After taking this course, you will be able to:
- Explain intuitively and mathematically the followingbasic ideas in computer vision and implement relevant modules in code:
- The geometry and physics of image formation
- Statistical properties of images
- Basic image processing techniques: Edge detection, corner detection, convolution
- For any computer vision problem, including reconstruction, reorganization or recognition problems, answer the following questions:
- What are the inputs and required outputs?
- Why should we care about this problem?
- What are the constraints / challenges?
- What are the cues that we can use?
- How do we design an algorithm using these cues?
- What are the limitations of the algorithm used?
- Do good research, including the following skills:
- Critiquing research papers
- Choosing a research problem to work on
- Performing careful experiments: designing and testing hypothesis
- Writing and presenting technical work
- Understanding the impact of and effect on bias and inequalities; ethical implications of AI research