Method of Digitally Presented Texts Extraction from the Image of a Document and their Examination

Abstract

In this work, the problems of extracting textual information from a document image are solved. It is important to note that the work includes complex use of special knowledge in three areas: technical and forensic examination of documents; phototechnical expertise and computer-technical expertise. The article considers and demonstrates in detail the information for detecting changes in textual information (ink, toner and writing instrument pastes) from digital images. The commission of crimes in the economic sphere, as a rule, is associated with the falsification (forgery) of documents, and the increase in the document flow in the regulation of legal relations, which has been noticeable in recent years, has led to a significant increase in the number of forged documents. This is confirmed by statistical data on forensic handwriting and technical forensic examinations. Since the document is the basis of all human activity, and it contains data drawn up in a certain order and having legal significance. The problem has got many interesting solutions thanks to practical applications such as text recognition, translation, forensics and etc. Despite the fact that this problem has been dealt with for a long time, it is still missing, i.e. there is no well-developed methodology for image recognition of documents. The image of text information depends on the type of scene, type of digital camera, amount and direction of illumination, type of substrate and etc. It is important to note here that when obtaining information (from the document under study) in modern conditions, it is possible to fix the document using any device (camera, smartphone, scanner and etc.) and in any conditions (day/night, street, radiation source) that are unknown in advance. Proceeding from this, and this is a problem in modern conditions, in the study of electronic digital information of text documents. In this work, a study to solve this problem was carried out.