teaching
CMSC 91R
The Computational Image (S2024)
overview | logistics | schedule | assignments | edstem | resources
Class: Tuesday & Thursday 9:5-11:10am (SCI 204)Lab A: Tuesday 1:05-2:35pm (SCI 240)
Lab B: Tuesday 2:45-4:15pm (SCI 240)
Office Hours: Wednesday & Thursday 1-2pm and by appointment (SCI 205C)
Textbooks
- Computer Vision: Algorithms and Applications. Szeliski. Springer. 2022. ISBN: 3030343715.
- Programming Computer Vision with Python. Solem. O'Reilly. 2012. ISBN: 1449316549.
- Generative Design: Visualize, Program, and Create with JavaScript in p5.js. Gross, Bohnacker, Laub, Lazzeroni. Princeton Architectural Press. 2018. ISBN: 1616897589
- Eloquent Javascript. Haverbeke. Third Edition. ISBN: 1593279507.
- Getting Started with p5.js. McCarthy, Reas, and Fry. Maker Media. 2015. ISBN 1457186772.
- Assignments (40%): Programming assignments
- Midterms (30%): Two paper & pencil exams
- Project (20%): Team project worked on for approximately 1/3 of the term
- Participation (10%): Short weekly quizzes, critiques and homework
- Participate. There will be myriad opportunities: in class, lab, google docs, github, dropbox paper, excalidraw, office hours, edstem.
- When reading, studying, and listening, be active by taking notes and asking questions.
- Visit the professor's drop-in office hours.
- Attend class & be on time (whenever possible given COVID reality).
- Make sure to have read the required reading BEFORE class.
- Start all the assignments early.
- Check EdStem & this class website.
- Be respectful of your fellow classmates; my rule of thumb for judging whether a response is worthwhile: Is it Nice? Is it True? Is it Necessary? Pick at least two.
- Adhere to the Code of Ethics and Professional Conduct for the Association for Computing Machinery.
- Cooperate carefully and thoughtfully:
- Work within your pair & pod, and visit drop-in hours, before seeking help beyond.
- Credit work, including all sources you used from the web, other books, etc.
- Sharing ideas is encouraged, but blatantly copying work without attribution will be treated as scholastic dishonesty and receive no credit.
- Be prepared to demonstrate the theory of your program (Peter Naur).
- Keep your work backed-up and private.