Infopaket

Models and methods of pattern recognition

ВК 1.6

Вибіркова дисципліна для ОП

First

2024/2025

7 Semester

5

Be able to use the methods of artificial intelligence, machine learning, knowledge representation in intelligent systems, genetic and evolutionary programming to solve problems of recognition, forecasting, classification, identification of control objects, etc. Be able to apply methods and algorithms of computational intelligence and intelligent data analysis in the tasks of classification, forecasting, cluster analysis, finding associative rules using software tools to support multidimensional data analysis based on DataMining, TextMining, WebMining technologies. Be able to apply knowledge representation models in modern information systems, process audio, video and text information and numerical data, including using neural network technologies.

Full-time form

Know higher mathematics, discrete mathematics, probability theory, statistics, information technology, expert systems, algorithm theory, algorithmization and programming, system modeling, intelligent data analysis, design of expert systems and decision support systems, architecture of modern information systems, methods and systems of parallel programming, decision-making methods, computer design technologies, theory of neural networks, intelligent data analysis. Have elementary skills of working with graphic editors, programming languages.

The discipline "Models and methods of pattern recognition" examines the physiological structure of the human brain and visual channel, basic definitions of the concept of pattern recognition, recognition systems, classification of recognition systems, systems without training, systems of training with a teacher, self-learning systems, recognition procedures, recognition methods, mathematical description of images, methods of selecting informative features, characteristics of images, classification using decision functions, linear decision functions, generalized decision functions, classification using distance functions, matching method with standard, reference dictionary method, Euclidean, Manhattan, Chebyshev, Mahalanobis distance, Hamming, stochastic analysis, Bayes formula, image recognition, image recognition methods, characteristic features of images, image preprocessing methods, contour selection, object identification, text recognition, biometric identification methods.

Основи теорії розпізнавання образів : навч. посіб. : у 2 ч. / А. С. Довбиш, І. В. Шелехов. – Суми : Сумський державний університет, 2015. – Ч. 1. – 109 с Pratt W.K. 2016. Digital Images Processing. Third edition. Wiley. Т. М. Басюк, В. В. Литвин, Л. М. Захарія, Н. Е. Кунанець. Машинне навчання: Навчальний посібник призначений для студентів, що навчаються за першим (бакалаврським) рівнем вищої освіти за спеціальностями галузі знань 12 „Інформаційні технології”. Львів: Видавництво «Новий Світ - 2000», 2019. ‒ 315 с. Stepan Bilan, SergeyYuzhakov. Image Processing and Pattern Recognition Based on Parallel Shift Technology.- CRC Press, Taylor & Francis Group,- 2018,- 194 p. Parker J. Algorithms for Image Processing and Computer Vision. Wiley. -2011.

Lectures, laboratory activities, individual work

The level of achievement of all planned learning outcomes is determined by the results of defense of laboratory work and individual tasks of independent work. Semester assessment of students is carried out during the semester for all types of work. The total score is formed as a weighted sum of points earned by the student for various types of work. The maximum number of points that a student can receive for work in a semester does not exceed 100 points. The final evaluation form is an exam. The exam is conducted by assigning a final grade, which is defined as the sum of points for all successfully evaluated learning outcomes. A student is not admitted to the exam if he scored less than 36 points during the semester. To pass the exam, it is mandatory to complete all laboratory work (minimum score - 51 points, maximum -85 points), independent work (minimum score - 9 points, maximum - 15 points).

Ukrainian