Median Filtering Forensics in Compressed Video

Median filtering has received extensive attention from forensics analyzers, as a common content-preserving, smoothing, and denoising manipulation. We propose a detection scheme for median filtering of video sequences in compressed domain based on the singular value decomposition of the process matrix, which approximates the median filtering. Projection over some of the eigenspaces of the process matrix gives a set of features of small dimension, even as small as three, making the proposed scheme a fast and suitable detector for video median filtering. The experimental evaluations show that the proposed method outperforms the state-of-the-art detectors of median filtering, and its edge becomes significant for localized detection over small blocks within frames. The new method can potentially be used as a detector of other editing processes.

• Publication year

  2019

• Venue

  IEEE Signal Processing Letters

• Publication date

  2019-02-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/LSP.2018.2889921
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Detecting median filtering via two-dimensional AR models of multiple filtered residuals

  2018cited by this paper
• Robust median filtering detection based on local difference descriptor

  2017influential reference
• A Deterministic Approach to Detect Median Filtering in 1D Data

  2016cited by this paper
• Median Filtering Forensics Based on Convolutional Neural Networks

  2015cited by this paper
• Median Filtered Image Quality Enhancement and Anti-Forensics via Variational Deconvolution

  2015cited by this paper
• Countering anti-forensics of median filtering

  2014cited by this paper
• Linear Algebra and Matrix Analysis for Statistics

  2014cited by this paper
• Revealing the Traces of Median Filtering Using High-Order Local Ternary Patterns

  2014influential reference
• Information Forensics: An Overview of the First Decade

  2013cited by this paper
• Anti-forensics of median filtering

  2013cited by this paper
• Blind Detection of Median Filtering in Digital Images: A Difference Domain Based Approach

  2013cited by this paper
• Robust Median Filtering Forensics Using an Autoregressive Model

  2013cited by this paper
• LIBSVM: A library for support vector machines

  2011cited by this paper
• Blind Forensics of Median Filtering in Digital Images

  2011influential reference
• Generalized RBF feature maps for Efficient Detection

  2010cited by this paper
• On detection of median filtering in digital images

  2010influential reference
• Steganalysis by Subtractive Pixel Adjacency Matrix

  2009cited by this paper
• On the Early History of the Singular Value Decomposition

  1993cited by this paper
• Streaking in median filtered images

  1987cited by this paper

• Floc image-driven deep learning enhanced by temporal windows and transformers for carbon emission reduction in drinking water treatment plants.

  2025cites this paper
• Image recognition enhances efficient monitoring of the coagulation-settling in drinking water treatment plants

  2024cites this paper
• Neural noiseprint transfer: a generic noiseprint-based counter forensics framework

  2023cites this paper
• Dilemma and Solution of Copyright Justice System for Health Short Video under Network Big Data Environment Monitoring

  2022cites this paper
• Sector Entry Flow Prediction Based on Graph Convolutional Networks

  2022cites this paper
• Crack Extraction for Polycrystalline Solar Panels

  2021cites this paper
• A No-Reference Quality Metric for Parameter Tuning of Edge-Aware Filters – An Anti-Image Forensic Method

  2020cites this paper
• Removing the Traces of Median Filtering via Unsharp Masking as an Anti-forensic Approach in Medical Imaging

  2019cites this paper