Fast camera fingerprint matching in very large databases

Samet Taspinar, Husrev T. Sencar, Sevinc Bayram, Nasir Memon

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

    Abstract

    Given a query image or video, or a known camera fingerprint, there is a lack of capabilities for fast identification of media, from a large repository of images and videos, that match the query fingerprint. This work introduces a new approach that improves the computation efficiency of pairwise camera fingerprint matching and incorporates group testing to make the search more effective. More specifically, we jointly leverage the individual strengths of composite fingerprints and fingerprint digests in a novel manner and design two methods that are superior to existing approaches. The results show that under very high-performance requirements, where the probability of correct identification is close to one with a false-positive rate of zero, the proposed search methods are 2-8 times faster than the state-of-art search methods.

    Original languageEnglish (US)
    Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
    PublisherIEEE Computer Society
    Pages4088-4092
    Number of pages5
    Volume2017-September
    ISBN (Electronic)9781509021758
    DOIs
    StatePublished - Feb 20 2018
    Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
    Duration: Sep 17 2017Sep 20 2017

    Other

    Other24th IEEE International Conference on Image Processing, ICIP 2017
    CountryChina
    CityBeijing
    Period9/17/179/20/17

    Fingerprint

    Cameras
    Composite materials
    Testing

    Keywords

    • Camera fingerprint
    • Composite fingerprint
    • Fingerprint digests
    • PRNU noise
    • Sensor noise

    ASJC Scopus subject areas

    • Software
    • Computer Vision and Pattern Recognition
    • Signal Processing

    Cite this

    Taspinar, S., Sencar, H. T., Bayram, S., & Memon, N. (2018). Fast camera fingerprint matching in very large databases. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (Vol. 2017-September, pp. 4088-4092). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8297051

    Fast camera fingerprint matching in very large databases. / Taspinar, Samet; Sencar, Husrev T.; Bayram, Sevinc; Memon, Nasir.

    2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. p. 4088-4092.

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

    Taspinar, S, Sencar, HT, Bayram, S & Memon, N 2018, Fast camera fingerprint matching in very large databases. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. vol. 2017-September, IEEE Computer Society, pp. 4088-4092, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 9/17/17. https://doi.org/10.1109/ICIP.2017.8297051
    Taspinar S, Sencar HT, Bayram S, Memon N. Fast camera fingerprint matching in very large databases. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September. IEEE Computer Society. 2018. p. 4088-4092 https://doi.org/10.1109/ICIP.2017.8297051
    Taspinar, Samet ; Sencar, Husrev T. ; Bayram, Sevinc ; Memon, Nasir. / Fast camera fingerprint matching in very large databases. 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Vol. 2017-September IEEE Computer Society, 2018. pp. 4088-4092
    @inproceedings{d335b15e03f94934bb8d630307cfb32f,
    title = "Fast camera fingerprint matching in very large databases",
    abstract = "Given a query image or video, or a known camera fingerprint, there is a lack of capabilities for fast identification of media, from a large repository of images and videos, that match the query fingerprint. This work introduces a new approach that improves the computation efficiency of pairwise camera fingerprint matching and incorporates group testing to make the search more effective. More specifically, we jointly leverage the individual strengths of composite fingerprints and fingerprint digests in a novel manner and design two methods that are superior to existing approaches. The results show that under very high-performance requirements, where the probability of correct identification is close to one with a false-positive rate of zero, the proposed search methods are 2-8 times faster than the state-of-art search methods.",
    keywords = "Camera fingerprint, Composite fingerprint, Fingerprint digests, PRNU noise, Sensor noise",
    author = "Samet Taspinar and Sencar, {Husrev T.} and Sevinc Bayram and Nasir Memon",
    year = "2018",
    month = "2",
    day = "20",
    doi = "10.1109/ICIP.2017.8297051",
    language = "English (US)",
    volume = "2017-September",
    pages = "4088--4092",
    booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - Fast camera fingerprint matching in very large databases

    AU - Taspinar, Samet

    AU - Sencar, Husrev T.

    AU - Bayram, Sevinc

    AU - Memon, Nasir

    PY - 2018/2/20

    Y1 - 2018/2/20

    N2 - Given a query image or video, or a known camera fingerprint, there is a lack of capabilities for fast identification of media, from a large repository of images and videos, that match the query fingerprint. This work introduces a new approach that improves the computation efficiency of pairwise camera fingerprint matching and incorporates group testing to make the search more effective. More specifically, we jointly leverage the individual strengths of composite fingerprints and fingerprint digests in a novel manner and design two methods that are superior to existing approaches. The results show that under very high-performance requirements, where the probability of correct identification is close to one with a false-positive rate of zero, the proposed search methods are 2-8 times faster than the state-of-art search methods.

    AB - Given a query image or video, or a known camera fingerprint, there is a lack of capabilities for fast identification of media, from a large repository of images and videos, that match the query fingerprint. This work introduces a new approach that improves the computation efficiency of pairwise camera fingerprint matching and incorporates group testing to make the search more effective. More specifically, we jointly leverage the individual strengths of composite fingerprints and fingerprint digests in a novel manner and design two methods that are superior to existing approaches. The results show that under very high-performance requirements, where the probability of correct identification is close to one with a false-positive rate of zero, the proposed search methods are 2-8 times faster than the state-of-art search methods.

    KW - Camera fingerprint

    KW - Composite fingerprint

    KW - Fingerprint digests

    KW - PRNU noise

    KW - Sensor noise

    UR - http://www.scopus.com/inward/record.url?scp=85045335199&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85045335199&partnerID=8YFLogxK

    U2 - 10.1109/ICIP.2017.8297051

    DO - 10.1109/ICIP.2017.8297051

    M3 - Conference contribution

    VL - 2017-September

    SP - 4088

    EP - 4092

    BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

    PB - IEEE Computer Society

    ER -