Spring, period 3.
After completing the course, student
1. can utilize common machine vision methods for various image analysis problems2. can detect and recognize objects using features computed from images3. can use motion information in image analysis4. can use model matching in image registration and object recognition5. can explain the basics of geometric computer vision6. can calibrate cameras7. can use stereo imaging for 3D reconstruction8. can use Matlab for implementing basic machine vision algorithms
Course provides an introduction to machine vision, and its applications to practical image analysis problems. Common computer vision methods and algorithms as well as principles of image formation are studied. Topics: 1. Introduction, 2. Imaging and image representation, 3. Color and shading, 4. Image features, 5. Recognition, 6. Texture, 7. Motion from 2D image sequences, 8. Matching in 2D, 9. Perceiving 3D from 2D images, 10. 3D reconstruction.
Face-to-face teaching, homework assignments.
Lectures (20 h), exercises (16 h) and Matlab homework assignments (16 h).
Computer Science and Engineering students and other Students of the University of Oulu.
521467A Digital Image Processing
521289S Machine Learning. This courses provide complementary information on machine learning methods applied in machine vision. It is recommended to be studied simultaneously.
Lecture notes and exercise material. The following books are recommended for further information: 1) Shapiro, L.G., Stockman,G.C.: Computer Vision, Prentice Hall, 2001. 2) R. Szeliski: Computer Vision: Algorithms and Applications, Springer, 2011. 3) D.A. Forsyth & J. Ponce: Computer Vision: A Modern Approach, Prentice Hall, 2002.
The course is passed with final exam and accepted homework assignments.
Read more about assessment criteria at the University of Oulu webpage.
The course unit utilizes a numerical grading scale 1-5. In the numerical scale zero stands for a fail.