Being able to reliably link a picture to the device that shot it is of paramount importance to give credit or assign responsibility to the author of the picture itself. However, this task needs to be performed at large scales due to the recent explosion in the number of photos taken and shared. Existing methods cannot satisfy those requirements. Methods based on the Photo Response Non-Uniformity (PRNU) of digital sensors are able to link a photo to the device that shot it and have already been used as proof in the Court of Law. Such methods are reliable but so far, they can be only used for small-scale forensic tasks involving few cameras and pictures. ToothPic, an acronym for "Who Took This Picture?", is a novel image retrieval engine that allows to find all the pictures in a large-scale database shot by a given query camera.

ToothPic: camera-based image retrieval on large scales / Valsesia, Diego; Coluccia, Giulio; Bianchi, Tiziano; Magli, Enrico. - In: IEEE MULTIMEDIA. - ISSN 1070-986X. - ELETTRONICO. - 26:2(2019), pp. 33-43. [10.1109/MMUL.2018.2873845]

ToothPic: camera-based image retrieval on large scales

Valsesia, Diego;Coluccia, Giulio;Bianchi, Tiziano;Magli, Enrico
2019

Abstract

Being able to reliably link a picture to the device that shot it is of paramount importance to give credit or assign responsibility to the author of the picture itself. However, this task needs to be performed at large scales due to the recent explosion in the number of photos taken and shared. Existing methods cannot satisfy those requirements. Methods based on the Photo Response Non-Uniformity (PRNU) of digital sensors are able to link a photo to the device that shot it and have already been used as proof in the Court of Law. Such methods are reliable but so far, they can be only used for small-scale forensic tasks involving few cameras and pictures. ToothPic, an acronym for "Who Took This Picture?", is a novel image retrieval engine that allows to find all the pictures in a large-scale database shot by a given query camera.
File in questo prodotto:
File Dimensione Formato  
vals_MMUL2018_OA.pdf

accesso aperto

Descrizione: articolo versione autore
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 938.43 kB
Formato Adobe PDF
938.43 kB Adobe PDF Visualizza/Apri
vals_MMUL2018.pdf

non disponibili

Descrizione: articolo versione publisher
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 2.41 MB
Formato Adobe PDF
2.41 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

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

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2727340