Image Processing

By
Dr. Gopalakrishnan
Assistant Professor
 Course
•Objectives
To understand the fundamentals of digital image
processing.
• To gain knowledge on image transformation techniques
and color
image
processing.
• To understand various image enhancement
methods.
• To know the various restoration and segmentation
techniques used in
image
processing.
• To understand the image compression
methods.
2
Course Outcomes-
COsUnderstand the fundamentals and basic mathematical
CO1.
operations on
image processing.
CO2. Understand the significance of different image
transforms.

CO3. Apply techniques for enhancement of Digital

images.

CO4. Analyse the Image degradation/restoration

methods.

CO5. Understand various image segmentation

Techniques 3
Why Digital Image
Processing?
• To have improvement of pictorial information for
interpretatio
human
•nTo make processing of image data for tasks
such as
storage, transmission, and extraction of
pictorial
information.

4
What is Digital Image
Processing(DIP)?
• An image may be defined as a two-dimensional
function, f (x, y),
where x and y are spatial (plane) coordinates, and the
amplitude of
• fWhen
at anyx, pair of the
y, and coordinates (x, y) isofcalled
intensity values the intensity
f are all
or gray
quantities,
finite, discretewe call the image a digital
• level of the
image.
The field ofimage
digitalat that point.
image processing refers to
images bydigital
processing means of a digital
computer.

5
What is Digital Image
Processing(DIP)?
• Digital image is composed of a
finite
number of elements, each of
which
has a particular location and
value.
• These elements
Pixel is the are called
term used most
picture
widely
elements, image elements,
to denote the elements of apels,
and
digital
pixels.
image. 6
What is Digital Image
Processing(DIP)?

7
Binary Image Vs Gray
Image

8
Grayscale
Chart

9
Levels in Image
Processing
• Low-level processes involve operations such as image
noise, contrast
preprocessing toenhancement,
reduce and image
sharpening.
• A low level process is characterized by the fact that both its inputs
areoutputs
and
• images.
Mid-level processing of images involves tasks such as segmentation,
for computer processing, and classification (recognition) of
description
• individual
A mid-levelobjects.
process is characterized by the fact that its inputs
generally are
images, but its outputs are attributes extracted from those images
• (e.g., edges, processing involves “making sense” of an ensemble of
Higher-level
contours, and the identity of individual objects).
recognized
objects, as in image analysis, and, at the far end of the continuum,
performing the
cognitive functions normally associated with human vision. 10
The Origins of Digital Image
Processing
• One of the earliest applications of digital
images was
in the newspaper industry, when pictures
were first
sent by submarine cable between London
and New
York.
• Bartlane cable picture transmission system
Figure 1. A digital picture produced
•inSpecialized
the printing equipment coded in 1921 from a coded tape by a
early 1920s
pictures for reduced the time required to telegraph printer with special
transport
cable a
transmission, then reconstructed typefaces.
picture
• them
Images atacross the Atlantic
the transmitted
was infrom moreand
this way than a
week to end.
receiving
reproduced
less than three hours.
on a telegraph printer fitted with
typefaces
simulating a halftone pattern. 11
The Origins of Digital Image
•Processing
One of the earliest applications of digital images was in the
newspaper industry,
when pictures were first sent by submarine cable between
• London
Some of and New problems in improving the visual quality of these
the initial
York.digital
early
pictures were related to the selection of printing procedures
and the
distribution of intensity levels.

Figure 1. A digital Figure 2. A digital picture

picture produced made in 1922 from a tape
in 1921 from a coded punched after the signals
tape by a telegraph had crossed the Atlantic 12
printer with special twice. (McFarlane.)
The Origins of Digital Image
Processing
• Although the examples just shown
digital
images, they are not considered digital
image
processing results in the context of
our the history of digital image
• Thus,
definition,isbecause digital computers
processing
were not tied to the development
intimately
used
of in their creation.
the
• In fact, digital images require so much
digital
storage computer.
and computational power and Figure 3. Unretouched cable picture of
the development
dependent on of digital computers Generals Pershing (right) and Foch,
transmitted in 1929 from London to New York
and of by 15-tone equipment. (McFarlane.)
supporting technologies that include
data
storage, display, and transmission. 13
The Origins of Digital Image
•Processing
The first computers powerful enough to
carry
out meaningful image processing
• tasks
Work on using computer
appeared infor
techniques the early 1960s.
improving images from a space probe
began at
the Jet Propulsion Laboratory
(Pasadena,
California) in 1964, when pictures of the
moon Figure 4. The first picture of the moon by a
transmitted by Ranger 7 were U.S. spacecraft. Ranger 7 took this image on
processed by a July 31, 1964 at 9:09 A.M. EDT, about 17
minutes before impacting the lunar surface.
computer to correct various types of (Courtesy of NASA.)
image 14
Fundamental Steps in
DIP

15
Image
Acquisition • Acquire
images
from
• sensors
Perfor
m
conversio
A/D
•nOutput
image
are
s
16
Image
Enhancement • Manipulating
image to be
more
suitable than
previous.
• It is a
process
subjective
.
• Performed
on
Spatial and
domains
frequency
.
17
Image
• Restore the
Restoration images from
the
degradations /
noises.
• It is an
process
objective
• .Based on
mathematical
/
probabilistic
models

18
 Wavelets and Multiresolution
Processing
• Foundation for
representing
images
in various
degrees
of resolution.

19
Color Image
Processing •
presentatio
Pleasing
ns
understanding
and more
s.

20
Image
Compression • Reduces
the
image size
suitable
transmissio
for
n
storage,
and
manage
bandwidth.

21
Morphological
Processing
• Deals with
tools
to extract
useful for
image
representatio
components
n
• and
Gives
description.
images
output
attributes.

