cs 682: computer visionzduric/cs682/slides/cs682_introduction.pdfdr. zoran duric (cs dept. gmu) cs...

CS 682: Computer Vision

Dr. Zoran Duric

CS Dept. GMU

January 27, 2009

Office: S&T II, Rm. 427email: zduric@cs.gmu.edu

Office Hours: Tue. 2:00-4:00pm, Thu 1:30-2:30pm or by app.URL: http://www.cs.gmu.edu/∼zduric/

Course: http://www.cs.gmu.edu/∼zduric/cs682.html

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 1/ 16January 27, 2009 1 / 16

Class Administration

How will the class work?

I will lecture most of the time

There will be discussions, Matlab programming examples

There will be several homework assignments in Matlab

There will be a midterm and a final exam

Students will present their projects

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 2/ 16January 27, 2009 2 / 16

Class Administration (cont.)

Grading

Class participation and presentations: 10%

Midterm: 20%

Final: 20%

Homeworks: 30%

Project: 20%

Resources:

Robotics Laboratory has several/many video cameras, R1 470Laboratory for the Study and Simulation of Human Movementhas a other equipment, R1 470/477

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 3/ 16January 27, 2009 3 / 16

Class Textbook

Required

M. Sonka, V. Hlavec, and R. Boyle. Image Processing, Analysis, andMachine Vision. Thomson 2008.

Recommended

Matlab with Image Processing Toolbox, can be used on GMUcomputers for free

Svoboda, Kybic, and Hlavec. Image Processing, Analysis, andMachine Vision: A MATLAB Companion. Thomson 2008.

Class notes (will be posted on the class web page).

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 4/ 16January 27, 2009 4 / 16

Introduction

Chapter 1: Introduction

1.1 Motivation

1.2 Why is computer visiondifficult?

1.3 Image representation andimage analysis tasks

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 5/ 16January 27, 2009 5 / 16

Introduction Motivation

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 6/ 16January 27, 2009 6 / 16

Introduction Motivation

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 7/ 16January 27, 2009 7 / 16

Introduction Motivation

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 8/ 16January 27, 2009 8 / 16

Introduction Why is computer vision difficult?

Why is computer vision difficult?

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 9/ 16January 27, 2009 9 / 16

Introduction Why is computer vision difficult?

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 10/ 16January 27, 2009 10 / 16

Introduction Why is computer vision difficult?

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 11/ 16January 27, 2009 11 / 16

Introduction Image representation and image analysis tasks

Image representation and image analysis tasks

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 12/ 16January 27, 2009 12 / 16

Introduction Image representation and image analysis tasks

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 13/ 16January 27, 2009 13 / 16

Introduction Image representation and image analysis tasks

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 14/ 16January 27, 2009 14 / 16

Introduction Image representation and image analysis tasks

Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 15/ 16January 27, 2009 15 / 16

Introduction Summary

Summary

Human vision is natural and seems easy; computer mimicry of this isdifficult.We might hope to examine pictures, or sequences of pictures, forquantitative and qualitative analysis.Many standard and advanced AI techniques are relevant.High and low levels of computer vision can be identified.Processing moves from digital manipulation, through pre-processing,segmentation, and recognition to understanding—but these processesmay be simultaneous and co-operative.An understanding of the notions of heuristics, a priori knowledge,syntax, and semantics is necessary.The vision literature is large and growing; books may be specialized,elementary, or advanced.A knowledge of the research literature is necessary to stay up to datewith the topic.Developments in electronic publishing and the Internet are makingaccess to vision simpler.Dr. Zoran Duric (CS Dept. GMU) CS 682: Computer Vision 16/ 16January 27, 2009 16 / 16