Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A VIDEO CAMERA MODEL IDENTIFICATION SYSTEM USING DEEP LEARNING AND FUSION

Abstract: 

While significant work has been conducted to perform source cam- era model identification for images, little work has been done specif- ically for video camera model identification. This is problematic because different forensic traces may be left in digital images and videos captured by the same camera. As our experiments in this paper will show, a system trained to perform camera model identifi- cation for images yields unacceptably low performance when given video frames from the same cameras. To overcome this problem, new systems for identifying a videos source must be developed. In this paper, we propose a deep learning based system for determining the source camera model that captured a digital video. To do this, we use a convolutional neural network to produce camera model iden- tification scores for small patches taken from video frames. These patches are chosen by a patch selection system that obtains patches from several appropriate frames temporally distributed throughout the video. Forensic information obtained by the CNN is provided to a fusion system, which combines it to produce a single, more accurate identification result. Through a series of experiments, we evaluate several system design choices and show that our system can achieve 95.9% video camera model identification accuracy.

up
0 users have voted:

Paper Details

Authors:
B. Hosler, O. Mayer, B. Bayar, X. Zhao, C. Chen, J. A. Shackleford, M. C. Stamm
Submitted On:
27 March 2019 - 9:03am
Short Link:
Type:
Research Manuscript
Event:
Presenter's Name:
Brian Hosler
Paper Code:
3577
Document Year:
2019
Cite

Document Files

ICASSP2019.pdf

(72)

Subscribe

[1] B. Hosler, O. Mayer, B. Bayar, X. Zhao, C. Chen, J. A. Shackleford, M. C. Stamm, "A VIDEO CAMERA MODEL IDENTIFICATION SYSTEM USING DEEP LEARNING AND FUSION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/3856. Accessed: Sep. 21, 2019.
@article{3856-19,
url = {http://sigport.org/3856},
author = {B. Hosler; O. Mayer; B. Bayar; X. Zhao; C. Chen; J. A. Shackleford; M. C. Stamm },
publisher = {IEEE SigPort},
title = {A VIDEO CAMERA MODEL IDENTIFICATION SYSTEM USING DEEP LEARNING AND FUSION},
year = {2019} }
TY - EJOUR
T1 - A VIDEO CAMERA MODEL IDENTIFICATION SYSTEM USING DEEP LEARNING AND FUSION
AU - B. Hosler; O. Mayer; B. Bayar; X. Zhao; C. Chen; J. A. Shackleford; M. C. Stamm
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/3856
ER -
B. Hosler, O. Mayer, B. Bayar, X. Zhao, C. Chen, J. A. Shackleford, M. C. Stamm. (2019). A VIDEO CAMERA MODEL IDENTIFICATION SYSTEM USING DEEP LEARNING AND FUSION. IEEE SigPort. http://sigport.org/3856
B. Hosler, O. Mayer, B. Bayar, X. Zhao, C. Chen, J. A. Shackleford, M. C. Stamm, 2019. A VIDEO CAMERA MODEL IDENTIFICATION SYSTEM USING DEEP LEARNING AND FUSION. Available at: http://sigport.org/3856.
B. Hosler, O. Mayer, B. Bayar, X. Zhao, C. Chen, J. A. Shackleford, M. C. Stamm. (2019). "A VIDEO CAMERA MODEL IDENTIFICATION SYSTEM USING DEEP LEARNING AND FUSION." Web.
1. B. Hosler, O. Mayer, B. Bayar, X. Zhao, C. Chen, J. A. Shackleford, M. C. Stamm. A VIDEO CAMERA MODEL IDENTIFICATION SYSTEM USING DEEP LEARNING AND FUSION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/3856