5 ECTS cr
|Language of instruction
Spring, period 3.
Upon completion of the course the student
1. understands the fundamentals of image acquisition, representation and modeling
2. can utilize elementary methods of machine vision for image recognition problems
3. can use 2D transformations in model fitting and image registration
4. can explain the basics of 3D imaging and reconstruction
1. Introduction, 2. Imaging and image representations, 3. Light and color, 4. Binary image analysis, 5. Texture, 6. Local features, 7. Recognition, 8. Motion, 9. 2D models and transformations, 10. Perceiving 3D from 2D images, 11. 3D transformations and reconstruction.
|Mode of delivery
Face-to-face teaching, homework assignments.
|Learning activities and teaching methods
Lectures (24 h), exercises (16 h) and programming assignments (32 h), self-studying (61 h)
Computer Science and Engineering students and other Students of the University of Oulu.
|Prerequisites and co-requisites
521467A Digital Image Processing or an equivalent course, basic Python programming skills.
|Recommended optional programme components
521289S Machine Learning. This course provides complementary knowledge on machine learning methods needed in machine vision.
|Recommended or required reading
Lecture slides and exercise material. The following books are recommended for further information: 1) Shapiro, L.G. & Stockman, G.C.: Computer Vision, Prentice Hall, 2001. 2) Szeliski, R.: Computer Vision: Algorithms and Applications, Springer, 2011. 3) Forsyth, D.A. & Ponce, J.: Computer Vision: A Modern Approach, Prentice Hall, 2002.
|Assessment methods and criteria
The course is passed with final exam and accepted homework assignments.
Read more about assessment criteria at the University of Oulu webpage.
Numerical grading scale 1-5. Zero stands for a fail.
|Working life cooperation
Course is in Moodle: target=_blank>https://moodle.oulu.fi/course/view.php?id=1198