Computer Vision & Pattern Recognition
The purpose of the course is to introduce basic problems in image processing, computer vision, and pattern recognition, and to provide the students with an understanding of fundamental principles underlying the most important solutions.
The course covers the following topics: image formation (from both a photometric and geometric perspective), low-level imaging methods (filtering and edge detection), image restoration and inverse problems (in particular denoising), single and multi-view geometry for 3D reconstruction, feature extraction for object recognition, 3D surfaces and their registration. Lectures are accompanied by various examples of applications where these methods apply, and hands-on programming exercise to solve real-world problems.
The topics will be presented in the form of lectures and tutorials. Homework assignments with theoretical and practical programming exercises will be handed out, graded, and discussed in the tutorials.
The course grade is determined by the results of the homework assignments (50%) and the written final exam (50%).
- Richard Hartley and Andrew Zisserman. Multiple View Geometry in Computer Vision. Second Edition. Cambridge University Press, 2004
- Rafael C. Gonzalez and Richard E. Woods. Digital Image Processing. Fourth Edition. Pearson, 2020
- Additional material will be provided through the course homepage.