Identifying Color Laser Printer Using Noisy Feature and Support Vector Machine

Abstract

Color laser printers are nowadays abused to forge official documents and bills. Identifying the source used to print documents will be a step for digital media forensics. Each printer vender applies its specific manufacturing and printing process and that makes printed documents from different venders to have a little invisible difference looks like noise. In this paper, we propose a color laser printer identification method which detects the vendor or model of color laser printers used to print the unknown images. The invisible noises specific to each printer are estimated with Wiener-filter and then a gray level co-occurrence matrix (GLCM) is calculated to analyze the noise texture. From the GLCM, 60 statistical features are extracted and applied to train and test the support vector machine classifier for identifying the color laser printers. Experimental results on total 2,597 images from 7 color laser printers prove that the presented method identifies the color laser printers well.