DCT-domain deep convolutional neural networks for multiple JPEG compression classification

Show simple item record

dc.contributor.author Verma, Vinay
dc.contributor.author Agarwal, Nikita
dc.contributor.author Khanna, Nitin
dc.date.accessioned 2018-06-13T12:51:59Z
dc.date.available 2018-06-13T12:51:59Z
dc.date.issued 2018-09
dc.identifier.citation Verma, Vinay; Agarwal, Nikita and Khanna, Nitin, "DCT-domain deep convolutional neural networks for multiple JPEG compression classification", Signal Processing: Image Communication, DOI: 10.1016/j.image.2018.04.014, vol. 67, pp. 22-33, Sep. 2018. en_US
dc.identifier.isbn 1879-2677
dc.identifier.issn 0923-5965
dc.identifier.uri http://dx.doi.org/10.1016/j.image.2018.04.014
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/3737
dc.description.abstract With the rapid advancements in digital imaging systems and networking, low-cost hand-held image capture devices equipped with network connectivity are becoming ubiquitous. This ease of digital image capture and sharing is also accompanied by widespread usage of user-friendly image editing software. Thus, we are in an era where digital images can be very easily used for the massive spread of false information and their integrity needs to be seriously questioned. Application of multiple lossy compressions on images is an essential part of any image editing pipeline involving lossy compressed images. This paper aims to address the problem of classifying images based on the number of JPEG compressions they have undergone, by utilizing deep convolutional neural networks in DCT domain. The proposed system incorporates a well designed pre-processing step before feeding the image data to CNN to capture essential characteristics of compression artifacts and make the system image content independent. Detailed experiments are performed to optimize different aspects of the system, such as depth of CNN, number of DCT frequencies, and execution time. Results on the standard UCID dataset demonstrate that the proposed system outperforms existing system for multiple JPEG compression classification and is capable of classifying more number of re-compression cycles than existing systems
dc.description.statementofresponsibility by Vinay Verma, Nikita Agarwal and Nitin Khanna
dc.format.extent vol. 67, pp. 22-33
dc.language.iso en en_US
dc.publisher Elsevier en_US
dc.subject Image forensics en_US
dc.subject Compression forensics en_US
dc.subject Deep convolutional neural network(CNN) en_US
dc.subject JPEG forensics en_US
dc.subject Multiple compression en_US
dc.subject Forgery detection en_US
dc.title DCT-domain deep convolutional neural networks for multiple JPEG compression classification en_US
dc.type Article en_US
dc.relation.journal Signal Processing: Image Communication

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


My Account