This course provides an overview of geometric, statistical and morphological methods in computer vision and image understanding. The course aims at covering the fundamental principles of image processing, multiple view geometry and probabilistic techniques as related to applications in the scope of robotic and machine vision and image processing by introducing the student to classical problems found in the literature, such as segmentation and grouping, matching, classification and recognition.

By the end of this course, you should be able to:

1. To introduce the mathematical and theoretical foundations of image processing and computer vision. These include 2D image signal processing, multiview geometry, some standard machine learning algorithms widely used in computer vision.
2. To develop a practical appreciation of the main algorithms and methods for image processing, image clustering, object recognition and detection.
3. To understand the uses and limitations of computer vision techniques through practical case studies.
4. To have a knowledge about state-of-the-art theories in computation vision.

Permission of the course coordinator

Recommended reading:

• D. Forsyth and J. Ponce. Computer Vision: A Modern Approach. Prentice Hall, 2002.
• R. Hartley, A. Zisserman. Multiple View Geometry in Computer Vision. 2nd Edition, Cambridge University Press, 2004.
• J. C. Russ. The Image Processing Handbook. 4th Edition, CRC, 2002.

You might find these books useful (but not required). You can borrow these books from ANU library, there is at least 1 copy available for each.