This paper proposes a novel approach for registering the PRNU pattern between different camera acquisition modes by relying on the imaged scene content. First, images are aligned by establishing correspondences between local descriptors: The result can then optionally be refined by maximizing the PRNU correlation. Comparative evaluations show that this approach outperforms those based on brute-force and particle swarm optimization in terms of reliability, accuracy and speed. The proposed scene-based approach for PRNU pattern alignment is suitable for video source identification in multimedia forensics applications.

PRNU pattern alignment for images and videos based on scene content / Bellavia Fabio, Iuliani Massimo, Fanfani Marco, Colombo Carlo, Piva Alessandro. - ELETTRONICO. - (2019), pp. 0-0. (Intervento presentato al convegno 26th International Conference on Image Processing ICIP 2019 tenutosi a Taipei, Taiwan nel September 2-5, 2019) [10.1109/ICIP.2019.8802990].

PRNU pattern alignment for images and videos based on scene content

Bellavia Fabio
;
Iuliani Massimo;Fanfani Marco;Colombo Carlo;Piva Alessandro
2019

Abstract

This paper proposes a novel approach for registering the PRNU pattern between different camera acquisition modes by relying on the imaged scene content. First, images are aligned by establishing correspondences between local descriptors: The result can then optionally be refined by maximizing the PRNU correlation. Comparative evaluations show that this approach outperforms those based on brute-force and particle swarm optimization in terms of reliability, accuracy and speed. The proposed scene-based approach for PRNU pattern alignment is suitable for video source identification in multimedia forensics applications.
2019
International Conference on Image Processing. Proceedings of
26th International Conference on Image Processing ICIP 2019
Taipei, Taiwan
September 2-5, 2019
Bellavia Fabio, Iuliani Massimo, Fanfani Marco, Colombo Carlo, Piva Alessandro
File in questo prodotto:
File Dimensione Formato  
PRNU.pdf

accesso aperto

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 285.31 kB
Formato Adobe PDF
285.31 kB Adobe PDF

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1154652
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 5
social impact