Exposing video forgeries by detecting MPEG double compression

Sun, Tanfeng; Wang, Wan; Jiang, Xinghao

doi:10.1109/icassp.2012.6288150

Cited by 64 publications

(44 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Fig.5 (a) shows an example of how to mark PU types in one image. We mark 4 5 (b) shows the horizontal frequency matrix of Fig.5 (a), where r, c denote the PU types of the PU-type pair; the number in each cell means the times of the PUtype pair occurs with the interval =1 d in horizontal direction. Once the frequency matrix is achieved, we can calculate the 4 4 u probability co-occurrence matrix of it in horizon, vertical, major diagonal and minor diagonal according to Eq.…”

Section: The Extraction Of Cmoputsmentioning

confidence: 99%

“…Ref [3] introduced the sequence of average residual of Pframes (SARP) and used its time-and frequency-domain features to classify the tampered videos and original videos. Sun and Xu in [4][5] detected double compression for MPEG videos by studying the distribution of quantized DCT coefficients. In Ref [6], a method based on the statistical feature of macroblock mode (MBM) which consists of macroblock type and motion vector in P-frames was proposed to detect double MPEG compression.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, Ref [1,[4][5][6][7][8][9] studied the double compression for MPEG videos and ref [2][3] aims at H.264 videos. As the latest generation of coding standards, HEVC provides lower video data rate.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Double HEVC Compression Detection with Different Bitrates Based on Co-occurrence Matrix of PU Types and DCT Coefficients

Jia

Zhang

et al. 2017

ITM Web Conf.

View full text Add to dashboard Cite

Abstract. Detection of double video compression is of particular importance in video forensics, as it reveals partly the video processing history. In this paper, a double compression method is proposed for HEVC-the latest video coding standard. Firstly, four 5×5 co-occurrence matrixes were derived from DCT coefficients along four directions respectively, i.e., horizontal, vertical, main diagonal and minor diagonal. Then four 4×4 co-occurrence matrixes were derived from PU types which are innovative features of HEVC and rarely been utilized by researchers. Finally, these two feature set are combined and sent to support vector machine (SVM) to detect re-compressed videos. In order to reduce the feature dimension, only the co-occurrence matrixes of DCT coefficients and PU types in horizontal direction are adopted to identify whether the video has undergone double compression. Experimental results show the effectiveness and the robustness against frame deletion of the proposed scheme.

show abstract

Section: The Extraction Of Cmoputsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Double HEVC Compression Detection with Different Bitrates Based on Co-occurrence Matrix of PU Types and DCT Coefficients

Jia

Zhang

et al. 2017

ITM Web Conf.

View full text Add to dashboard Cite

show abstract

“…Some methods propose to use noise characteristics [5] to detect possible forgeries. Other works try to detect proofs of the evidence of a double compression [6,7]. Wang and Farid [8] proposed a method to detect duplicated frames used to remove people or objects from a video.…”

Section: State Of the Artmentioning

confidence: 99%

A Tool to Support the Creation of Datasets of Tampered Videos

Ardizzone

Mazzola

2015

Image Analysis and Processing — ICIAP 2015

View full text Add to dashboard Cite

Abstract. Digital Video Forensics is getting a growing interest from the Multimedia research community, as the need for methods to validate the authenticity of a video content is increasing with the number of videos freely available to the digital users. Unlike Digital Image Forensics, to our knowledge, there are not standard datasets to test video forgery detection techniques. In this paper we present a new tool to support the users in creating datasets of tampered videos. We furthermore present our own dataset and we discuss some remarks about how to create forgeries difficult to be detected by an observer, to the naked eye.

show abstract

“…Su and Xu detect double compression by studying the distribution of quantized DCT coefficients for MPEG video in [1,2]. By judging whether the probability distribution of the first digits of the non-zero MPEG quantized AC coefficients will be disturbed, Chen in [3] distinguish the occurrence of the double compression.…”

Section: Introductionmentioning

confidence: 99%

Double HEVC Compression Detection with the Same QPs Based on the PU Numbers

Jia

Zhang

et al. 2016

ITM Web Conf.

View full text Add to dashboard Cite

Abstract. Double HEVC compression detection is of great importance in video forensics. However, effective detection algorithm based on the same Qps is rarely reported. In this paper, a novel method based on the same Qps is applied in dealing with double HEVC compression detection. Firstly, the numbers of PU blocks with the size of 4×4 in each I frame is extracted during the codec procedures when the video is compressed with the same Qps. Then, calculate the standard deviation of 4×4 PU blocks difference (SDoPU) before and after the compression. Finally, select the appropriate threshold for compression testing classification according to the SDoPU statistical feature. By performing numerical experiments, We prove that the proposed algorithm is of high classification accuracy for detecting double HEVC compression.

show abstract

Exposing video forgeries by detecting MPEG double compression

Cited by 64 publications

References 5 publications

Double HEVC Compression Detection with Different Bitrates Based on Co-occurrence Matrix of PU Types and DCT Coefficients

Double HEVC Compression Detection with Different Bitrates Based on Co-occurrence Matrix of PU Types and DCT Coefficients

A Tool to Support the Creation of Datasets of Tampered Videos

Double HEVC Compression Detection with the Same QPs Based on the PU Numbers

Contact Info

Product

Resources

About