Open AccessEnd‐to‐end double JPEG detection with a 3D convolutional network in the DCT domain
Author(s) -
Ahn W.,
Nam S.H.,
Son M.,
Lee H.K.,
Choi S.
Publication year - 2020
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2019.2719
Subject(s) - discrete cosine transform , jpeg , computer science , convolutional neural network , artificial intelligence , transform coding , quantization (signal processing) , lossless jpeg , data compression , computer vision , feature (linguistics) , pattern recognition (psychology) , image compression , image (mathematics) , image processing , linguistics , philosophy
Detection of double JPEG compression is essential in the field of digital image forensics. Although double JPEG compression detection methods have greatly improved with the development of convolutional neural networks (CNNs), they rely on handcrafted features such as discrete cosine transform (DCT) histograms. In this Letter, the authors propose an end‐to‐end trainable 3D CNN in the DCT domain for double JPEG compression detection. Moreover, they also propose a new type of module, called feature rescaling , to insert the quantisation table into the network suitably. The experiments show that the proposed method outperforms state‐of‐the‐art methods.