Cyber-Physical Systems: Advances in Design & Modelling. Studies in Systems, Decision and Control, vol 259. Springer, Cham DOI https://doi.org/10.1007/978-3-030-32579-4_4
The chapter develops the concept of a textual key point, the detector of which is a certain OCR. The descriptor of a textual key point is determined. Examples of algorithms for analyzing documents, using textual key points, are given. The chapter deals with the tasks of recognized document classification, localization of images of recognized documents and comparison of images of documents for finding differences. The results of the algorithms for the data sets of the documents of the Russian Federation are given. The proposed methods allow achieving high accuracy of complexly structured documents analysis with entering document images in modern cyber-physical systems based on big data technologies.