Application of kohonen neural networks to search for regions of interest in the detection and recognition of objects
Journal Title: Восточно-Европейский журнал передовых технологий - Year 2019, Vol 3, Issue 9
Abstract
<p>One of the most effective ways to improve accuracy and speed of recognition algorithms is to preliminary distinguish the regions of interest in the analyzed images. We studied a possibility of application of self-organizing maps and a Kohonen neural network for detection of regions of interest at a radar or satellite image of underlying surface. There is a high probability of finding an object of interest for further analysis in the found regions of interest. The definition of region of interest is necessary most of all to automate and speed up the process of search and recognition of objects of interest. The relevance is due to the increasing number of satellites. The study presents the process of modeling, analysis and comparison of the results of application of these methods for determination of regions of interest in recognition of images of aircraft against the background of underlying surface. It also describes the process of preliminary processing of input data. The study presents a general approach to construction and training of the Kohonen self-organizing map and neural network. Application of Kohonen maps and neural network makes it possible to decrease an amount of data analyzed by 15–100 times. It speeds up the process of detection and recognition of an object of interest. Application of the above algorithm reduces significantly the required number of training images for a convolutional network, which performs the final recognition. The reduction of a training sample occurs because the size of parts of an input image supplied to the convolutional network is bounded with the scale of an image and it is equal to the size of the largest detected object. Kohonen neural network showed itself more efficient in relation to this task, since it places cluster centers on the underlying surface rarely due to independence of weight of neurons on neighboring centers. These technical solutions could be used in the analysis of visual data from satellites, aircraft, and unmanned cars, in medicine, robotics, etc.</p>
Authors and Affiliations
Victor Skuratov, Konstantin Kuzmin, Igor Nelin, Mikhail Sedankin
Keywords
Related Articles
- EP ID EP666464
- DOI 10.15587/1729-4061.2019.166887
- Views 112
- Downloads 0
Exploring the process to obtain a composite based on Cr2O3–AlN using a method of hot pressing
<p>We have established the influence of heating rate of 150, 350 and 600 °C/min, pressure of 8 and 18 MPa, on the compaction process of the reaction mixture Cr<sub>2</sub>O<sub>3</sub>–15AlN<sub>nano</sub>, the hardness...
Designing adaptive PID controller non-sensitive to changes in aerodynamic characteristics of an unmanned aerial vehicle
The method of implementing an adaptive PID controller using a reference model of an unmanned aerial vehicle is presented. The unmanned aerial vehicle has a nonlinear characteristic and high sensitivity to external influe...
Analysis of technological innovations in digital marketing
<p class="a"><span lang="EN-US">The main technological innovations in digital marketing as a specific form of marketing under conditions of the informatization of society have been examined. It has been substantiated tha...
Algorithmizing the methods of basis matrices in the study of balace intersectoral ecological and economic models
<p>Ecological-economic models (such as Leontiev-Ford) play a special role in solving the fundamental problems of long-term planning, taking into account the factor of environmental management. On their basis, the task of...
The optimization algorithm for the directions of influence of risk factors on the system that manages the potential of machine-building enterprises
<p>The lines of influence of risk factors on the system of management of financial potential of machine-building enterprises were determined. Their application makes it possible to provide enterprises with complete and r...