filtering residuals (MFR) are used to preprocess the images. Then the output of MFR is expanded to four channels and used as the input of QCNN. In QCNN, quaternion convolution is designed that can better mix the information of different channels than traditional methods. The quaternion pooling layer is designed to evaluate the result of quaternion convolution. QCNN is proposed to features well combine the three-channel information of color image and fully extract forensics features. Experiments show that the proposed method has higher accuracy and shorter training time than the traditional convolutional neural network with the same convolution depth.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据