Aerospace Instrument-Making Annotation << Back ORIENTATION FINDING AND RECOGNITION OF PARTIALLY OCCLUDED OBJECTS BY THE VISIBLE PART OF THE COUNTOR USING DISCRETE FURIER TRANSFORM A.E. Artemyev The article proposes a method for analyzing the contours of objects for use in computer vision systems, which allows determining the orientation of objects partially occluded by other objects and simultaneously recognizing them. Processing is performed on the visible part of the contour using the discrete Fourier transform (DFT). The essence of the method is to use the DFT of the contour part (in the case when the object is occluded by another) and the DFT of the object’s reference contour to calculate the orientation of the observed object relative to the reference one by solving a polynomial equation, while finding the solution is also an object recognition fact. The method can be used, in particular, in aircraft identification systems and in short-range navigation systems and accurate landing of unmanned aerial vehicles (UAV). Also, the method can be used for fuzzy search of sequences in a certain data array. In the paper developed a mathematical apparatus and performed modeling in the MATLAB environment. Key words: partially occluded, recognition, fuzzy search, computer vision, orientation, discrete Fourier transform, air vehicle, unmanned aerial vehicle (UAV). DOI: 10.25791/aviakosmos.06.2019.672 Contacts: E-mail: arsoft@mail.ru Pp. 03-12.