Кафедра інформатики (ІНФ)

Постійний URI для цієї колекції

Перегляд

Останні подання

Зараз показано 1 - 5 з 473
  • Документ
    Матриця відстаней для множини компонентів структурного опису як інструмент для створення класифікатора зображень
    (2023) Гороховатський, В. О.; Передрій, О. О.; Творошенко, І. С.; Марков, Т. Є.
    The subject of the paper is the methods of image classification in computer vision systems. The goal is the further development of structural classification methods in terms of introducing a system of classification features based on the values of the distance matrix for multidimensional description components. Applied methods: AKAZE keypoint detector, set theory and vector spaces methods, metric models for determining relevance for a set of multidimensional vectors, theory of data distribution formation, elements of probability theory, software modeling. Results: modifications of the image classification method based on the implementation of the formalism of distance matrices for a set of description components have been developed, integration models for the formation of classification features and actions on sets of vectors based on the distance matrix have been proposed, metric features of a set of multidimensional vectors as classification features have been established. The effectiveness of the developed modifications of the classifier depends on the choice of a subset and the number of descriptors in the description, a measure for comparing descriptions. Based on the introduction of the distance matrix, it was possible to form built-in features in the form of one-dimensional data distributions and reduce computational costs while ensuring the effectiveness of classification on the training data set. The practical significance of the work is the formation of classification models based on the distance matrix, confirming the performance of the proposed modifications using image examples, and creating a software application that applies the proposed classifiers in computer vision.
  • Документ
    Метод розпізнавання тексту з зображення
    (ХНУРЕ, 2019) Угреватов, Д. І.
    Text recognition by automated methods is one of the most popular tasks of computer image recognition. This technology is used in many areas: in government structures, commercial projects, everyday life of ordinary people, etc. Several public libraries, such as OpenCV, have now been created that allow working with digital data, but their use still requires a certain technical education. Such libraries of computer vision do not contain ready-made solutions and are only a tool for creating working algorithms.
  • Документ
    Review of text recognition algorothms
    (ХНУРЕ, 2019) Петухова, К. С.
    This work is created to consider various methods of text recognition on images. The aim of it is to categorize and analyze different algorithms. Text recognition can be defined as main technique for image labeling. In recent years machine learning and pattern recognition, which are useful for text extraction, became very popular in computer vision area. That is why a lot of new schemes and algorithms have appeared. There are a lot of different algorithms and some of them can be useful for one purpose and another for second one. That is why it is important to understand and consider variety of all these approaches and methods.
  • Документ
    Дослідження питання нормалізації геометричних перетворень на основі аналізу дескрипторів характерних точок
    (ХНУРЕ, 2019) Чугаев, А. А.
    The given work is devoted to the study of the possibility of using the image characteristic points to eliminate geometric transformations that distinguish images. This process is called normalization and has a very important practical value. Characteristic points were determined on SURF descriptor based. For experimental research, the language of JAVA, the IntelliJ IDEA development environment, OpenCV library were used. The research, carried out in the work, allows us to conclude that it is expedient to use descriptors of characteristic points for the image normalization.
  • Документ
    Застосування алгоритму feature detection для побудови доповненної реальності
    (ХНУРЕ, 2019) Танянський, О. С.
    Theory of a computer vision - the basis for the development of technologies of additional reality. The article discusses the possibility of using the algorithm of feature detection to build augmented reality. To increase the speed of the algorithms, various ways of filtering points are used to minimize their number and eliminate completely ineffective combinations