22
Image
Segmentation
• Partition
the image
into
objects

23
Representation &
• Converts the
Description raw image
data
compute
suitable to
rprocesse
• s.Descriptions
isfeatur
eselection,
based
on attributes,
differentiates
one class
from 24
Object
Recognition
• Assigning
labels to
an
object
based
descriptor
on
s. its

Dr. D. REGAN, SISTK 25

Image Enhancement
Example

26
Applications of
DIP

27
Applications of
DIP
• The field of image processing has applications in
and the space
medicine
• program.
Computer procedures are used to enhance the
contrast or
interpretation of X-ray
code the intensity images
levels and the
into color biological
for easier
• sciences.
Geographers use the same or similar techniques
topollution
study patterns from aerial and satellite
imagery.

28
 Fields that use Digital Image
•Processing
There are numerous applications using DIP but here
based on the
source of energy for images presented (X-ray, visual,
• infrared,
The principal energy source for images in use
acoustic
today and so on).
electromagnetic
is the energy
spectrum.images, used for modeling and visualization, are
• Synthetic
by
generated
computer.

29
Gamma-Ray
Imaging • Nuclea
r medicines
and
astronomical
observations

30
X-Ray
Imaging

31
Imaging in the Ultraviolet
Band

32
Imaging in the Ultraviolet
Band • Fluorescen
cemicroscop
e
• imaging
Normal corn
and
“smut”
infected
corn images

33
Imaging in the Visible and Infrared
Bands

34
Imaging in the Microwave
Band

35
Imaging in the Radio
Band

36
Other Imaging Modalities that
are used

37
Electron Microscope
Images

38
Synthetic
Images

39
Brightness Vs
Contrast
• Brightness increases the
overall
lightness of the image
—for
example, making dark
colors
lighter and light colors
• whiter—
Example of adjustments
while to contrast
made adjusts
the
the brightness and contrast
difference
of an between the
darkest and
image shown next.
Ref: https://pro.arcgis.com/en/pro-app/2.8/help/analysis/raster-functions/contrast-and-brightness-function.htm

lightest colors. 40
Mach Band
Effect • Intensity of stripes
is
constant, but
we
perceive brightness
is
stronger near
the
boundaries. This
effect 41
 Mach Band
Effect • In area A, brightness
perceived is darker
while in
A
area B is brighter. This
B phenomenon is called
Mach
Band Effect.

Positio
n

42
 Simultaneous
•Contrast
All small squares have exactly the same
intensity but
they appear progressively darker as
background
becomes lighter.

43
Other Key
Terms
• Monochromatic : Light that is void of
•colors
Chromatic: Light spans the EM spectrum of
0.79μ
0.43 to
• m.
Radiance: The total amount of energy
fromflows
that the light source, measured in
• watts(w)
Luminance: A measure of the amount of
energy an
observer perceives from a light source,
measured in
lumens(lm). 44
Optical
illusion
• It is an human
perception
phenomena where
information or
eye
fills
wrongly
in non-existing
perceives
geometrical
properties of
objects.

45
 Image Sensing and
Acquisition
• Images are generated by the combination of an
“illumination”
source and the reflection or absorption of energy
• from that
The illumination may originate from a source of
EMsource
such asby
energy, the elements
a radar, infrared,oforthe “scene” being
X-ray
imaged.
system.
• Image acquisition may be of different
types:
• Single
Sensorimage
StripesSensor
that may be a linear or
circular
• Array Sensors
46
 Image Acquisition using Single
Sensor
• Simple idea is photo diode
assensor
a
• .According to the
illumination of
light, output waveform is
• generated.
Output is proportional to
incident light
the
• intensity.
Filter is used to
selectivit
improve
y
47
Line
Sensor
Array
Sensor

48
 Image Acquisition using Single
Sensor • To generate 2-d image,
the
sensor must have relative
displacement in both X-
and Y- is mounted on lead
• Sensor
direction.
film negative is on
screw,
•Adrum.
light source is inside the
drum.
• As the light passes through the film, its intensity is modified
by the film
density
• This before it isof
"modulation" captured
the lightby the sensor.
intensity causes corresponding
variations in the sensor voltage, which are converted to
image intensity 49
 Image Acquisition using Sensor
Stripes
••Motion perpendicular
The strip to the elements in one
provides imaging
strip
direction.
provides imaging in the
• other
This arrangement is used in
direction,
flat bed as shown in Fig.
most
• scanners.
Sensing devices with 4000 or more
in-line sensors are possible.
• They are used in airborne imaging applications, in
which the system is mounted on an aircraft that flies at
imaging
a constant
altitude and speed over the geographical area to be 50
 Image Acquisition using Sensor
Stripes
• Sensor strips in a ring configuration are
used
in medical and industrial imaging to
•Aobtain
rotating X-ray source provides
cross-sectional (“slice”) images of 3-D
illumination,
objects.
and X-ray sensitive sensors opposite
the
• source collect
This is the the
basis energy
for that
medical andpasses
through
industrial
the object.
computerized axial tomography
(CAT)
imaging 51
A Simple Image formation
model

52
A Simple Image formation
model

53
Hubble Telescope Mirror
Flaw

Before After

54
Image
Enhancement

55
Image
Restoration

56
Reference
s:
• R.C. Gonzalez & R.E. Woods, Digital Image Processing, Addison
Wesley/Pearson education, 3rd
• edition, 2010.S Esakkirajan, T Veerakumar, Digital Image processing,
S Jayaraman,
Tata McGraw Hill,
• 1stedition, 2009.
NPTEL :: Electronics & Communication Engineering - NOC:Digital
Image Processing

57