Introduction to Computer Vision

Course Summary

Computer Vision is the branch of Computer Science whose goal is to model the real world or to recognize objects from digital images. These images can be acquired using video or infrared cameras, radars or specialized sensors such as those used by doctors.
The student will be introduced to the basic techniques of the field of Computer Vision. He will learn to apply Image Processing techniques where appropriate.
We will concentrate on the black and white and color images acquired using standard video cameras. We will introduce the basic processing techniques.

Course Outline

The Vision Problem

Image formation

Low level image processing

Edge-Detection / Filtering
Classification / Segmentation
Texture

Shape from X

Shading
Texture
Stereo
Motion

High-level processing

Textbooks

V. S. Nalwa, A Guided Tour of Computer Vision, Addison-Wesley, 1993.

D. A. Forsyth, J. Ponce, Computer Vision: A Modern Approach, Prentice Hall, 2002.

R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2003.

R. Horaud and O. Monga, Vision par Ordinateur, Editions Hermes,1995.

On the web

Lecture Notes

Introduction

Edges and Regions