Digital Image Processing

The aim of the course is to provide the student with the theoretical and practical knowledge of digital image processing methods and techniques, ranging from classical ones up to modern deep learning architectures. The content includes image enhancement and noise reduction, morphological image analysis, image segmentation, edge detection, object recognition, semantic segmentation and other practically useful aspects (following the news in the field). Students will learn how to use existing image processing software tools to complete different image processing tasks.

Provide the student with the theoretical and practical knowledge of digital image processing methods and techniques and indicate the direction towards which the field moves and how to find the newest information.

Basic knowledge of mathematics, programming and graph theory.

1. Introduction to digital image processing and application examples. 2. Computer vision and image processing: different levels of analysis. 3. Image filtering. 4. Edge detection methods. 5. Morfological image analysis. 6. Model-based image analysis. 7. Image segmentation (classical and contemporary methods). 8. Main deep networks architectures for image analysis. 9. Resources for image analysis. 10. Advanved architectures for image analysis (e.g. graph neural networks, generative adversarial networks).

1. Depth and with of knowledge of the presented material 2. Ability to bring different topics presented in the material together 3. Ability to reason based on the provided material and ability to summarize 4. Ability to compare different methods of computer vision 5. Ability to study material on ones own 6. Ability to use material in a new task 7. Ability to find additional material for clarification of arising questions 8. Ability to read and understand research papers in the field of computer vision 9. Ability to give answers to the provided questions in a logically correct sequence (not interrupted and not contradictory). 10. Readability of written work (non-readable texts will not be evaluated) 11. Ability to choose correct methods for the solution of computer vision tasks 12. Practical demonstration of knowledge of image processing methods and skills in choosing appropriate image processing methods for a given problem. 13. Practical demonstration the ability to manipulate with implementations of image processing methods in order to solve the problem in some field of application given by a teacher. 14. Meaningfully explanation of the application of an image processing solution of an applied problem. 15. Mini-project result presentation to colleagues and the lecturer.