Course Description

This is an undergraduate course the basics of machine perception (a.k.a. image processing). Topics covered will include concepts from two-dimensional signal processing (e.g., 2D Fourier transforms, z-transforms, etc.) including image filtering/restoration, edge detection, segmentation, image analysis, image compression, and image reconstruction.

Course Website, Schedule, and Lectures

The course website is at https://sparsity.ucsd.edu/172a/. This website will be used for posting the lecture slides. The schedule will also be posted there.

Canvas will be used to post assignments and store grades. Gradescope will be used for submitting assignments. Piazza will be used for course communication.

For more details about the course, please see the course syllabus.

Course Information

Lectures: Tuesdays 17:00 – 19:50 (CENTR 216)
Discussions: Mondays 17:00 – 17:50 (CENTR 212)

Instructor: Rahul Parhi (rahul@ucsd.edu)
Office: Jacobs Hall, Room 6406
Office Hours:
       Thursdays 16:00 – 17:00
       Fridays 16:00 – 17:00

TA: Niyas Attasseri (nattasseri@ucsd.edu)
Office Hours:
       Wednesdays 13:00 – 14:00
       Fridays 14:00 – 15:00
Office Hours Location: Jacobs Hall, Room 5101B

Canvas: https://canvas.ucsd.edu/courses/62410
Piazza: https://piazza.com/class/m5hdhecdrjp4dz
Gradescope: https://www.gradescope.com/courses/938339
DataHub: https://datahub.ucsd.edu

Prerequisites

This course assumes basic knowledge of linear systems fundamentals at the level of ECE 101. Some background in probability will be helpful (e.g., at the level of ECE 109). Familiarity with Python will be necessary for the programming components of the course.

Course Grade

The course grade will be determined by

• 5-8 Assignments (either “pen-and-paper” homework or programming lab exercises) (40%)
• Midterm Exam (20%)
• Final Exam (40%)
  • The final will take place on Thursday, March 20th from 19:00 – 21:59

Academic Integrity

UCSD’s Code of Academic Integrity applies to this course. It is dishonest to cheat on exams, copy other people’s work, or fake experimental results. An important element of academic integrity is fully and correctly acknowledging any materials taken from the work of others. Instances of academic dishonesty will be referred to the Office of Student Conduct for adjudication.