Navigation

19M041DOS2 - Digital Image Processing 2

Course specification
Course title Digital Image Processing 2
Acronym 19M041DOS2
Study programme Electrical Engineering and Computing
Module
Type of study master academic studies
Lecturer (for classes)
Lecturer/Associate (for practice)
Lecturer/Associate (for OTC)
ESPB 6.0 Status elective
Condition Passed exam in Digital Image Processing from the bachelor academic studies.
The goal The objective of the course is to introduce advanced topics from digital image processing such as feature extraction and description, image classification, image analysis, object recognition and analysis of video signal. This course represents algorithmic background for development of machine vision based embedded and industrial systems.
The outcome After completing this course, students will be familiar with theoretical and practical aspects of most important algorithms in high level digital image processing and image analysis. Students will be able to develop solutions for different digital image processing problems regarding image analysis, object recognition used in embedded and industrial systems.
Contents
Contents of lectures Feature extractions and description. Feature matching. Geometric image transformations. Image registration. Optical flow. Basic concepts of pattern recognition. Image classification. Image clustering and segmentation. Introduction to artificial neural networks with applications in image analysis. Convolutional neural networks. Video signal analysis and object tracking. Scene content analysis.
Contents of exercises Exercises in computer laboratory are used for practical implementation of algorithms introduced during lectures. Students are using these techniques to solve specific tasks for the homework assignments. For the final project at the end of the course students should develop complete solution for some practical problem.
Literature
  1. R. Szeliski, Computer Vision: Algorithms and Applications, Springer, 2010 (Original title)
  2. R. Klette, Concise computer vision, Springer, 2014 (Original title)
  3. D. Forsyth and J. Ponce, Computer Vision: A Moden Approach, Pearson, 2011 (Original title)
  4. I. Goodfellow et al, Deep Learning, The MIT Press, 2016 (Original title)
Number of hours per week during the semester/trimester/year
Lectures Exercises OTC Study and Research Other classes
3 1 1
Methods of teaching Lectures. Exercises in computer laboratory. Homework assignments. Final project.
Knowledge score (maximum points 100)
Pre obligations Points Final exam Points
Activites during lectures Test paper
Practical lessons 70 Oral examination 30
Projects
Colloquia
Seminars