Press "Enter" to skip to content

Vol. 21, no 3. P. 34-42

Reports AIAS. Vol. 21, no 3. P. 34-42. ISSN 1726-9946

Contents of this issue

DOI: 10.47928/1726-9946-2021-21-3-34-42


Research Article

Modern approaches analysis of raster drawings digitalization automation

Diukareva V.M.

Presented by academician of AIAS Z.M. Shibzukhov

St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences,
St. Petersburg

    Nowadays, manufacturers, as well as distributors, have a large amount of paper-based technical drawings. The development of information and communication technologies last year cause the task of such drawing digitalization. The task becomes popular 20 years ago in the research and development community (R&D) and now it is still opened since it has not been solved completely. Now there is a lot of scientific papers as well as a lot of commercial systems that have been created to support such a process. R&D community considers the following tasks: converting a raster drawing to vector, noise removing, etc. Some of them can recognize scanned drawings with good quality. The paper aims to analyze current research and developments for the raster drawings digitalization automation. We consider and analyze different approaches that allow supporting the digitalization process: neutral networks (YOLO, MFC-gan, AUTOFEAT, intelligent feature recognition methodology), graph theorybased approach, an algorithm based on a set of rules and Opitz coding system, an algorithm based on
field losses of the surface and the concept of bridges. There is commercial software that supports the digitalization process for the PDF that has been exported from the CAD software. However, scanned image recognition does not work fine.

Keywords: drawings, recognition, automatization.

© V.M. Diukareva, 2021

Список литературы (ГОСТ)

1. Mohamad Faizal Ab. Jabal, Mohd. Shafry Mohd. Rahim, Nur Zuraifah Syazrah Othman, Zahabidin
Jupri A comparative study on extraction and recognition method of CAD data from CAD drawings // International Conference on Information Management and Engineering, Kuala Lumpur, Malaysia: IEEE, 2009, pp. 709-713.
2. Zehtaban L., Elazhary O., Roller D. A framework for similarity recognition of CAD models // Journal of Computational Design and Engineering, 2016, no. 3, pp. 274-285.
3. Жилина Н.Д., Мошкова Т.В., Роменский С.А., Ротков С.И., Тюрина В.А. Распознавание компонент связности в задаче восстановления трехмерной модели по проекционным изображениям // Труды международной конференции по компьютерной графики и зрению “Графикон”. 2019. № 29. С. 185-187.
4. Астахов Ю.С., Емельянов А.И., Клименко С.В., Ротков С.И. Восстановление не полностью реконструированных CAD-моделей // Приволжский научный журнал. 2012. № 3(23). С. 94-99.
5. Wanga Z.,Tsumuraa K.,Saitoa Y. Recognition of hand-written mechanical drawing by multilevel neural network (MLNN) // Seventh International Conference on Production/Precision Engineering, 4th International Conference on High Technology. Chiba Japan: 1994, pp. 1-6.
6. Elyan E., Jamieson L., Ali-Gombe A. Deep learning for symbols detection and classification in engineering drawings // Neural Networks. September 2020, no. 129, pp. 91-102.
7. Инструментарий Raster Design входит в состав AutoCAD URL:
autocad/ (дата обращения: 09.01.2020)
8. PDF to DWG Converter URL: (дата обращения: 09.01.2020).
9. Scan2CAD | Raster to Vector Software | Convert Images to CAD URL: (дата обращения: 09.01.2020).
10. INKSCAPE URL: (дата обращения: 13.11.2020).
11. PlanTracer – серия программ для кадастровых инженеров URL: (дата обращения: 13.11.2020).
12. Усовершенствованная обработка данных для трехмерных изображений // Bentley Descartes URL: (дата обращения: 7.12.2020).

For citation. Diukareva V.M. Modern approaches analysis of raster drawings digitalization automation. Reports Adyghe (Circassian) International Academy of Sciences. 2021, vol. 21, no. 3, pp.  34-42. DOI: 10.47928/1726-9946-2021-21-3-34-42

Read article

©​ | 2022 | Адыгская (Черкесская) Международная академия наук