APPLICATION OF A CONVOLUTIONAL NEURAL NETWORK WITH A MODULE OF ELEMENTARY GRAPHIC PRIMITIVE CLASSIFIERS IN THE PROBLEMS OF RECOGNITION OF DRAWING DOCUMENTATION AND TRANSFORMATION OF 2D TO 3D MODELS

Khorolska K. Skladannyi P. Sokolov V. Korshun N. Bebeshko B. Lakhno V. Zhumadilova M.
31 December 2022 Little Lion Scientific

Journal of Theoretical and Applied Information Technology
2022 #100 Issue 24 7426 - 7437 pp.

This paper presents the results of the research related to the design of a convolutional neural network with a module of graphic primitives elementary classifiers (EC) in the tasks of drawing documentation recognition and transformation of the 2D into 3D models. An architecture of a convolutional neural network with an elementary classifiers module of graphic primitives was proposed for solving the drawing recognition and 2 → 3 transformation problem. A graphic image classifier model based on covered classes and elementary primitive classifiers has been developed to increase the effectiveness of CNN training.

Decision Support System , Information Protection , Information Security , Infrastructure Management , Organizational and Economic Support , Risk Minimization

Text of the article Перейти на текст статьи

State National University of Trade and Economics, Kyiv, Ukraine
Borys Grinchenko Kyiv Metropolitan University, Kyiv, Ukraine
National University of Life and Environmental Sciences of Ukraine, Kyiv, Ukraine
Yessenov University, Aktau, Kazakhstan

State National University of Trade and Economics
Borys Grinchenko Kyiv Metropolitan University
National University of Life and Environmental Sciences of Ukraine
Yessenov University

10 лет помогаем публиковать статьи Международный издатель

Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026