Instructor: Prof. Harry
Wechsler wechsler@gmu.edu
Course
Description –
Computer Vision (3:3:0). 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). It continues with fundamentals and motivation for image analysis
(“vision architectures”) for recognition and re-identification (“what /who”), layout
in space (“where”), and behavior (“motion”; and “(video) tracking”). Emphasis
on convolutional neural networks (CNN)
and Deep Learning for classification;
and Show and Tell for image
description and image query answering using semantic alignment between image
and (caption) text. Hands-on experience with MATLAB (and its tool boxes) and
MatConvNet: CNN for MATLAB. Major applications include object recognition and biometrics
/ face recognition.
(Reference) Textbook: Concise Computer Vision, Reinhard Klette, Springer, 2014 (including slides https://www.cs.auckland.ac.nz/~rklette/TeachAuckland.html/775/ )
Day,
Time, and Venue:
R – Thursday, 4:30 pm – 7:10 pm, Planetary Hall 224.
Office
Hours: Thursday,
3:00 – 4:00 pm (ENGR - 4448)
http://registrar.gmu.edu/calendars/spring-2016/
First day of classes: Thursday, January 21
Spring break: no class on Thursday, March 10
Midterm (“closed books and closed notes”): Thursday, March
17
Last day of classes: Thursday, April 28
Grade Composition
- Homework: 20%
- Midterm: 15%
- Term (team) Projects: 50%
- FINAL: 15%
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