2021, issue 4, p. 51-60

Received 09.12.2021; Revised 13.12.2021; Accepted 21.12.2021

Published 30.12.2021; First Online 27.01.2022

https://doi.org/10.34229/2707-451X.21.4.6

Previous  |  FULL TEXT (in Ukrainian)  |  Next

 

MSC 90C15

Two Approaches for Recognizing the Structure of Block Diagrams

Kateryna Sosnenko

V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine, Kyiv

Correspondence: This email address is being protected from spambots. You need JavaScript enabled to view it.

 

Introduction. Working with graphic images is an essential element of almost any modern computer-aided design systems.

The result of neural network, including deep image processing, can be recognition of the belonging classes of objects present on them. Objects of the real world require large expenditures for the development and implementation of highly specialized computer vision systems.

In recent years, there has been an improvement of the quality characteristics obtained in the field of technical vision. This is made possible by artificial neural networks.

The article deals with the recognition of a flat, black and white flowchart image. These are two-dimensional images or their selected parts, which are displayed in an arbitrary graphic format by system means on a computer monitor screen. Basic block diagram shapes: rectangle, rhombus, parallelogram, circle, ellipse (oval), etc.

The purpose of the article is to solve the problem of graphic image recognition. The systems for the recognition of graphic images include modern systems of computer-aided design, management and document management. The article has formed a basic set of training and test images of block diagram nodes. Neural network models are proposed to improve the detection accuracy of block diagram nodes based on fully connected and convolutional neural networks.

Results. The basic procedures of the block diagram image recognition algorithm were partially tested at the software level, and allow us to conclude the effectiveness of the proposed structural methods. A comparative analysis of neural network and syntactic structural approaches for solving this problem is carried out.

Conclusions. Two methods of recognizing flat graphic figures and recognizing connections between figures in flowcharts are proposed: a method of recursive traversal of all branches of the tree of the current union of connections between figures and the figures themselves, and also a study was carried out for the created neural network in PyTorch to solve this problem using trained neural network methods.

 

Keywords: image recognition, convolutional neural networks, syntactic analysis.

 

Cite as: Sosnenko K. Two Approaches for Recognizing the Structure of Block Diagrams. Cybernetics and Computer Technologies. 2021. 4. P. 51–60. (in Ukrainian) https://doi.org/10.34229/2707-451X.21.4.6

 

References

           1.     Howard A.G., Zhu M., Chen B., Kalenichenko B., Wang W., Wey T., Andreetto M., Adam H. MobileNets: Efficient convolutional neural networks for mobile vision applications, 2017. https://arxiv.org/abs/1704.04861 (accessed: 09.12.2021)

           2.     Hunt E. Artificial Intelligence. М .: Mir, 1978. 560 p. (in Russian)

           3.     US patent # 6775411, class. IPC G 06 K 9/62, dated 13.01.2005.

           4.     Fu K. Structural methods in pattern recognition. M .: Mir, 1977. 320 p. (in Russian)

           5.     Chichirin E.N. Block diagram graphic structure recognition. Computer tools, networks and systems. 2017. 16. P. 87–96. (in Russian) http://dspace.nbuv.gov.ua/handle/123456789/131513

           6.     LeCun Y. LeNet-5, convolutional neural networks. November 2015. LeNet-5, convolutional neural networks. (accessed: 09.12.2021)

           7.     Palagin O.V., Chichirin E.M., Sosnenko K.P. The method of recognizing the structure of flat graphic images. Patent for a utility model # 13061. (in Ukrainian)

           8.     Chichirin E.M., Sosnenko K.P. Neural network modeling of graphic circuit recognition processes. Computer tools, networks and systems. 2019. 18. P. 79–85. (in Ukrainian) http://dspace.nbuv.gov.ua/handle/123456789/168481

           9.     Palagin O.V., Semotyuk M.V., Chichirin E.N., Sosnenko K.P. Modeling environment for creation and adjustment of digital processing systems. Control Systems and Computers. 2013. 1. P. 37–41, 70. (in Russian) http://usim.org.ua/arch/2013/1/5.pdf

       10.     Canziani A., Paszke A., Culurciello E. An analysis of deep neural network models for practical applications. ISCAS, 2017. https://arxiv.org/abs/1605.07678 (accessed: 09.12.2021)

 

 

ISSN 2707-451X (Online)

ISSN 2707-4501 (Print)

Previous  |  FULL TEXT (in Ukrainian)  |  Next

 

 

 

© Website and Design. 2019-2021,

V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine,

National Academy of Sciences of Ukraine.