Random subspace method for source camera identification

Ruizhe Li, Constantine Kotropoulos, Chang Tsun Li, Yu Guan

    Research output: Book chapter/Published conference paperConference paperpeer-review

    5 Citations (Scopus)


    Sensor pattern noise is an inherent fingerprint of imaging devices, which has been widely used for source camera identification, image classification, and forgery detection. In a previous work, we proposed a feature extraction method based on the principal component analysis denoising concept, which can enhance the performance of conventional SPN extraction methods. However, this method is vulnerable, because the training samples are seriously affected by the image content. Accordingly, it is difficult to train a reliable feature extractor by using such a training set. To address this problem, a camera identification framework based on the random subspace method and majority voting is proposed in this work. The experimental results show that the proposed solution can suppress the interference from scene details and enhance the performance in terms of the receiver operating characteristic curve.
    Original languageEnglish
    Title of host publication2015 IEEE International Workshop on Machine Learning for Signal Processing
    Subtitle of host publicationProceedings of MLSP 2015
    EditorsDeniz Erdoğmuş , Murat Akçakaya , Serdar Kozat, Jan Larsen
    PublisherIEEE Computer Society
    Number of pages5
    ISBN (Electronic)9781467374545
    Publication statusPublished - 10 Nov 2015
    Event25th IEEE International Workshop on Machine Learning for Signal Processing: MLSP 2015 - Northeastern University, Boston, United States
    Duration: 17 Sep 201520 Sep 2015
    http://mlsp2015.conwiz.dk/home.htm (Conference website)


    Conference25th IEEE International Workshop on Machine Learning for Signal Processing
    Country/TerritoryUnited States
    Internet address


    Dive into the research topics of 'Random subspace method for source camera identification'. Together they form a unique fingerprint.

    Cite this