Graphics are visual presentations on some surface, such as a wall, computer screen, paper, or stone to brand, or entertain. Examples are photographs, drawings, graphs, diagrams, maps, engineering drawings, or other images

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

2. 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
3

4. 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. 5
Image acquisition
 Video camera
 Infrared camera
 Range camera
 Line-scan camera
 Hyperspectral camera
 Omni-directional camera
 and more …

6. 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. 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]  [5 10 6 4]T
The probabilistic representation (random
field)
The graphical representation

8. 8
j
(i, j) (i, j+1)
(i, j-1)
(i-1, j) (i-1, j+1)
(i+1, j+1)
(i+1, j)
(i-1, j-1)
(i+1, j-1)
i
(row)
(column)
4-neighborhood 8-neighborhood
Types of neighborhoods
Neighbors of a pixel

9. 9
Closedness ambiguity (The
adjacency paradox)

10. 10
A variation: Hexagonal pixels

11. Image as surface - Gradient
11
Gradient
Isophote
Ridge

12. Outline
12

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

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
15