Title
Median filtering detection of small-size image based on CNN.
Abstract
•A new CNN model named MFNet is proposed to detect median filtering.•Magnifying the test images can enlarge the differences between the original image and its median filtered version.•The mlpconv layer is used to enhance the nonlinear modeling ability of the network.•The proposed method performs well for highly compressed image of size as small as 16 × 16.
Year
DOI
Venue
2018
10.1016/j.jvcir.2018.01.011
Journal of Visual Communication and Image Representation
Keywords
Field
DocType
Median filtering forensics,CNN,Nearest neighbor interpolation
Nearest-neighbor interpolation,Computer vision,Median filter,Pattern recognition,Image based,Preprocessor,Nonlinear classification,Artificial intelligence,Mathematics,Network structure
Journal
Volume
ISSN
Citations 
51
1047-3203
7
PageRank 
References 
Authors
0.54
14
4
Name
Order
Citations
PageRank
Hongshen Tang170.54
Rongrong Ni271853.52
Yao Zhao31926219.11
Xiaolong Li42264114.79