CMPSCI 670: Computer Vision
Offering: Fall, 2017
Overview
Overview
This course will explore current techniques for the analysis of visual data (primarily color images). In the first part of the course we will examine the physics and geometry of image formation, including the design of cameras and the study of color sensing in the human eye. In each case we will look at the underlying mathematical models for these phenomena. In the second part of the course we will focus on algorithms to extract useful information from images. This includes detection of reliable interest points for applications such as image alignment, stereo and instance recognition; learning representations of images for recognition; and principles for grouping and segmentation. Time permitting we will look at some additional topics at the end of the course.
Course assignments will highlight several computer vision tasks and methods. For each task you will construct a basic system, then improve it through a cycle of error analysis and model redesign. There will also be a final project, which will investigate a single topic or application in greater depth. This course assumes a good background in basic probability, linear algebra, and ability to program in MATLAB. Prior experience in signal/image processing is useful but not required.
Logistics
- Instructor: Subhransu Maji (CS 274)
- TA: Chenyun Wu (chenyun@cs.umass.edu)
- Class hours: Tuesday/Thursday 1:00PM - 2:15PM, Marston Hall, 132
- Instructor office hours: Monday 3:30PM - 4:30PM, CS 272
- TA office hours: Monday 2:00PM - 3:00PM, CS 207 (cube 1)
- All the lecture materials, homework assignments, and other resources will be posted on moodle. Registered students can acccess the moodle page here.
- All discussions and annoucements will be posted on piazza. You can sign up for piazza here.
Textbooks
There is no required textbook for this class. The books below are useful references.- Computer Vision: A Modern Approach by David Forsyth and Jean Ponce (2nd ed.)
- Computer Vision: Algorithms and Applications, by Richard Szeliski (online copy).
Additional resources
- Matlab resources
- Vector geometry notes by Denis Sevee
- Linear algebra review (via David Kriegman)
- Random variables review (via David Kriegman)
Grading
Grading will be based on mini-projects(4-5), final project/final exam, weekly homeworks, and class participation.Override waitlist
If you need to sign up on the override waitlist, make sure to do it on the CS department's form at: www.cs.umass.edu/overrides. Make sure to carefully describe your reason to take the course.Tentative syllabus
- Week 1: Introduction
- Week 2: Pinhole camera model, lenses, sensors
- Week 3: Light, color, shading
- Week 4: Signal processing
- Week 5: Filtering and applications
- Week 6: Image alignment
- Week 7: Optical flow
- Week 8: Recognition and image representation
- Week 9: Decision trees, bagging, random forests
- Week 10: Linear classifiers, loss functions, neural networks, convolutional neural networks
- Week 11: Image classification, object detection
- Week 12: Texture, materials, style transfer, 3D shape understanding
- Week 13: Advanced topics (TBD)
Past offerings at the university
- Fall 2016, Instructor: Subhransu Maji