New features to identify computer generated images

A. E. Dirik, S. Bayram, H. T. Senear, N. Memon

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Discrimination of computer generated images from real images is becoming more and more important. In this paper, we propose the use of new features to distinguish computer generated images from real images. The proposed features are based on the differences in the acquisition process of images. More specifically, traces of demosaicking and chromatic aberration are used to differentiate computer generated images from digital camera images. It is observed that the former features perform very well on high quality images, whereas the latter features perform consistently across a wide range of compression values. The experimental results show that proposed features are capable of improving the accuracy of the state-of-the-art techniques.

    Original languageEnglish (US)
    Title of host publication2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings
    Volume4
    DOIs
    StatePublished - 2006
    Event14th IEEE International Conference on Image Processing, ICIP 2007 - San Antonio, TX, United States
    Duration: Sep 16 2007Sep 19 2007

    Other

    Other14th IEEE International Conference on Image Processing, ICIP 2007
    CountryUnited States
    CitySan Antonio, TX
    Period9/16/079/19/07

    Fingerprint

    Digital cameras
    Aberrations
    Image quality

    Keywords

    • Bayer filter
    • Chromatic aberration
    • Computer generated
    • Demosaicking
    • Digital image forensics

    ASJC Scopus subject areas

    • Engineering(all)

    Cite this

    Dirik, A. E., Bayram, S., Senear, H. T., & Memon, N. (2006). New features to identify computer generated images. In 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings (Vol. 4). [4380047] https://doi.org/10.1109/ICIP.2007.4380047

    New features to identify computer generated images. / Dirik, A. E.; Bayram, S.; Senear, H. T.; Memon, N.

    2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. Vol. 4 2006. 4380047.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Dirik, AE, Bayram, S, Senear, HT & Memon, N 2006, New features to identify computer generated images. in 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. vol. 4, 4380047, 14th IEEE International Conference on Image Processing, ICIP 2007, San Antonio, TX, United States, 9/16/07. https://doi.org/10.1109/ICIP.2007.4380047
    Dirik AE, Bayram S, Senear HT, Memon N. New features to identify computer generated images. In 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. Vol. 4. 2006. 4380047 https://doi.org/10.1109/ICIP.2007.4380047
    Dirik, A. E. ; Bayram, S. ; Senear, H. T. ; Memon, N. / New features to identify computer generated images. 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings. Vol. 4 2006.
    @inproceedings{11631dbaa86842a9a804102de3a5f73f,
    title = "New features to identify computer generated images",
    abstract = "Discrimination of computer generated images from real images is becoming more and more important. In this paper, we propose the use of new features to distinguish computer generated images from real images. The proposed features are based on the differences in the acquisition process of images. More specifically, traces of demosaicking and chromatic aberration are used to differentiate computer generated images from digital camera images. It is observed that the former features perform very well on high quality images, whereas the latter features perform consistently across a wide range of compression values. The experimental results show that proposed features are capable of improving the accuracy of the state-of-the-art techniques.",
    keywords = "Bayer filter, Chromatic aberration, Computer generated, Demosaicking, Digital image forensics",
    author = "Dirik, {A. E.} and S. Bayram and Senear, {H. T.} and N. Memon",
    year = "2006",
    doi = "10.1109/ICIP.2007.4380047",
    language = "English (US)",
    isbn = "1424414377",
    volume = "4",
    booktitle = "2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings",

    }

    TY - GEN

    T1 - New features to identify computer generated images

    AU - Dirik, A. E.

    AU - Bayram, S.

    AU - Senear, H. T.

    AU - Memon, N.

    PY - 2006

    Y1 - 2006

    N2 - Discrimination of computer generated images from real images is becoming more and more important. In this paper, we propose the use of new features to distinguish computer generated images from real images. The proposed features are based on the differences in the acquisition process of images. More specifically, traces of demosaicking and chromatic aberration are used to differentiate computer generated images from digital camera images. It is observed that the former features perform very well on high quality images, whereas the latter features perform consistently across a wide range of compression values. The experimental results show that proposed features are capable of improving the accuracy of the state-of-the-art techniques.

    AB - Discrimination of computer generated images from real images is becoming more and more important. In this paper, we propose the use of new features to distinguish computer generated images from real images. The proposed features are based on the differences in the acquisition process of images. More specifically, traces of demosaicking and chromatic aberration are used to differentiate computer generated images from digital camera images. It is observed that the former features perform very well on high quality images, whereas the latter features perform consistently across a wide range of compression values. The experimental results show that proposed features are capable of improving the accuracy of the state-of-the-art techniques.

    KW - Bayer filter

    KW - Chromatic aberration

    KW - Computer generated

    KW - Demosaicking

    KW - Digital image forensics

    UR - http://www.scopus.com/inward/record.url?scp=48149097069&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=48149097069&partnerID=8YFLogxK

    U2 - 10.1109/ICIP.2007.4380047

    DO - 10.1109/ICIP.2007.4380047

    M3 - Conference contribution

    SN - 1424414377

    SN - 9781424414376

    VL - 4

    BT - 2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings

    ER -