This course provides a foundation in computer vision and image understanding. Through a mix of theory and hands-on coding, students will learn the fundamental techniques used to process and analyze visual information. Tools include Python, OpenCV, and deep learning frameworks like PyTorch or TensorFlow.
- Level: Foundation / Undergraduate
- Duration: 10–12 weeks
- Delivery: Lectures, Labs, Assignments, Capstone Project
- Tools: Python, OpenCV, PyTorch or TensorFlow
- Instructor: Nimol Thuon
By the end of this course, students will be able to:
- Understand the principles of computer vision and image understanding
- Apply image processing techniques for feature extraction
- Implement basic ML and DL models for vision tasks
- Analyze and evaluate computer vision pipelines
- Solve real-world problems using vision-based applications
| Week | Title | Page | Google Colab |
|---|---|---|---|
| 1 | Introduction to Computer Vision | 📄 Week Page | 💻 Code |
| 2 | Image Formation and Representation | 📄 Week Page | 💻 Code |
| 3 | Image Processing Fundamentals | 📄 Week Page | 💻 Code |
| 4 | Feature Extraction and Matching | 📄 Week Page | 💻 Code |
| 5 | Geometric Vision and Camera Models | 📄 Week Page | 💻 Code |
| 6 | Classical Machine Learning for Vision | 📄 Week Page | 💻 Code |
| 7 | Deep Learning for Image Understanding | 📄 Week Page | 💻 Code |
| 8 | Object Detection | 📄 Week Page | 💻 Code |
| 9 | Image Segmentation | 📄 Week Page | 💻 Code |
| 10 | Applications and Ethics | 📄 Week Page | 💻 Code |
| 11–12 | Capstone Project | 📄 Week Page | 💻 Code |
- What is Computer Vision?
- Image Understanding vs. Image Processing
- Applications and Real-World Impact
- History and Evolution
- 📝 Assignment: Research report on vision applications
- Color Spaces: RGB, HSV, Grayscale
- Resolution and Coordinate Systems
- Camera Sensors and File Formats
- Lab: Load and manipulate images with OpenCV
- Brightness & Thresholding
- Filtering: Smoothing, Sharpening
- Edge Detection: Sobel, Prewitt, Canny
- Histogram Equalization
- Lab: Apply filters and detect edges
- Keypoint Detection: Harris, FAST
- Descriptors: SIFT, SURF, ORB
- Feature Matching Techniques
- Lab: Match features between images
- OCR and Document Understanding
- Bias in Facial Recognition
- Privacy in Medical Imaging
- Ethical Considerations
- 📝 Assignment: Write a position paper on ethics in vision
- Define a project
- Implement and evaluate it
- Present findings
- 🎓 Deliverables: Code, Report, and Presentation
| Component | Weight |
|---|---|
| Assignments & Quizzes | 25% |
| Labs & Code Submissions | 25% |
| Midterm Assessment | 20% |
| Final Project | 30% |