CMPSCI 370: Introduction to Computer Vision

Offering: Spring, 2017

This introductory computer vision class will address fundamental questions about getting computers to "see" like humans. We investigate questions such as -- What is the role of vision in intelligence? How are images represented in a computer? How can we write algorithms to recognize an object? How can humans and computers "learn to see better" from experience? We will write a number of basic computer programs to do things like recognize handwritten characters, track objects in video, and understand the structure of images.

The course will introduce a number of key concepts, techniques and algorithms. The focus will be on the mathematical foundations rather than the use of software packages as black box. The course requires appropriate mathematical background in probability and statistics, calculus, linear algebra. Prior familiarity with Matlab will be helpful, but not required. Students will be taught basic programming using Matlab during the course. The course has the following official prerequisites: CMPSCI 240 or CMPSCI 383 with a 'C' or better.

Logistics

• Class hours: Tuesday/Thursday 11:30AM - 12:45PM, LGRT 121
• TA office hours: Chenyun Wu, Monday 2-3PM CS 270
• Instructor office hours: Subhransu Maji, CS 274 (Tuesday after class)
• 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).

Grading

We will use the following grading scheme: homework (60%), mid-term (15%), final (25%)

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: Color perception
• Week 4: Signal quantiaztion, color maps, basic image processing
• Week 5: Edge detection
• Week 6: Corner detection
• Week 7: Image features
• Week 8: Image transformation and feature matching
• Week 9: Recognition basics
• Week 10: Image representations
• Week 11: Intro to machine learning
• Week 12: Convolutional neural networks
• Week 13: Advanced topics

Past offerings at the university

• Spring 2016, Instructor: Subhransu Maji
• Spring 2014, Instructor: Erik Learned-Miller

Accommodation statement

The University is committed to providing an equal educational opportunity for all students. If you have a documented physical, psychological, or learning disability on file with Disability Services (DS), you may be eligible for reasonable academic accommodations to help you succeed in this course. If you have a documented disability that requires an accommodation, please notify me within the first two weeks of the semester so that we may make appropriate arrangements.

Academic honesty

Since the integrity of the academic enterprise of any institution of higher education requires honesty in scholarship and research, academic honesty is required of all students. Students are expected to be familiar with this policy and the commonly accepted standards of academic integrity (http://www.umass.edu/honesty).