Detection of fake 3D video using CNN

Shuvendu Rana, Sibaji Gaj, Arijit Sur, Prabin Kumar Bora

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

1 Citation (Scopus)

Abstract

In this paper, a novel automatic fake and the real 3D video recognition scheme is proposed to distinguish the 3D video converted from the 2D video using 2D to 3D conversion process (say fake 3D) from the 3D video captured using direct capturing of the 3D camera (say real 3D). To identify the real and fake 3D, pre-filtration is done using the dual tree complex wavelet transform to emerge the edge and vertical and horizontal parallax characteristics of real and fake 3D videos. Convolution neural network (CNN) is used to train the 3D characteristics to distinguish the fake 3D videos from the real ones. A comprehensive set of experiments has been carried out to justify the efficacy of the proposed scheme over the existing literature.

LanguageEnglish
Title of host publication2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP)
Place of Publication[New York]
PublisherIEEE
Number of pages5
ISBN (Print)9781509037247
DOIs
Publication statusPublished - 16 Jan 2017
Event18th IEEE International Workshop on Multimedia Signal Processing, MMSP 2016 - Montreal, Canada
Duration: 21 Sep 201623 Sep 2016

Conference

Conference18th IEEE International Workshop on Multimedia Signal Processing, MMSP 2016
CountryCanada
CityMontreal
Period21/09/1623/09/16

Fingerprint

Convolution
Wavelet transforms
Cameras
Neural networks
Experiments

Keywords

  • 3D high-efficient-video-coding (3D-HEVC)
  • convolution neural network (CNN)
  • depth-image-based rendering (DIBR)
  • DIBR-3D
  • dual-tree complex-wavelet-transform (DT-DCT)
  • fake 3D video
  • multi-view video plus depth (MVD)
  • real 3D video

Cite this

Rana, S., Gaj, S., Sur, A., & Bora, P. K. (2017). Detection of fake 3D video using CNN. In 2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP) [7813368] [New York]: IEEE. https://doi.org/10.1109/MMSP.2016.7813368
Rana, Shuvendu ; Gaj, Sibaji ; Sur, Arijit ; Bora, Prabin Kumar. / Detection of fake 3D video using CNN. 2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP). [New York] : IEEE, 2017.
@inproceedings{b59ee8ebbd1a42138510ba1594da3267,
title = "Detection of fake 3D video using CNN",
abstract = "In this paper, a novel automatic fake and the real 3D video recognition scheme is proposed to distinguish the 3D video converted from the 2D video using 2D to 3D conversion process (say fake 3D) from the 3D video captured using direct capturing of the 3D camera (say real 3D). To identify the real and fake 3D, pre-filtration is done using the dual tree complex wavelet transform to emerge the edge and vertical and horizontal parallax characteristics of real and fake 3D videos. Convolution neural network (CNN) is used to train the 3D characteristics to distinguish the fake 3D videos from the real ones. A comprehensive set of experiments has been carried out to justify the efficacy of the proposed scheme over the existing literature.",
keywords = "3D high-efficient-video-coding (3D-HEVC), convolution neural network (CNN), depth-image-based rendering (DIBR), DIBR-3D, dual-tree complex-wavelet-transform (DT-DCT), fake 3D video, multi-view video plus depth (MVD), real 3D video",
author = "Shuvendu Rana and Sibaji Gaj and Arijit Sur and Bora, {Prabin Kumar}",
year = "2017",
month = "1",
day = "16",
doi = "10.1109/MMSP.2016.7813368",
language = "English",
isbn = "9781509037247",
booktitle = "2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP)",
publisher = "IEEE",

}

Rana, S, Gaj, S, Sur, A & Bora, PK 2017, Detection of fake 3D video using CNN. in 2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP)., 7813368, IEEE, [New York], 18th IEEE International Workshop on Multimedia Signal Processing, MMSP 2016, Montreal, Canada, 21/09/16. https://doi.org/10.1109/MMSP.2016.7813368

Detection of fake 3D video using CNN. / Rana, Shuvendu; Gaj, Sibaji; Sur, Arijit; Bora, Prabin Kumar.

2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP). [New York] : IEEE, 2017. 7813368.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Detection of fake 3D video using CNN

AU - Rana, Shuvendu

AU - Gaj, Sibaji

AU - Sur, Arijit

AU - Bora, Prabin Kumar

PY - 2017/1/16

Y1 - 2017/1/16

N2 - In this paper, a novel automatic fake and the real 3D video recognition scheme is proposed to distinguish the 3D video converted from the 2D video using 2D to 3D conversion process (say fake 3D) from the 3D video captured using direct capturing of the 3D camera (say real 3D). To identify the real and fake 3D, pre-filtration is done using the dual tree complex wavelet transform to emerge the edge and vertical and horizontal parallax characteristics of real and fake 3D videos. Convolution neural network (CNN) is used to train the 3D characteristics to distinguish the fake 3D videos from the real ones. A comprehensive set of experiments has been carried out to justify the efficacy of the proposed scheme over the existing literature.

AB - In this paper, a novel automatic fake and the real 3D video recognition scheme is proposed to distinguish the 3D video converted from the 2D video using 2D to 3D conversion process (say fake 3D) from the 3D video captured using direct capturing of the 3D camera (say real 3D). To identify the real and fake 3D, pre-filtration is done using the dual tree complex wavelet transform to emerge the edge and vertical and horizontal parallax characteristics of real and fake 3D videos. Convolution neural network (CNN) is used to train the 3D characteristics to distinguish the fake 3D videos from the real ones. A comprehensive set of experiments has been carried out to justify the efficacy of the proposed scheme over the existing literature.

KW - 3D high-efficient-video-coding (3D-HEVC)

KW - convolution neural network (CNN)

KW - depth-image-based rendering (DIBR)

KW - DIBR-3D

KW - dual-tree complex-wavelet-transform (DT-DCT)

KW - fake 3D video

KW - multi-view video plus depth (MVD)

KW - real 3D video

UR - http://www.scopus.com/inward/record.url?scp=85013140569&partnerID=8YFLogxK

U2 - 10.1109/MMSP.2016.7813368

DO - 10.1109/MMSP.2016.7813368

M3 - Conference contribution book

SN - 9781509037247

BT - 2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP)

PB - IEEE

CY - [New York]

ER -

Rana S, Gaj S, Sur A, Bora PK. Detection of fake 3D video using CNN. In 2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP). [New York]: IEEE. 2017. 7813368 https://doi.org/10.1109/MMSP.2016.7813368