Random Subspace Method For Source Camera Identification
Ruizhe Li, Constantine Kotropoulos, Chang Tsun Li, Yu Guan

Abstract:
Sensor Pattern Noise is an inherent fingerprint of imaging devices, which has been widely used in the tasks of source camera identification, image classification and forgery detec- tion. 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, when training samples are contaminated by image content. In this case, 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 sub- space method and majority voting is proposed in this work. Our 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.