Стиснення опису зображення за критерієм інформативності

Abstract

A method of data reduction for image classification problems is developed. It is based on the introduction of metric criteria for assessing the informativeness of the elements of the structural description of the image, which shortens the description and speeds up the calculation. The classification time for the considered experimental descriptions decreases proportionally with decreasing description volume. The conducted modeling confirms the efficiency and effectiveness of the proposed method in terms of ensuring the quality of classification using the means of reduction.