Median Filtering Forensics Scheme for Color Images Based on Quaternion Magnitude-Phase CNN  

作　　者：Jinwei Wang Yang Zhang 

机构地区：[1]Nanjing University of Information Science&Technology,School of Computer and Software,Nanjing,210044,China

出　　处：《Computers, Materials & Continua》2020年第1期99-112,共14页计算机、材料和连续体（英文）

基　　金：The work was supported in part by the Natural Science Foundation of China under Grants(Nos.61772281,61502241,61272421,61232016,61402235 and 61572258);in part by the Natural Science Foundation of Jiangsu Province,China under Grant BK20141006;in part by the Natural Science Foundation of the Universities in Jiangsu Province under Grant 14KJB520024;the PAPD fund and the CICAEET fund.

摘　　要：In the paper,a convolutional neural network based on quaternion transformation is proposed to detect median filtering for color images.Compared with conventional convolutional neural network,color images can be processed in a holistic manner in the proposed scheme,which makes full use of the correlation between RGB channels.And due to the use of convolutional neural network,it can effectively avoid the one-sidedness of artificial features.Experimental results have shown the scheme’s improvement over the state-of-the-art scheme on the accuracy of color image median filtering detection.

关 键 词：Quaternion transform convolutional neural network median filtering forensics color image 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]