Course description
This course introduces the foundations and applications of computer vision. Topics include image formation, colour spaces, the human visual system, and core image processing techniques such as filtering, edge detection, segmentation, and 3D reconstruction. Students also explore artificial intelligence and machine learning methods for vision, including feature extraction, support vector machines, convolutional neural networks, and transfer learning, with applications in robotics, medical imaging, and augmented/virtual reality.
Course content
- Brief introduction to essential math topics
- Complex numbers
- Time and frequency domains
- Fourier transform
- Foundations of computer vision
- Image formation and representation
- Colour spaces and transformations
- Human visual system overview and its influence on computer vision models
- Image processing basics
- Intensity transformation
- Spatial filtering
- Frequency-domain filtering
- Introduction to classical computer vision techniques
- Edge detection
- Image pyramids and multi-scale representation
- Image restoration and reconstruction
- Morphological image processing
- Image segmentation
- 3D reconstruction
- Introduction to machine learning for computer vision
- Feature extraction
- Image classification using support vector machines
- Simple object detection with feature-based approaches
- Architecture and training of convolutional neural networks
- Transfer learning for vision tasks
- Practical applications
- Robotics and autonomous systems
- Medical imaging
- Augmented and virtual reality
Learning activities
The topics are covered through in-class lectures, labs, assignments, projects, readings, and research.
Means of assessment
Assessment will be in accordance with the Douglas College Evaluation Policy. The instructor will present a written course outline with specific evaluation criteria at the beginning of the semester. This is letter-graded course.
Evaluation will be based on the following:
|
Labs
|
10-25%
|
|
Assignments
|
0-20%
|
|
Projects
|
0-30%
|
|
Term Test(s)
|
20-35%
|
|
Final Exam
|
25-40%
|
|
Total
|
100%
|
Learning outcomes
Upon successful completion of this course, students will be able to:
- explain key mathematical concepts, image formation models, and colour space representations in computer vision;
- apply fundamental image processing techniques, including filtering, edge detection, segmentation, and morphological operations;
- analyze and interpret the role of the human visual system in the design of computer vision models;
- implement classical computer vision methods such as image pyramids, 3D reconstruction, and image restoration;
- utilize machine learning techniques for vision tasks, including feature extraction and classification with support vector machines;
- design and train convolutional neural networks, applying transfer learning for practical vision applications;
- evaluate and apply computer vision techniques in real-world domains such as robotics, medical imaging, and augmented/virtual reality.
Textbook materials
Consult the Douglas College Bookstore for the latest required textbooks and materials.
Sample textbooks and materials may include:
- Rafael C. Gonzalez and Richard E. Woods. Digital Image Processing (current edition). Pearson.