Document 15072456

advertisement
Mata kuliah : T0283 - Computer Vision
Tahun
: 2010
Lecture 01
Introduction to Computer Vision
Learning Objectives
After carefully listening this lecture, students will be able to
do the following :
show what computer vision is all about and basic principles
of various computer vision applications
explain approaches in computer vision systems (three level
processing).
explain how a digital image is formed and other related
matters such as light and visual perception.
January 20, 2010
T0283 - Computer Vision
3
What is Computer Vision ?
Ballard and Brown:
The construction of explicit, meaningful description
of physical objects from images
Forsyth and Ponce:
Extracting descriptions of the world from pictures
or sequences of pictures
January 20, 2010
T0283 - Computer Vision
4
What is Computer Vision ?
January 20, 2010
T0283 - Computer Vision
5
Image Processing
Image Enhancement
January 20, 2010
T0283 - Computer Vision
6
Image Processing (cont’d)
Image Restoration(e.g., correcting out-focus images)
January 20, 2010
T0283 - Computer Vision
7
Image Processing (cont’d)
Image Compression
January 20, 2010
T0283 - Computer Vision
8
Computer Graphics
Geometric modeling
January 20, 2010
T0283 - Computer Vision
9
Computer Vision
January 20, 2010
T0283 - Computer Vision
10
An Industrial Computer Vision System
January 20, 2010
T0283 - Computer Vision
11
Cap Inspection System
» Low-level image analysis: Identify edges, regions
» Mid-level: Distinguish “cap” from “no cap”
» Estimation: What are orientation of cap, height of liquid?
January 20, 2010
T0283 - Computer Vision
12
Face Detection
courtesy of H. Rowley
How is this like the bottle problem on the previous slide?
January 20, 2010
T0283 - Computer Vision
13
Text Detection & Recognition
from J. Zhang et al.
Similar to face finding: Where is the text and what does it say?
Viewing at an angle complicates things...
January 20, 2010
T0283 - Computer Vision
14
High Level Capability
Computer Vision System (CVS) is expected to have
high level capabilities like Human Visual System
(HVS) does such as :
Object detection – is an object present in the scene ? If
so, where is its boundaries
Recognition – putting a label on an object
Description – assigning properties to objects
3D inference – interpreting a 3D object from 2D views
Interpreting motion
January 20, 2010
T0283 - Computer Vision
15
Approach in Computer Vision
3-D World
Objects
Images
Edges/Region/Depth
Features/Surfaces
Models and
Assumptions
Objects Detection &
Recognitions
January 20, 2010
T0283 - Computer Vision
16
The Three Processing Level
Low-level processing
Standard procedures are applied to improve image quality
Procedures are required to have no intelligent capabilities.
January 20, 2010
T0283 - Computer Vision
17
The Three Processing Level (cont’d)
Intermediate-level processing
Extract and characterize components in the image
Some intelligent capabilities are required.
January 20, 2010
T0283 - Computer Vision
18
The Three Processing Level (cont’d)
High-level processing
Recognition and interpretation.
Procedures require high intelligent capabilities.
January 20, 2010
T0283 - Computer Vision
19
How are images represented in the
computer?
January 20, 2010
T0283 - Computer Vision
20
Image Formation
There are two parts to the image
formation process:
The geometry of image formation, which determines
where in the image plane the projection of a point
in the scene will be located.
The physics of light, which determines the brightness
of a point in the image plane as a function of
illumination and surface properties.
January 20, 2010
T0283 - Computer Vision
21
Image formation (cont’d)
Geometric parameters
type of projections
position and orientation of camera in space
perspective distortions introduced by the imaging
process
Photometric parameters
type, intensity, and direction of illumination
reflectance properties of the viewed surfaces
Optical parameters of the lens
lens type
focal length
field of view
January 20, 2010
T0283 - Computer Vision
22
A Simple model of image formation
The scene is illuminated by a single source.
The scene reflects radiation towards the camera.
The camera senses it via chemicals on film.
January 20, 2010
T0283 - Computer Vision
23
What is light?
The visible portion of the electromagnetic (EM)
spectrum.
It occurs between wavelengths of approximately 400
and 700 nanometers.
January 20, 2010
T0283 - Computer Vision
24
CCD (Charged-Coupled Device) Cameras
Tiny solid state cells convert light energy into
electrical charge.
The image plane acts as a digital memory that can
be read row by row by a computer.
January 20, 2010
T0283 - Computer Vision
25
Frame Grabber
Usually, a CCD camera plugs into a computer board
(frame grabber).
The frame grabber digitizes the signal and stores it
in its memory (frame buffer).
January 20, 2010
T0283 - Computer Vision
26
Image Digitization
Sampling means measuring the value of an image at a
finite number of points.
Quantization is the representation of the measured
value at the sampled point by an integer.
January 20, 2010
T0283 - Computer Vision
27
Image Digitization (cont’d)
January 20, 2010
T0283 - Computer Vision
28
Image Quantization
256 gray levels (8 bpp)
8 gray levels (3 bpp)
January 20, 2010
32 gray levels (5 bpp)
4 gray levels (2 bpp)
T0283 - Computer Vision
16 gray levels (4 bpp)
2 gray levels (1 bpp)
29
Image Sampling
original image
sampled by a factor of 4
January 20, 2010
sampled by a factor of 2
sampled by a factor of 8
T0283 - Computer Vision
30
Digital Image
An image is represented by a rectangular array of
integers.
An integer represents the brightness or darkness of the
image at that point.
N: # of rows, M: # of columns, Q: # of gray levels
N = 2 n , M = 2 m , Q = 2 q (q is the # of bits/pixel)
Storage requirements: NxMxQ (e.g., N=M=1024,
q=8, 1MB)
f (0,0)
f (1,0)
...
f ( N  1,0)
January 20, 2010
f (0,1)
...
f (1,1)
...
...
...
f ( N  1,1) ...
f (0, M  1)
f (1, M  1)
...
f ( N  1, M  1)
T0283 - Computer Vision
31
Image File Formats
Many image formats adhere to the simple model shown
below (line by line, no breaks between lines).
The header contains at least the width and height of the
image.
Most headers begin with a signature or “magic number” a short sequence of bytes for identifying the file format.
January 20, 2010
T0283 - Computer Vision
32
Common Image File Formats
GIF (Graphic Interchange Format) PNG (Portable Network Graphics)
JPEG (Joint Photographic Experts Group)
TIFF (Tagged Image File Format)
PGM (Portable Gray Map)
FITS (Flexible Image Transport System)
January 20, 2010
T0283 - Computer Vision
33
Download