Course Description and Overview

This seminar will survey the state of the art in computer vision through readings of original papers and implementation of selected algorithms. Students will develop their ability to convey technical content in public by taking the lead role in presenting selected individual papers. Each student will implement a significant project over the course of the semester, based upon current published work. Students will take the lead in directing the course of study as needed to support their projects. Prerequisites: CSC 212, MTH 153. Vector calculus and linear algebra are helpful but not required.

Goals

You should come out of this course with a sense of the fun possibilities, ethical issues, and technical challenges inherent in computer vision. You will learn to read and analyze a computer science research paper, and present its significant results. You may gain some familiarity with Matlab and/or NumPy. Finally, you will see the sorts of problems currently under study by researchers in computer vision.

Course Textbook

Computer Vision: Algorithms and Applications, by Richard Szeliski. You may buy a physical copy if you wish, or rely on the free PDF version.

I have additional books on computer vision that may be loaned out for short periods.

Requirements

Grading

In keeping with the student-driven design, we will follow ungrading practices in this course. This means that students will self-evaluate their performance, with guidance and feedback from the professor. A-level work means completing all expected deliverables on time and at a high level of quality. We will perform reflective exercises at several points during the semester to provide interim feedback.

The professor will only override self-assigned grades in cases where the student's assessment is clearly inconsistent with their actual performance and that of the rest of the class, or if the student does not participate adequately in the self-assessment process.

Collaboration policy: Because the details of each student's project will differ, peer consultation on technical aspects is permitted. As a guiding principle, any work submitted for grading must accurately reflect the understanding of the student presenting it. Cases where significant assistance was provided by others must always be documented clearly. Abuses of this policy will result in a referral to the Honor Board.

Course Details

Professor
Nick Howe
Ford Hall 354
585-3878

Office hours
Meeting Times
3:05-4:20 PM Mondays & 2:45-4:00 PM Wednesdays
Room
McConnell 403

Other Policies

Laptops and phones can be great tools at certain times. While laptops are not forbidden in class, having them out during discussions tends to inhibit the free flow of conversation. If you feel the need to use a laptop or phone in class, please use them judiciously, and avoid carrying out personal tasks (email, social media, etc.) that would detract from your full participation.

For accessibility reasons, we kindly ask that you refrain from wearing scented products in class.

Student Success

Smith is committed to providing support services and reasonable accommodations to all students with disabilities. To request an accommodation, please register with the Office of Disability Services at the beginning of the semester. Information on how to register and request accommodations is provided on the Smith Disability Services website.

Everyone should find success in this course. If the course isn't meeting your needs in any way, please let me know what adjustments would be helpful and I will try to accommodate. Self-care is important.