Graduate Education Institute · Computer Science and Engineering · Master
Course Objective
The purpose of machine vision is to calculate the properties of the three-dimensional world from digital images. Problems in this area include defining the 3D shape of an environment through the analysis of images and videos, identifying how objects move, and recognizing familiar people and objects.
Course Content
low-level image perception aspects, such as image formation, cameras, color and continue with mid-level vision topics, such as interest point detection and local feature extraction, introduce the fundamentals of high-level vision tasks, such as face detection/recognition, object recognition, and human motion analysis.
Required Resources
Computer Vision: Algorithms and Applications, by Richard Szeliski, Springer, 2010.
Computer Vision: A Modern Approach (2nd edition), by D.A. Forsyth and J. Ponce, Prentice Hall, 2011.
Recommended Resources
Learning OpenCV, by Gary Bradski & Adrian Kaehler, O'Reilly Media, 2008.
Pattern Classification (2nd Edition), by R.O. Duda, P.E. Hart, and D.G. Stork, Wiley-Interscience, 2000.
Course Learning Outcomes
- Use mathematical modeling tools to represent digital images.
- Explain some successful applications of computer vision algorithms and how they work.
- Use stereo vision techniques and optical flow methods to study motion.
- Solve basic computer vision problems using programs such as MATLAB, C / C ++ and OpenCv.
- Applying morphological operations for shape recognition and template matching Uses advanced algorithms such as support vector machines and artificial neural networks for object recognition and classification.
- Perform transformations and filtering operations in time and frequency domains to obtain the desired outputs.
Core Area Distribution
Teaching Methods
Assessment & Evaluation
ECTS / Workload
| Activity | Quantity | Duration (h) | Total Workload |
|---|---|---|---|
| Course Duration (Including Exam Week) | 16 | 3 | 48 |
| Out of Class Study Period | 16 | 3 | 48 |
| Midterm | 2 | 35 | 70 |
| Quiz | 0 | 0 | 0 |
| Assignment | 3 | 15 | 45 |
| Practice | 0 | 0 | 0 |
| Final | 2 | 50 | 100 |
Course Schedule
| Week | Subject | Preparation |
|---|---|---|
| 1 | Introduction to machine vision | lecture notes |
| 2 | Basic concepts + Camera Calibration | lecture notes |
| 3 | Basic concepts + Camera Calibration | lecture notes |
| 4 | Image processing +Filters and edge detection | lecture notes |
| 5 | Filters and edge detection | lecture notes |
| 6 | Features | lecture notes |
| 7 | Features | lecture notes |
| 8 | Midterm Exam | Midterm Exam |
| 9 | Features + Stereo Vision | lecture notes |
| 10 | Stereo Vision | lecture notes |
| 11 | Stereo Vision | lecture notes |
| 12 | Motion | lecture notes |
| 13 | Motion | lecture notes |
| 14 | Object Modeling and Recognition | lecture notes |
| 15 | Object Modeling and Recognition | lecture notes |
| 16 | Final | Final |