ИССЛЕДОВАНИЕ ПРИМЕНИМОСТИ НЕЙРОНЕЧЕТКОГО И НЕЙРОСЕТЕВОГО МОДЕЛИРОВАНИЯ ДЛЯ ВЫДЕЛЕНИЯ И РАСПОЗНАВАНИЯ КОНТУРОВ НА ИЗОБРАЖЕНИЯХ

Abstract

Listen

Translate article

The article describes a technique for recognizing objects in images based on neuro-fuzzy modeling of decision-making on pixel contours and neural network classification of selected object contours using features calculated by the fast Fourier transform. The proposed technique is based on solving four problems: building and using a neuro-fuzzy model for making a decision on an image pixel contour depending on the brightness difference of its eight surrounding pixels, tracking individual contours, forming a feature vector, and neural network classification of features of the contour in question. When describing the neuro-fuzzy model, the linguistic variables used, the type of fuzzy production rules, the main idea of the rule base formation algorithm, and the difference and feature of the genetic algorithm used are described. To track individual contours in a binary image, the Moore method is used, which allows obtaining an array containing sets of coordinates describing individual contours. The features of the selected contour are formed using the Fourier transform. The obtained features are invariant with respect to displacement, scaling, and rotation. The article describes the basic idea of the algorithm for constructing a training sample for a neural network classifier model. It describes the composition of the developed software package that implements the proposed method. It describes an experiment that determines the possibility of using the developed neuro-fuzzy model to detect continuous closed (without gaps) contours on a noisy image with a small PSNR value. Experimental studies on images taken from the open dataset “Kaggle - Roundabout Aerial Images for Vehicle Detection” and other sources have shown the possibility of using the developed neuro-fuzzy model for images with a “similar” distribution of the brightness gradient. It is concluded that further research is needed to determine the criterion of “similarity” of the distribution of the brightness gradient of neighboring pixels in an image for adequate application of the neuro-fuzzy model.