The article suggests an algorithm of boundary extraction based on image clustering. In the process of clustering, the image is decomposed into simply connected regions based on pixel color. Edges of the regions are considered as the boundaries. The proposed approach allows obtaining welldefined boundaries without blurring. The algorithm is highly resistant to impulse noise. Keywords: boundary extraction, edge detection in an image. Сведения об авторах Белим Сергей Викторович, д.ф.-м.н., профессор, заведующий кафедрой информационной безопасности Омского государственного университета им. Ф.М. Достоевского. Область научных интересов: обработка изображений, интеллектуальный анализ данных, системы защиты информации.
This article considers the problem of image segmentation based on its representation as an undirected weighted graph. Image segmentation is equivalent to partitioning a graph into communities. The image segment corresponds to each community. The growing area algorithm search communities on the graph. The average edge weight in the community is a measure of the separation quality. The correlation radius determines the number of next nearest neighbors connected by edges. Edge weight is a function of the difference between color and geometric coordinates of pixels. The exponential law calculates the weights of an edge in a graph. The computer experiment determines the parameters of the algorithm.
This article proposes an algorithm for recognizing road signs based on a determination of their color and shape. It first searches for the edge segment of the road sign. The boundary curve of the road sign is defined by the boundary of the edge segment. Approximating the boundaries of a road sign reveals its shape. The hierarchical road sign recognition system forms classes in the form of a sign. Six classes are at the first level. Two classes contain only one road sign. Signs are classified by the color of the edge segment at the second level of the hierarchy. The image inside the edge segment is cut at the third level of the hierarchy. The sign is then identified based on a comparison of the pattern. A computer experiment was carried out on two collections of road signs. The proposed algorithm has a high operating speed and a low percentage of errors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.