Detecting Source Video Artifacts with Supervised Sparse Filters

A variety of powerful picture quality predictors are available that rely on neuro-statistical models of distortion perception. We extend these principles to video source inspection, by coupling spatial divisive normalization with a filterbank tuned for artifact detection, implemented in an augmented sparse functional form. We call this method the Video Impairment Detection by SParse Error CapTure (VIDSPECT). We configure VIDSPECT to create state-of-the-art detectors of two kinds of commonly encountered source video artifacts: upscaling and combing. The system detects upscaling, identifies upscaling type, and predicts the native video resolution. It also detects combing artifacts arising from interlacing. Our approach is simple, highly generalizable, and yields better accuracy than competing methods. A software release of VIDSPECT is available online: http://live.ece.utexas.edu/research/quality/VIDSPECT release.zip for public use and evaluation.

[1]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[2]  David M. Baylon.  On the Detection of Temporal Field Order in Interlaced Video Data , 2007, 2007 IEEE International Conference on Image Processing.

[3]  Babak Mahdian,et al.  Ieee Transactions on Information Forensics and Security 1 Blind Authentication Using Periodic Properties of Interpolation , 2022 .

[4]  David Vazquez-Padin,et al.  Prefilter design for forensic resampling estimation , 2011, 2011 IEEE International Workshop on Information Forensics and Security.

[5]  Alan C. Bovik,et al.  Making a “Completely Blind” Image Quality Analyzer , 2013, IEEE Signal Processing Letters.

[6]  Manish Pindoria,et al.  Automatic Interlace or Progressive Video Discrimination , 2012 .

[7]  Eero P. Simoncelli,et al.  Natural image statistics and neural representation. , 2001, Annual review of neuroscience.

[8]  Kim Steenstrup Pedersen,et al.  Detecting Interlaced or Progressive Source of Video , 2005, 2005 IEEE 7th Workshop on Multimedia Signal Processing.

[9]  David Vazquez-Padin,et al.  An SVD approach to forensic image resampling detection , 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

[10]  Anne Aaron,et al.  Native Resolution Detection of Video Sequences , 2015 .

[11]  Guillermo Sapiro,et al.  Supervised Dictionary Learning , 2008, NIPS.

[12]  Andrew C. Gallagher.  Detection of linear and cubic interpolation in JPEG compressed images , 2005, The 2nd Canadian Conference on Computer and Robot Vision (CRV'05).

[13]  Alan C. Bovik,et al.  Automatic Prediction of Perceptual Image and Video Quality , 2013, Proceedings of the IEEE.

[14]  Matthias Kirchner,et al.  Spectral methods to determine the exact scaling factor of resampled digital images , 2012, 2012 5th International Symposium on Communications, Control and Signal Processing.

[15]  Lei Zhang,et al.  A Feature-Enriched Completely Blind Image Quality Evaluator , 2015, IEEE Transactions on Image Processing.

[16]  Alan C. Bovik,et al.  A Two-Step Framework for Constructing Blind Image Quality Indices , 2010, IEEE Signal Processing Letters.

[17]  Hany Farid,et al.  Exposing digital forgeries by detecting traces of resampling , 2005 .

[18]  Alan C. Bovik,et al.  Blind Picture Upscaling Ratio Prediction , 2016, IEEE Signal Processing Letters.

[19]  Heung-Kyu Lee,et al.  Estimation of linear transformation by analyzing the periodicity of interpolation , 2014, Pattern Recognit. Lett..

[20]  Matthias Kirchner,et al.  Fast and reliable resampling detection by spectral analysis of fixed linear predictor residue , 2008, MM&Sec '08.

[21]  Ingemar J. Cox,et al.  Normalized Energy Density-Based Forensic Detection of Resampled Images , 2012, IEEE Transactions on Multimedia.

[22]  D. Ruderman.  The statistics of natural images , 1994 .

[23]  Alan C. Bovik,et al.  No-Reference Image Quality Assessment in the Spatial Domain , 2012, IEEE Transactions on Image Processing.

[24]  S. Prasad,et al.  On Resampling Detection and its Application to Detect Image Tampering , 2006, 2006 IEEE International Conference on Multimedia and Expo.