Printer source identification by feature modeling in the total variable printer space

Advances in the digital world have attracted the attention of many researchers in terms of developing digital forensics. Using machine learning methods for print source identification is one of the developing areas in the field of digital forensics. In this paper, a new method is presented for printer source identification by modeling the primary Local Binary Pattern (LBP) features in the total variable printer space and extracting the secondary features based on the joint factor analysis. Only one low-dimensional i-vector feature is employed for each document image without using any optical character recognition (OCR) algorithm or similar processes. This property eliminates the requirement for the majority voting algorithm and reduces the computational cost of the classification process. Furthermore, the proposed algorithm is not limited to a specific language or character set. The capabilities of the proposed method in extracting useful discriminant information from the sparse print shadow texture are revealed through simulation. The simulation results showed that the proposed algorithm obtained the accuracy of 98.48% by refining the basic features of LBP, which is comparable to the results of the state-of-the-art approaches in this field.