Text-Independent Algorithm for Source Printer Identification Based on燛nsemble Learning

Because of the widespread availability low-cost printers and scanners, document forgery has become extremely popular. Watermarks or signatures are used to protect important papers such as certificates, passports, identification cards. Identifying origins printed documents is helpful for criminal investigations also authenticating digital versions a in today’s world. Source printer (SPI) increasingly popular identifying frauds documents. This paper provides proposed algorithm source categorizing questioned into one classes. A dataset 1200 from 20 distinct (13) laser (7) inkjet achieved significant results. based on global features Histogram Oriented Gradient (HOG) local Local Binary Pattern (LBP) descriptors been identification. For classification, Decision Trees (DT), k-Nearest Neighbors (k-NN), Random Forests, Aggregate bootstrapping (bagging), Adaptive-boosting (boosting), Support Vector Machine (SVM), mixtures these classifiers have employed. The can accurately classify their appropriate adaptive boosting classifier attained 96% accuracy. compared four recently published algorithms that same gives better classification