Software systems and computational methodsReference:
Optimization of information signs recognition methods for the problem of indoor navigation
Article was received:18-12-2018
Abstract.The paper proposes the solution of a number of problems related to the optimization of recognition of information signs by the correlation-extremal contour method based on the evaluation of similarity invariant with respect to affine transformations.A description is given of a speed-efficient algorithm for obtaining regions of a certain color and its parallelization. It is shown that solving this problem allows reducing both the number of objects presented for recognition and the number of standards used, as well as obtaining a better contour description of objects and, therefore, significantly increasing the speed of the recognition algorithm itself. The solution of the problem of optimization of calculations in the recognition algorithm itself is given. It is shown that one of the ways to solve this problem for a particular chosen recognition algorithm is to parallelize the computation of the similarity estimate by the affine transformation parameters. Another presented way of solving the problem of optimization of computations was focused on obtaining estimates of the similarity of the current standard with objects from the local area of the image, which is determined on the basis of the parameters of affine transformation and dimensions of the standard. It is noted that the created algorithmic software allows to solve problems of recognition of information objects in real time.
Keywords: affine transformation, optimization, color segmentation, parallel algorithm, pattern recognition, image processing, computer graphics, standart image, adaptive description, correlation-extreme contour method
This article written in Russian. You can find full text of article in Russian here .
The journal allows the author(s) to hold the copyright without restrictions. All authors automatically own full copyright in their work as soon as they create it, and current Russian Federal legislation protects them.
Licence type: Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)
The journal is an open access journal which means that everybody can read, download, copy, distribute, print, search, or link to the full texts of these articles in accordance with Creative Commons Attribution- NonCommercial 4.0 International License.
You are free to:
Share — copy and redistribute the material in any medium or format.
Adapt — remix, transform, and build upon the material The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
NonCommercial — You may not use the material for commercial purposes.
No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.