Course Info
Instructor: Prof. Jihoon Ryoo (Jihoon.ryoo@sunykorea.ac.kr, https://sites.google.com/site/jihoonryoo/ ), C413
When: 3:30-4:50 Tuesday/Thursday
Where: B314
Class website: CSE327 Computer Vision for SUNY Korea at Google Classroom (nqrsu3f)
Office hours: Tuesday/Thursday 2-3 pm (an hour before the class), by appointment if necessary
Textbook: Computer Vision: Algorithms & Applications by Richard Szeliski; Springer (ISBN # 978-1848829343) free PDF version available by the author https://szeliski.org/Book/
Grading Policy
Grades will be assigned based on the following formula, with cut-offs determined by my opinion of students on the boundary.
Programming Assignments – 30% (10% points of 3 assignments)
Midterm 1 – 20%
Midterm 2 – 20%
Final Project – 25%
Attendance - 5%
Quizzes – extra points
*The weights are approximate and subject to change
Programming Assignments
There will be three (or four) programming assignments over the course of the semester. All assignments should be done by only you. Assignments will be graded based on your effort (EXCELLENT/PASS/MARGINAL/FAIL), the incorrect answer will be accepted but copied submission will consider as a violation. Please try and practice. You must submit your solution at Google classroom before the due date. No late acceptance.
Exams
My exam strategy is as follows. Programming assignments and midterm exam problems will be drawn from the coursework. Thus the correct way to study for this course is to review these problems and figure out how to solve them. The more you work, the better your grade will be. The midterm will be closed book, but there is no need to memorize solutions. Once you have solved them once you should be able to reconstruct them on demand. A page of (you can use front and back of the A4 or equivalent paper size) cheating sheet is allowed in the exams.
Rules of the Games
1. We will use Google classroom as a question and answer platform this semester. That said, I will be doing as little as possible with it, so students will have to fill the void. The Google classroom link is given above.
2. The best way to learn the material is by solving problems. You are encouraged to work in pairs, for the best way to understand the subtleties of the homework problems is to argue about the answers. Each of you should look at all the problems independently, and not just divide the list into two parts each time. Don't be a leech and let your partner do all the work. Unless you learn how to solve problems, I promise that you will get burned on the exams and thus for your final grade.
3. The partner system relies upon a certain maturity among the students. If you don't have a partner, tell me and I will hook you up with one. If you are having trouble with your partner and want a divorce, tell me and I will set you up with a new one. I will act as a broker but not as a counselor. I do not want to hear what a louse your old partner is, and you will get a dirty look from me when you demand a divorce regardless of who was at fault.
Only one solution to the assignment per pair should be turned in. Unless announced otherwise in class, any solution to a part of a homework problem which takes more than one side of a sheet of paper will not be graded. This is to save you the ordeal of trying to impress with volume instead of quality.
4. Even if you discuss them with your classmates, you should turn in your own code and write-up. Do not share your code! Final projects can be done by one or two people. Two people projects will be scaled accordingly. There will be 3 free late dates for the semester. After that there will be 10% penalty per day.
5. If you have a physical, psychological, medical or learning disability that may impact your course work, please contact Disability Support Services office. They will review your concerns and determine, with you, what accommodations are necessary and appropriate. All information and documentation of disability is confidential.
Students who require assistance during emergency evacuation are encouraged to discuss their needs with me.
6. Each student must pursue his or her academic goals honestly and be personally accountable for all submitted work. Representing another person's work as your own is always wrong. Any suspected instance of academic dishonesty will be reported to the Academic Judiciary. For more comprehensive information on academic integrity, including categories of academic dishonesty, please refer to the academic judiciary website at: http://www.stonybrook.edu/uaa/academicjudiciary
Adopted by the Undergraduate Council September 12, 2006
Intended Audience
This course is intended for undergraduate students with interests in all areas of Visual Computing, such as Computer Vision, Computer Graphics, Visualization, Biomedical Imaging, Robotics, Virtual Reality, Computational Geometry, Optimization, Deep Learning, HCI. Prerequisites include a foundation in Linear Algebra and Calculus, and the ability to program. We will be programming in Python (OpenCV, NumPy, SciKit) and Matlab.
To be updated accordingly.