ANALYSIS OF PROPERTIES, CHARACTERISTICS AND RESULTS OF THE USE OF ADVANCED DETECTORSTO DETERMINE THE SPECIFIC POINTS OF THE IMAGE
DOI:
https://doi.org/10.26906/SUNZ.2018.1.093Keywords:
computer vision, structural recognition, special image points, ORB, BRISK methods, binary analysis method, Kohonen network, image database, software modeling, classification efficiencyAbstract
The problem being solved is of invariant recognition of visual objects with the use of structural methods based on descriptions in the form of a set of special points of the image. The analysis of the characteristics and means of software modeling ofmodern methods ORB and BRISK for the determination of special points has been carried out. A method of binary analysis forthe formation of the class centers and the subsequent classification is proposed. The program modeling of the method was compared with the Kohonen network, and the results of the developed method for the applied database of images were obtained.Downloads
References
Ethan Rublee, Vincent Rabaud, Kurt Konolige, Gary Bradski. ORB: an efficient alternative to SIFT or SURF. – Computer Vision (ICCV), IEEE International Conference on IEEE, pp. 2564 – 2571, 2011.
Stefan Leutenegger, Margarita Chli, Roland Y. Siegwart. BRISK: Binary Robust Invariant Scalable Keypoints. – Computer Vision (ICCV), pp. 2548 – 2555, 2011.
Гороховатский В.А. Исследование результативности структурных методов классификации изображений с применением кластерной модели данных / В.А. Гороховатский, Е.П. Путятин, В.С. Столяров // Радиоэлектроника, информатика, управление. – 2017. – №3 (42). – C. 78–85.
Rosten, Edward, Tom Drummond. Machine learning for high-speed corner detection. – 9th European Conference on Computer Vision (ECCV), pp. 430 – 443, 2006.
Michael Calonder, Vincent Lepetit, Christoph Strecha, Pascal Fua. BRIEF:Binary Robust Independent Elementary Features. – 11th European Conference on Computer Vision (ECCV), pp. 778 – 792, 2010.
Патин М. В. Сравнительный анализ методов поиска особых точек и дескрипторов при группировке изображений по схожему содержанию [Электронный ресурс] / М. В. Патин, Д. В. Коробов // Молодой ученый. — 2016. — №11. — С. 214-221. – Режим доступа: https://moluch.ru/archive/115/31188/.
Gorokhovatsky V.A. Intellectual Data Processing and Self-Organization of Structural Features at Recognition of Visual Objects / V.A. Gorokhovatsky, A. V. Gorokhovatsky, A.Ye. Berestovsky // Telecommunications and Radio Engineering. – 2016, Vol. 75, No 2. – P. 155–168.
Lowe, David G. Object recognition from local scaleinvariant features. – Proceedings of the International Conference on Computer Vision, pp. 1150 – 1157, 1999.
Herbert Bay, Tinne Tuytelaars, Luc Van Gool. SURF: Speeded Up Robust Features. – Proceedings of the ninth European Conference on Computer Vision, pp. 404 – 417, 2006.
Борисов Е.С. Кластеризатор на основе нейронной сети Кохонена. [Электронный ресурс]. – Режим доступа: http://mechanoid.kiev.ua/neural-net-kohonenclusterization. html /
Кручинин А. Распознавание с использованием OpenCV . – [Электронный ресурс]. 2011. – Режими доступа: http://recog.ru/library/opencv/opencvkruchinin.pdf, свободный. – Загл. с экрана.
OpenCV Open Source Computer Vision. [Электронный ресурс]. – Режим доступа: https://docs.opencv.org/master/index.html, свободный. – Загл. с экрана.
