Learning Outcomes:

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