Further studies on forensic features for source camera identification

Most camera identification schemes focus on finding image features that can increase classification accuracy as well as computational efficiency. For forensic investigation purposes, however, these selection criteria are not enough since most real-world photos may have undergone common image processing due to various reasons. Therefore, source camera classifiers must have the capability to resist the influence of common image processing when they tackle these processed photos. In this work, we implement a published camera classifier and investigate the performance of the classifier on images under shearing, histogram equalization, and contrast-stretching operations. Besides, we probe into the impact of camera databases of different sizes on the performance of the classifier.