Methods for Forensic Examination of Digital Images of Documents

Based on the approach involving the use of mathematical algorithms for information processing, this article puts forward proposals aimed at supplementing the classification of methods of forensic document examination. In particular, it is proposed to consider the following bases for classifying such methods: By the information type displayed in a document converted into digital form (digital image of a document): physical-optical methods, frequency-statistical methods, structural-geometric methods, semantic (neural network) methods, clustering methods, metadata analysis methods. By the analysis level of the information studied, displayed in a document converted into digital form (digital image of a document): low-level methods, medium-level methods, high-level methods. For each of the proposed classification bases the conditions are specified that allow a particular method to be assigned to a specific group. These conditions include, in particular: physical properties of the sensor, photosensitivity indicators, spectrum distribution analysis, object boundary analysis, use of neural networks and other artificial intelligence tools, data clustering features, file service information, etc. The classification of methods presented herein creates the scientific prerequisites for forensic examination of documents in digital form and expands the expert capabilities for solving specific tasks that arise in the course of document examination.