Ahmad M. AyazGorokhovatskyi, V.Tvoroshenko, I.Vlasenko, N.Mustafa Syed Khalid2021-10-072021-10-072021M. Ayaz Ahmad, Volodymyr Gorokhovatskyi, Iryna Tvoroshenko, Nataliia Vlasenko, Syed Khalid Mustafa (2021) The Research of Image Classification Methods Based on the Introducing Cluster Representation Parameters for the Structural Description, International Journal of Engineering Trends and Technology, 69(10), pp. 186-192.DOI: 10.14445/22315381/IJETT-V69I10P223https://openarchive.nure.ua/handle/document/17851The results of the development of high-speed methods for classifying images in computer vision systems using the description as a set of keypoints descriptors are presented. Classification methods based on the system of cluster centers parameters, which are independently constructed for etalon descriptors set, are researched. The competitive voting of the descriptors of object being recognized on a set of etalon centers is proposed. An optimal way of comparing the sets of cluster centers for an object and etalons is applied. Experimental estimation of the efficiency for the two presented classification methods in terms of computation time and classification accuracy based on the results of applied dataset processing are shown. Based on the research, a conclusion about the effectiveness of classification technologies using cluster centers for structural descriptions of images to ensure decision-making in real-time is made.encomputer visiondescriptorimage classificationkeypointORB DetectorThe Research of Image Classification Methods Based on the Introducing Cluster Representation Parameters for the Structural DescriptionArticle