1. ECE 692 – Advanced Topics in Computer Vision
Lecture 1 - Introduction
01/14/16

2. Some clarification Image & Graphics Image processing & Computer vision
Image processing & Image understanding
Image processing & Pattern recognition
Image Processing: ECE472, ECE572
Pattern Recognition: ECE471, ECE571
Computer Vision: ECE573
Computer Graphics: CS494, CS594
Advanced Topics: ECE692

3. Image Representation

4. What is an image? - The bitmap (iconic) representation
Also called “raster or pixel maps” representation
An image is broken up into a grid
pixel
Gray level
Original picture
Digital image
f(x, y)
I[i, j] or I[x, y] x y

5. Image acquisition Video camera Infrared camera Range camera
Line-scan camera
Hyperspectral camera
Omni-directional camera
and more …

6. What is an image? - The vector representation
Object-oriented representation
Does not show information of individual pixel, but information of an object (circle, line, square, etc.)
Circle(100, 20, 20)
Line(xa1, ya1, xa2, ya2)
Line(xb1, yb1, xb2, yb2)
Line(xc1, yc1, xc2, yc2)
Line(xd1, yd1, xd2, yd2)

7. What is an image? (cont’d)
The functional representation
z = ax2+by2+cxy+dx+ey+f
The linear (vector representation)
[5 10; 6 4]  [ ]T
The probabilistic representation (random field)
The graphical representation

8. Types of neighborhoods
Neighbors of a pixel j
(column)
(i-1, j-1)
(i-1, j)
(i-1, j+1)
(i, j-1)
(i, j)
(i, j+1) i
(i+1, j-1)
(i+1, j)
(i+1, j+1)
Explain like
The current pixel of interest is (I,j),
The origin is at the upper-left corner
Then its neighbors would be …
(row)
4-neighborhood
8-neighborhood

9. Closedness ambiguity (The adjacency paradox)

10. A variation: Hexagonal pixels

11. Image as surface - Gradient
Isophote
Ridge

12. Outline

13. What has been learned? (472/572)
Preprocessing – low level
Image Improvement
High-level IP
Image Understanding
Image
Enhancement
Image
Restoration
Image
Segmentation
Image
Acquisition
Image
Compression
Image
Coding
Representation
& Description
Morphological
Image Processing
Wavelet
Analysis
Recognition &
Interpretation
Knowledge Base

14. What to learn? (this course)
Preliminaries
Image representation and creation
Preprocessing
Kernel operators
Noise removal
Mathematical morphology
Image understanding
Segmentation
Parametric transforms
Shape
Descriptors
From 2D to 3D

15. Objectives In-depth study of computer vision algorithms
Study the trend and predict the future
Optimization and consistency
CVPR/WACV/ECCV submissions