Course Content and Outcomes Guides (CCOG)

CCOG for MUC 252 archive revision 202204

You are viewing an old version of the CCOG. View current version »

Effective Term:
Fall 2022

Course Number:
MUC 252
Course Title:
Computer Vision
Credit Hours:
4
Lecture Hours:
40
Lecture/Lab Hours:
0
Lab Hours:
0

Course Description

Introduces motivations, applications and techniques in Computer Vision and Digital Signal Processing. Explores the history of Computer Vision, evolving social implications, and appropriations of Computer Vision and “seeing machines” by artists, designers, and creatives. Audit available.

Addendum to Course Description

Computer Vision is commonly associated with current approaches to AI and Machine Learning, but is also a field of research with decades of history. This course intends to leverage the history of Computer Vision as a narrative through which to explore beginner and intermediate coding topics, and explore general mathematics concepts with an interactive, code-forward approach. This course will build confidence through exercises in using code to solve problems, while invoking current themes in AI within a Humanities context.

Intended Outcomes for the course

Upon completion of the course students should be able to:

  • Recount history of computer vision in context of power relations, connecting computational methods, their proliferation and cultural impact.
  • Identify use cases, potential ethical or social concerns, and common methods of deriving information from digital images.
  • Implement algorithms that transform and filter digital images to produce data.
  • Assess emergent outcomes of different ways of solving problems within large systems.

Course Activities and Design

  • Code Notebooks
  • Group/Pair Programming
  • Readings and Case Studies
  • Interactive Software
  • Process Visualizations

Outcome Assessment Strategies

  • Code Review
  • Class Participation
  • Assignments
  • Projects

Course Content (Themes, Concepts, Issues and Skills)

History of using technology to interpret images

Structure of digital representations of images

Convolution

Matrix operations

Images as digital signals

Optical Character Recognition

Eigen Faces

Probability

Statistics