Victor Skuratov, Konstantin Kuzmin, Igor Nelin, Mikhail Sedankin


Today, there is a serious need to improve the performance of algorithms for detecting objects in images. This process can be accelerated with the help of preliminary processing, having found areas of interest on the images where the probability of object detection is high. To this end, it is proposed to use the algorithm for distinguishing the boundaries of objects using the Sobel operator and Kohonen self-organizing maps, described in this paper and shown by the example of determining zones of interest when searching and recognizing objects in satellite images. The presented algorithm allows 15–100 times reduction in the amount of data arriving at the convolutional neural network, which provides the final recognition. Also, the algorithm can significantly reduce the number of training images, since the size of the parts of the input image supplied to the convolution network is tied to the image scale and equal to the size of the largest recognizable object, and the object is centered in the frame. This allows to accelerate network learning by more than 5 times and increase recognition accuracy by at least 10 %, as well as halve the required minimum number of layers and neurons of the convolutional network, thereby increasing its speed.


pattern recognition; Kohonen self-organizing maps; search and recognition of objects in the image; satellite and radar images; region of interest

Full Text:



Simard, P. Y., Steinkraus, D., Platt, J. C. (2003). Best practices for convolutional neural networks applied to visual document analysis. Proceedings of the Seventh International Conference on Document Analysis and Recognition. doi:

Novikova, N. M., Dudenkov, V. M. (2015). Modelirovanie neyronnoy seti dlya raspoznavaniya izobrazheniy na osnove gibridnoy seti i samoorganizuyuschihsya kart Kohonena. Aspirant, 2, 31–34.

Narushev, I. R. (2018). Neural network on the basis of the self-organizing kochonen card as a means of detecting anomalous behavior. Ohrana, bezopasnost', svyaz', 2 (3 (3)), 194–197.

Girshick, R., Donahue, J., Darrell, T., Malik, J. (2014). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition. doi:

Girshick, R., Donahue, J., Darrell, T., Malik, J. (2016). Region-Based Convolutional Networks for Accurate Object Detection and Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38 (1), 142–158. doi:

Girshick, R. (2015). Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV). doi:

Ren, S. et. al. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 91–99.

He, K., Gkioxari, G., Dollar, P., Girshick, R. (2017). Mask R-CNN. 2017 IEEE International Conference on Computer Vision (ICCV). doi:

Redmon, J., Divvala, S., Girshick, R., Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:

Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A. C. (2016). SSD: Single Shot MultiBox Detector. Computer Vision – ECCV 2016, 21–37. doi:

Skuratov, V., Kuzmin, K., Nelin, I., Sedankin, M. (2019). Application of kohonen neural networks to search for regions of interest in the detection and recognition of objects. Eastern-European Journal of Enterprise Technologies, 3 (9 (99)), 41–48. doi:

Haykin, S. (2008). Neyronnye seti: polniy kurs. Moscow: Izdatel'skiy dom Vil'yams.

Kohonen, T. (2001). Self-organizing maps. Vol. 30. Springer Science & Business Media, 502. doi:



  • There are currently no refbacks.

Copyright (c) 2020 Victor Skuratov, Konstantin Kuzmin, Igor Nelin, Mikhail Sedankin

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

ISSN 2461-4262 (Online), ISSN 2461-4254 (Print)