Boosting up Source Scanner Identification Using Wavelets and Convolutional Neural Networks
Chaima Ben Rabah, Gouenou Coatrieux, Riadh Abdelfattah · Traitement du signal · 2020
In this paper, we present a conceptually innovative method for source scanner identification (SSI), that is to say, identifying the scanner at the origin of a scanned document. Solutions from literature can distinguish between scanners of different brands and models but fail to differentiate between scanners of the same models. To overcome this issue, the approach we propose takes advantage of a convolutional neural network (CNN) to automatically extract intrinsic scanner features from the distribution of the coefficients of the diagonal high-frequency (HH) sub-band of the discrete stationary wavelet transform (SWT) of scanned images. Such information serves as a reliable characteristic to classify scanners of different/same brands and models. Experiments conducted on a set of 8 scanners yielded a model with an accuracy of 99.31% at the block level and 100% at the full image level, showcasing the potential of using deep learning for SSI and outperforming existing schemes from literature. The influence of the model’s parameters such as the input size, the training data size, the number of layers, and the number of nodes in the fully connected layer as well as the effect of the pre-processing step were investigated.