Instructor: Prof. Harry
Wechsler wechsler@gmu.edu
Course
Description –
Computer Vision (3:3:0). Study of computational models
of visual perception and their implementation in computer systems.
Topics include early visual processing, edge detection, segmentation, intrinsic
images, image modeling, representation of visual knowledge, and image
understanding.
Objectives – Course starts with
a primer on probability and statistics and another primer on digital image
processing (DIP); continues with basics / motivation / image formation process
(“vision architectures”) for the purpose of identification / recognition (“what
/who”), location (“where”), and behavior
(“motion”, “(video) tracking”, and “human activity”). Hands-on experience is
expected using MATLAB (and its tool boxes), OpenCV, R, and/or mobileCV. Major
applications discussed are those of object representation and recognition,
tracking, and biometrics / face & gesture recognition.
(Reference) Textbook: Szelisky, Computer Vision, Springer, 2011.
You are welcome to download the PDF from http://szeliski.org/Book/
for personal use, but not to repost it on any other Web site.
Please post a link to this URL (http://szeliski.org/Book)
instead.
Day,
Time, and Venue:
T – Tuesday, 7:20 pm – 10:00 pm, Innovation Hall 206.
Office
Hours: Tuesday,
6:00 – 7:00 pm (ENGR - 4448)
http://registrar.gmu.edu/calendars/2013Spring.html
First day of classes: Tuesday, January 22
Spring break: no class on Tuesday, March 12
Midterm (“closed books and closed notes”): Tuesday, March
19
Last day of classes: Tuesday, April 30
http://registrar.gmu.edu/calendars/2013SpringExam.html
FINAL Exam –
cumulative - (“closed books and closed notes”): Tuesday, May 14, 7:30 pm – 10:15
pm
Grade Composition
- Homework: 25%
Homework and term project (see below) require
using MATLAB and/or OpenCV. You can buy a student version for MATLAB in Johnson
center or use it remotely from ITE labs. OpenCV is a C/C++ open source computer
vision library. You can also use image processing software for mobile applications,
Android and iPhone.
- Midterm: 25%
- Term (team) Project: 25%
- FINAL: 25%
Tentative Course Schedule:
Textbook (Chaps. 1 – 5, 8, 11, 14), Notes /
Journal & Conference Papers:
·
Overview
and Vision Architectures (1/22)
·
Primer
on Probability / Bayes and Digital Image Processing (1/29)
·
Image
formation and Digital Forensics (2/5)
·
Operators,
Filters, and Transforms (2/12)
·
Feature
Detection (2/19)
·
Image
Segmentation (2/26)
·
Optical
Flow and MIDTERM REVIEW (3/5)
·
SPRING
BREAK (3/12)
·
MIDTERM
(3/19)
·
Correspondence
and Stereo (3/26)
·
Tracking
(4/2)
·
Object
Recognition (4/9)
·
Biometrics
(4/16)
·
Term
(Team) Project Presentation (4/23)
·
FINAL
(cumulative) REVIEW (4/30)
You are expected to abide by the GMU honor
code. Homework assignments and exams are individual efforts. Information on the
university honor code can be found at http://academicintegrity.gmu.edu/honorcode/.
Additional departmental CS information: http://cs.gmu.edu/wiki/pmwiki.php/HonorCode/CSHonorCodePolicies