Transforming image descriptions as a set of descriptors to construct classification features

Abstract

The article develops methods to solve a fundamental problem in computer vision: image recognition of visual objects. The results of the 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 are presented. The application of the system of orthogonal functions as an apparatus for the transformation of the description showed the possibility of a significant gain in the speed of processing while maintaining high indicators of classification accuracy and interference resistance. The synthesized feature systems’ effectiveness has been confirmed in terms of a significant increase in the rate of codes and a sufficient level of efficiency. An experimental example showed that the time spent calculating the relevance of descriptions according to their modified presentation is more than ten times shorter than for traditional metric approaches. The developed classification features can be used in applied tasks where the time of visual objects’ identification is critical.