Special issue on deep learning in image and video forensics

Roberto Caldelli, Marc Chaumont, Chang Tsun Li, Irene Amerini

    Research output: Contribution to journalEditorialpeer-review

    2 Citations (Scopus)

    Abstract

    The pervasiveness of new technologies, such as smartphones, tablets and Internet, makes digital images and videos the primary source of visual information in the modern day society. However, their reliability as a true representation of reality cannot be taken for granted due to the affordable powerful graphics editing software that can easily alter the original content without leaving noticeable visual trace of the modification. Nowadays, machine learning techniques and, in particular, Deep Learning have come to play a vital role in dealing with a massive amount of raw data. In recent years, deep neural networks, such as deep belief network, deep autoencoder and convolutional neural network (CNN), have shown to be capable of extracting complex statistical features and efficiently learning their representations, allowing it to generalize well across a wide variety of computer vision tasks, including image classification, speech recognition and so on.
    Original languageEnglish
    Pages (from-to)199-200
    Number of pages2
    JournalSignal Processing: Image Communication
    Volume75
    DOIs
    Publication statusPublished - Jul 2019

    Fingerprint

    Dive into the research topics of 'Special issue on deep learning in image and video forensics'. Together they form a unique fingerprint.

    Cite this