Using orthogonal functions as a description transformation apparatus for image recognition of visual objects

Abstract

Research on the construction of modifications for the space of classification features based on the application of the transformation of the structural description through the decomposition in the orthogonal basis and the implementation of the distance matrix model between the components of the description can be used to improve computer vision methods. Using orthogonal functions as a tool for transforming the description demonstrated the potential for achieving substantial improvements in processing speed while preserving high levels of classification accuracy and resistance to interference.