Document forgery detection using source printer identification: A comparative study of text‐dependent versus text‐independent analysis

Abstract Source printer identification represents an interesting modality for document forgery detection. Establishing the identity of the printer that was employed to print a questioned document allows concluding its authenticity. This paper investigates the effectiveness of deep visual features (learned using convolutional neural networks) in characterization of the source printer. Images of printed documents are divided into small patches as well as characters for extraction of features. An off‐the‐shelf recognition engine is also integrated, allowing experiments in text‐dependent as well as text‐independent modes. Experiments are carried out on a standard data set of documents from 20 different printers and identification rates of 95.52% and 98.06% are reported using patches and characters, respectively. Furthermore, the discriminating power of different characters, as well as their combinations, is also being studied. Unlike many existing techniques, which rely on pre‐segmented characters and report results by comparing same characters only, the proposed technique works on complete images of printed documents and reports high identification rates.