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

facebooktwittermailshare

INPAINTING-BASED CAMERA ANONYMIZATION

Abstract: 

Over the years, the forensic community has developed a series of very accurate camera attribution algorithms enabling to detect which device has been used to acquire an image with outstanding results. Many of these methods are based on photo response non uniformity (PRNU) that allows tracing back a picture to the camera used to shoot it. However, when privacy is required, it would be desirable to anonymize photos, unlinking them from their specific device. This paper investigates a new and alternative approach to image anonymization task. The proposed method leverages image inpainting described as an inverse regularized problem, and does not need any priors about the PRNU to remove. Specifically, we show how PRNU pattern can be strongly attenuated by reconstructing each pixel of an image from its neighbors, only slightly affecting visual quality. Results confirm this approach as a viable alternative solution for image anonymization.

up
0 users have voted:

Paper Details

Authors:
Sara Mandelli, Luca Bondi, Silvia Lameri, Vincenzo Lipari, Paolo Bestagini, Stefano Tubaro
Submitted On:
19 September 2017 - 5:48am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Luca Bondi
Paper Code:
WA.L4.6
Document Year:
2017
Cite

Document Files

polimi_prnu-removal_icip17.pdf

(25 downloads)

Subscribe

[1] Sara Mandelli, Luca Bondi, Silvia Lameri, Vincenzo Lipari, Paolo Bestagini, Stefano Tubaro, "INPAINTING-BASED CAMERA ANONYMIZATION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2226. Accessed: Oct. 24, 2017.
@article{2226-17,
url = {http://sigport.org/2226},
author = {Sara Mandelli; Luca Bondi; Silvia Lameri; Vincenzo Lipari; Paolo Bestagini; Stefano Tubaro },
publisher = {IEEE SigPort},
title = {INPAINTING-BASED CAMERA ANONYMIZATION},
year = {2017} }
TY - EJOUR
T1 - INPAINTING-BASED CAMERA ANONYMIZATION
AU - Sara Mandelli; Luca Bondi; Silvia Lameri; Vincenzo Lipari; Paolo Bestagini; Stefano Tubaro
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2226
ER -
Sara Mandelli, Luca Bondi, Silvia Lameri, Vincenzo Lipari, Paolo Bestagini, Stefano Tubaro. (2017). INPAINTING-BASED CAMERA ANONYMIZATION. IEEE SigPort. http://sigport.org/2226
Sara Mandelli, Luca Bondi, Silvia Lameri, Vincenzo Lipari, Paolo Bestagini, Stefano Tubaro, 2017. INPAINTING-BASED CAMERA ANONYMIZATION. Available at: http://sigport.org/2226.
Sara Mandelli, Luca Bondi, Silvia Lameri, Vincenzo Lipari, Paolo Bestagini, Stefano Tubaro. (2017). "INPAINTING-BASED CAMERA ANONYMIZATION." Web.
1. Sara Mandelli, Luca Bondi, Silvia Lameri, Vincenzo Lipari, Paolo Bestagini, Stefano Tubaro. INPAINTING-BASED CAMERA ANONYMIZATION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2226