CLC Image Processing 1 Introduction
-
Upload
chiranji-lal-chowdhary -
Category
Documents
-
view
222 -
download
0
Transcript of CLC Image Processing 1 Introduction
-
8/3/2019 CLC Image Processing 1 Introduction
1/35
All from Gonzalez-Woods.
CLC
-
8/3/2019 CLC Image Processing 1 Introduction
2/35
One picture is worth more than ten thousand words
Anonymous
-
8/3/2019 CLC Image Processing 1 Introduction
3/35
Digital Image Processing, Rafael C.
Gonzalez & Richard E. Woods,
Addison-Wesley, 2002
Much ofthe material that follows is taken from this book.
Thankful to authors.
-
8/3/2019 CLC Image Processing 1 Introduction
4/35
This lecture will cover: Whatis a digital image?
Whatis digital image processing?
History of digital image processing State ofthe art examples of digital image processing
Key stages in digital image processing
-
8/3/2019 CLC Image Processing 1 Introduction
5/35
A digital image is a representation of a two-
dimensional image as a finite set of digital values,
called picture elements or pixels
Im
agestakenfromGonzale
z&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
6/35
Pixel values typically representgray levels, colours,
heights, opacities (non-transparent area, as cornea )
etc
Rememberdigitization implies that a digital image isan approximation of a real scene
1 pixel
Im
agestakenfromGonzale
z&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
7/35
Common image formats include: 1 sample per point (B&W or Grayscale)
3 samples per point (Red, Green, and Blue)
4 samples per point (Red, Green, Blue, and Alpha,
a.k.a. Opacity)
For most ofthis course we will focus on grey-scale
images
-
8/3/2019 CLC Image Processing 1 Introduction
8/35
Digital image processing focuses on two majortasks Improvement of pictorial information for human
interpretation
Processing ofimage data for storage,transmission and
representation for autonomous machine perception
Some argument about where image processing ends
and fields such as image analysis and computer
vision start
-
8/3/2019 CLC Image Processing 1 Introduction
9/35
The continuum from image processingto computer
vision can be broken up into low-, mid- and high-
level processes
LowLevel Process
Input: Image
Output: Image
Examples: Noise
removal,imagesharpening
Mid Level Process
Input: Image
Output:Attributes
Examples: Object
recognition,segmentation
High Level Process
Input:Attributes
Output: Understanding
Examples: Scene
understanding,autonomous navigation
In this course we will
stop here
-
8/3/2019 CLC Image Processing 1 Introduction
10/35
Early 1920s: One ofthe first applications of digital
imaging was in the news-
paperindustry
The Bartlane cable picturetransmission service
Images were transferred by submarine cable between
London and New York
Pictures were coded for cable transfer and reconstructed
atthe receiving end on a telegraph printer
Early digital image
Im
agestakenfromGonzale
z&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
11/35
Mid to late 1920s: Improvements to the Bartlane
system resulted in higher quality images New reproduction
processes based
on photographic
techniques
Increased number
oftones in
reproduced images
Improved
digital image Early 15 tone digital
image
Im
agestakenfromGonzale
z&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
12/35
1960s: Improvements in computingtechnology and
the onset ofthe space race led to a surge of work in
digital image processing
1964: Computers used toimprove the quality of
images ofthe moon taken
by the Ranger 7probe
Such techniques were used
in other space missionsincludingthe Apollo landings
A picture ofthe moon taken
by the Ranger 7 probe
minutes before landingIm
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
13/35
1970s: Digital image processing begins to be used
in medical applications 1979: Sir Godfrey N.
Hounsfield & Prof. Allan M.
Cormack share the Nobel
Prize in medicine forthe
invention oftomography,
the technology behind
Computerised AxialTomography (CAT) scansTypical head slice CAT
image
Im
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
14/35
1980s - Today: The use of digital image processing
techniques has exploded and they are now used for
all kinds oftasks in all kinds of areas
Image enhancement/restoration Artistic effects
Medical visualisation
Industrial inspection
Law enforcement
Human computerinterfaces
-
8/3/2019 CLC Image Processing 1 Introduction
15/35
One ofthe most common uses ofDIP techniques:
improve quality, remove noise etc
Im
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
16/35
Launched in 1990 the Hubble
telescope can take images of
very distant objects
However, an incorrect mirrormade many of Hubbles
images useless
Image processing
techniques wereused to fix this
-
8/3/2019 CLC Image Processing 1 Introduction
17/35
Artistic effects are used
to make images more
visually appealing,to
add special effects and
to make compositeimages
-
8/3/2019 CLC Image Processing 1 Introduction
18/35
Take slice from MRI scan of canine heart, and find
boundaries between types oftissue Image with gray levels representingtissue density
Use a suitable filterto highlight edges
Original MRI Image of a Dog Heart Edge Detection ImageIm
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
19/35
Geographic Information Systems Digital image processingtechniques are used extensively
to manipulate satellite imagery
Terrain classification
Meteorology
Im
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
20/35
Night-Time Lights of the
Worlddata set Global inventory of human
settlement
Not hard to imagine thekind of analysis that might
be done usingthis data
Im
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
21/35
Human operators are
expensive, slow and
unreliable
Make machines do the
job instead
Industrial vision systems
are used in all kinds of
industries
Can we trustthem?
Im
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
22/35
Printed Circuit Board (PCB) inspection Machine inspection is used to determine that all
components are present and that all solder joints are
acceptable
Both conventional imaging and x-ray imaging are used
-
8/3/2019 CLC Image Processing 1 Introduction
23/35
Image processing
techniques are used
extensively by law enforcers Number plate recognition for
speed cameras/automatedtoll systems
Fingerprint recognition
Enhancement of CCTV
images
Im
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
24/35
Try to make human computer
interfaces more natural Face recognition
Gesture recognition
Does anyone remembertheuserinterface from Minority
Report?
These tasks can be extremely
difficult
-
8/3/2019 CLC Image Processing 1 Introduction
25/35
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
ImageEnhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression
-
8/3/2019 CLC Image Processing 1 Introduction
26/35
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
ImageEnhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
CompressionIm
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
27/35
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
ImageEnhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
CompressionIm
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
28/35
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
ImageEnhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
CompressionIm
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
29/35
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
ImageEnhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
CompressionIm
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
30/35
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
ImageEnhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
CompressionIm
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
31/35
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
ImageEnhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
CompressionIm
agestakenfromGonzalez&Woods,
DigitalImageProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
32/35
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
ImageEnhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
CompressionIm
agestakenfromGonzalez&Woods,
DigitalImag
eProcessing(2002)
-
8/3/2019 CLC Image Processing 1 Introduction
33/35
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
ImageEnhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression
-
8/3/2019 CLC Image Processing 1 Introduction
34/35
Image
Acquisition
Image
Restoration
Morphological
Processing
Segmentation
Representation
& Description
ImageEnhancement
Object
Recognition
Problem Domain
Colour Image
Processing
Image
Compression
-
8/3/2019 CLC Image Processing 1 Introduction
35/35
We have looked at: Whatis a digital image?
Whatis digital image processing?
History of digital image processing
State ofthe art examples of digital image processing Key stages in digital image processing