🙋♀️ Syllabus for Spring 2024 🙌
This course is an introduction to those areas of Artificial Intelligence that deal with fundamental issues and techniques of computer vision and image processing. The emphasis is on physical, mathematical, and information-processing aspects of the vision. Topics to be covered include image formation, edge detection and segmentation, convolution, image enhancement techniques, extraction of features such as color, texture, and shape, object detection, 3-D vision, and computer vision system architectures and applications. Together, we will explore fascinating topics related to Computer Vision and Image Processing, including Optical Image Formation, Feature Extraction, Classification, and Recognition.
Instructor
| Name | Title | |
|---|---|---|
 |
Assistant Professor |
Spring 2024 Schedule 
| Weeks | Tuesday | Thursday |
|---|---|---|
|
Week 01 |
- - |
1/25 Lec 01: History, Overview |
|
Week 02 |
1/30 Lec 02: Camera Model |
2/1 Lec 03: Coloring |
|
Week 03 |
2/6 Lec 04: Warping |
2/8 Lec 05: Filtering |
|
Week 04 |
2/13 Lec 06: Morphology |
2/15 Lec 07: Edge Detection |
|
Week 05 |
2/20 Lec 08: Pyramids & Histogram |
2/22 Lec 09: Feature |
|
Week 06 |
2/27 Lec 10: Hough Transform |
2/29 Lec 11: Alignment and Fitting |
|
Week 07 |
3/5 Lec 12: RANSAC |
3/7 Lec 13: Stitching |
|
Week 08 |
3/12 Lec 14: Optical Flow |
3/14 Lec 15: Epipolar Geometry |
|
Week 09: 03/19 - 03/21 SPRING BREAK |
||
|
Week 10 |
3/26 Lec 16: Stereo Vision |
3/28 Lec 17: Texture |
|
Week 11 |
4/02 Lec 18: Segmentation |
4/04 Lec 19: Classification and Recognition I |
|
Week 12 |
4/09 Lec 20: Classification and Recognition II |
4/11 Lec 21: Instance Retrieval |
|
Week 13 |
4/16 Lec 22: Object Detection |
4/18 Lec 23: Face Detection, Boosting |
|
Week 14 |
4/23 Lec 24: Multi-layer Perceptron |
4/25 Lec 25: Intro to Deep Learning |
|
Week 15 |
4/30 No Class |
5/02 No Class |
|
Week 16 |
5/07 Final Exam Recap |
5/09 No Class |
|
Week 17 |
5/14 Final Exam |
|
Projects
Homeworks
Acknowledgement
Many materials are derived from Prof. David Doermann’s course slides. We give special thanks to Prof. Junsong Yuan and Prof. Nalini Ratha for providing fruitful suggestions. We also thank numerous generous researchers for contributing to the contents, which include but are not limited to K. Kitani, K. Grauman, S. Seitz, S. Marschner, M. Hebert, Fei-Fei Li, L. Lazebnik, R. Szeliski, A. Efros, A. Oliva, B. Leibe, D. Hoiem, A. Moore, and D. Lowe, etc.
