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

facebooktwittermailshare

LEARNED FORENSIC SOURCE SIMILARITY FOR UNKNOWN CAMERA MODELS

Abstract: 

Information about an image's source camera model is important knowledge in many forensic investigations. In this paper we propose a system that compares two image patches to determine if they were captured by the same camera model. To do this, we first train a CNN based feature extractor to output generic, high level features which encode information about the source camera model of an image patch. Then, we learn a similarity measure that maps pairs of these features to a score indicating whether the two image patches were captured by the same or different camera models. We show that our proposed system accurately determines if two patches were captured by the same or different camera models, even when the camera models are unknown to the investigator. We also demonstrate the utility of this approach for image splicing detection and localization

up
0 users have voted:

Paper Details

Authors:
Owen Mayer, Mathew C. Stamm
Submitted On:
27 April 2018 - 12:45pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Owen Mayer
Paper Code:
3283
Document Year:
2018
Cite

Document Files

poster pdf

(20 downloads)

Subscribe

[1] Owen Mayer, Mathew C. Stamm, "LEARNED FORENSIC SOURCE SIMILARITY FOR UNKNOWN CAMERA MODELS", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3185. Accessed: May. 20, 2018.
@article{3185-18,
url = {http://sigport.org/3185},
author = {Owen Mayer; Mathew C. Stamm },
publisher = {IEEE SigPort},
title = {LEARNED FORENSIC SOURCE SIMILARITY FOR UNKNOWN CAMERA MODELS},
year = {2018} }
TY - EJOUR
T1 - LEARNED FORENSIC SOURCE SIMILARITY FOR UNKNOWN CAMERA MODELS
AU - Owen Mayer; Mathew C. Stamm
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3185
ER -
Owen Mayer, Mathew C. Stamm. (2018). LEARNED FORENSIC SOURCE SIMILARITY FOR UNKNOWN CAMERA MODELS. IEEE SigPort. http://sigport.org/3185
Owen Mayer, Mathew C. Stamm, 2018. LEARNED FORENSIC SOURCE SIMILARITY FOR UNKNOWN CAMERA MODELS. Available at: http://sigport.org/3185.
Owen Mayer, Mathew C. Stamm. (2018). "LEARNED FORENSIC SOURCE SIMILARITY FOR UNKNOWN CAMERA MODELS." Web.
1. Owen Mayer, Mathew C. Stamm. LEARNED FORENSIC SOURCE SIMILARITY FOR UNKNOWN CAMERA MODELS [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3185