Local descriptors based on the image noise residual have proven extremely effective for a number of forensic applications, like forgery detection and localization. Nonetheless, motivated by promising results in computer vision, the focus of the research community is now shifting on deep learning. In this paper we show that a class of residual-based descriptors can be actually regarded as a simple constrained convolutional neural network (CNN). Then, by relaxing the constraints, and fine-tuning the net on a relatively small training set, we obtain a significant performance improvement with respect to the conventional detector.

Recasting residual-based local descriptors as convolutional neural networks: An application to image forgery detection / Cozzolino, Davide; Poggi, Giovanni; Verdoliva, Luisa. - (2017). (Intervento presentato al convegno ACM Workshop on Information Hiding and Multimedia Security) [10.1145/3082031.3083247].

Recasting residual-based local descriptors as convolutional neural networks: An application to image forgery detection

Davide Cozzolino;Giovanni Poggi;Luisa Verdoliva
2017

Abstract

Local descriptors based on the image noise residual have proven extremely effective for a number of forensic applications, like forgery detection and localization. Nonetheless, motivated by promising results in computer vision, the focus of the research community is now shifting on deep learning. In this paper we show that a class of residual-based descriptors can be actually regarded as a simple constrained convolutional neural network (CNN). Then, by relaxing the constraints, and fine-tuning the net on a relatively small training set, we obtain a significant performance improvement with respect to the conventional detector.
2017
978-145035061-7
Recasting residual-based local descriptors as convolutional neural networks: An application to image forgery detection / Cozzolino, Davide; Poggi, Giovanni; Verdoliva, Luisa. - (2017). (Intervento presentato al convegno ACM Workshop on Information Hiding and Multimedia Security) [10.1145/3082031.3083247].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/11588/703225
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 286
  • ???jsp.display-item.citation.isi??? ND
social impact