ICS 483: Computer Vision
Description: Introductory course in computer vision. Topics include image formation, image processing and filtering, edge detection, texture analysis and synthesis, binocular stereo, segmentation, tracking, object recognition and applications.
Objectives: See course-specific learning outcomes.
Course Learning Outcomes
- Students understand basic concepts, terminology, principles, models and methods in computer vision and image understanding.
- Students have a broad knowledge for understanding advanced topics and scientific literature in the field of computer vision.
- Students can describe the problems and basic methods of edge detection, texture analysis, stereo analysis, image segmentation, tracking, image retrieval, object recognition.
- Students can implement and systematically test fundamental methods/algorithms of computer vision, image processing, and image analysis.
- Students can design a computer vision system for a specific problem.
- Students can present applications of computer vision systems and identify the limitations of current vision systems.
Program Learning Outcomes
- a. Students can apply knowledge of computing and mathematics appropriate to the discipline
- c. Students can design, implement, and evaluate a computer-based system, process, component, or program to meet desired needs
- i. Students can use current techniques, skills, and tools necessary for computing practice
- j. An ability to use and apply current technical concepts and practices in the core information technologies. [BA IT only]
Prerequisites: 212 and 311, or consent.
Textbook(s): Computer Vision: A Modern Approach, Second Edition, byDavid A. Forsyth and Jean Ponce, Publisher: Pearson, ISBN-13: 978-0136085928
Grading: Homework Assignments (25%)
Course Project (30%)
Midterm Exam (20%)
Final Exam (25%)
Policies: Late policy: If you hand in late work without approval of the instructor you may receive zero credit.
Schedule
- Week 1. Introduction
- Week 2. Local Shading Models
- Week 3. Color: Physics, Color Perception, Color Spaces
- Week 4. Linear Filters and Convolution
- Week 5. Edge Detection
- Week 6. Texture
- Week 7. Basic Multi-view Geometry, Stereo
- Week 8. Segmentation: Clustering, Midterm Exam
- Week 9. Segmentation: Model Fitting
- Week 10. Segmentation: Probabilistic Methods
- Week 11. Tracking
- Week 12. Template Matching using Classifiers
- Week 13. Object Recognition
- Week 14. Image Retrieval
- Week 15. Image-based Rendering
- Week 16. Project Presentation
- Week 17. Final Exam