The aim of the course is to give an introduction to the basic algorithms used in digital image processing and computer vision. The lectures in the first part of the semester cover various topics from the classical image processing era, such as image representation, 2D convolutions, image enhancement and recovery, texture analysis and Fourier space based image filtering. The second part of the course is dedicated to more recent tools, including Meanshift and Markov Random Field segmentation models, extraction and utilization of SIFT, HOG and BLP descriptors, and the basics of using machine learning approaches for image recognition problems. For attending this course, no prior knowledge of image processing or computer vision is assumed. However, the participating students need to have a good programming background, and experience with different data structures, linear algebra, vector calculus, and the basics of signal processing.
For more information, please download the teaching guide HERE