A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Two-dimensional signal and image processing
Two-dimensional signal and image processing
Color Desktop Printer Technology (Optical Engineering)
Color Desktop Printer Technology (Optical Engineering)
Printer Identification Based on Distance Transform
ICINIS '08 Proceedings of the 2008 First International Conference on Intelligent Networks and Intelligent Systems
Document Forgery Detection with SVM Classifier and Image Quality Measures
PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Color laser printer identification by analyzing statistical features on discrete wavelet transform
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
| Hi-index | 0.00 |
Digital forensics in the ubiquitous era can enhance and protect the reliability of multimedia content where this content is accessed, manipulated, and distributed using high quality computer devices. Color laser printer forensics is a kind of digital forensics which identifies the printing source of color printed materials such as fine arts, money, and document and helps to catch a criminal. This paper present a new color laser printer forensic algorithm based on noisy texture analysis and support vector machine classifier that can detect which color laser printer was used to print the unknown images. Since each printer vender uses their own printing process, printed documents from different venders have a little invisible difference looks like noise. In our identification scheme, the invisible noises are estimated with the wiener-filter and the 2D Discrete Wavelet Transform (DWT) filter. Then, a gray level co-occurrence matrix (GLCM) is calculated to analyze the texture of the noise. From the GLCM, 384 statistical features are extracted and applied to train and test the support vector machine classifier for identifying the color laser printers. In the experiment, a total of 4,800 images from 8 color laser printer models were used, where half of the image is for training and the other half is for classification. Results prove that the presented algorithm performs well by achieving 99.3%, 97.4% and 88.7% accuracy for the brand, toner and model identification respectively.