Abstract
Source camera identification has recently received a wide attention due to its importantrole in security and legal issue. The problem of establishing the origin ofdigital media obtained through an imaging device is important whenever digitalcontent is presented and is used as evidence in the court. Source camera identification is the process of determining which camera device or model has been used to capture an image.Our first contribution for digital camera model identification is based on the extractionof three sets of features in a machine learning scheme. These featuresare the co-occurrences matrix, some features related to CFA interpolation arrangement,and conditional probability statistics computed in the JPEG domain.These features give high order statistics which supplement and enhance the identification rate. The experiments prove the strength of our proposition since it achieves higher accuracy than the correlation-based method.The second contribution is based on using the deep convolutional neural networks(CNNs). Unlike traditional methods, CNNs can automatically and simultaneouslyextract features and learn to classify during the learning process. A layer ofpreprocessing is added to the CNN model, and consists of a high pass filter which isapplied to the input image. The obtained CNN gives very good performance for avery small learning complexity. Experimental comparison with a classical two stepsmachine learning approach shows that the proposed method can achieve significantdetection performance. The well known object recognition CNN models, AlexNetand GoogleNet, are also examined.