Img Mod1 Session3 PDF

CSE4019 Image Processing
Module1
Dr.G.Malathi
Associate Professor Senior,
Imaging and Computer Vision Research Group Chair
School of Computing Science and Engineering
Vellore Institute of Technology, Chennai
1
Syllabus
Module1: Introduction, Digital Image, its
Representations 6 hours
Image Representation and image processing
Paradigm – Elements of digital image processing
– image model – Sampling and quantization –
relationships between pixels – connectivity,
distance measures between pixels – color
image(overview, various color models) – various
image formats –bmp, jpeg, tiff,pnd, gif, etc
2
PREPROCESSING
• To improve the image to ensure the success of
further processes
• e.g. enhancing contrast
removing noise
identifying information-rich areas
3
SEGMENTATION
• To partition the image into its constituent parts (objects)
– Autonomous segmentation (very difficult)

• Can facilitate or disturb subsequent processes
– Output (representation):
• Raw pixel data, depicting either boundaries or whole regions (corners vs.
texture for example)
• Need conversion to a form suitable for computer processing
– (Description)
4
Segmentation
5
The eye
Distinctive Iris Features
Flower Pattern - primary
Shaker
Stream
Jewel - primary
Irises are
responsible for
giving our eyes
their colour,
controlling the
diameter pupils
to determine
how much light
reaches the
retina.
Iris Recognition System
Segmenting the Iris
REPRESENTATION & DESCRIPTION
• Feature selection (description) deals with
extracting:
– features that result in quantitative information of

interest or
– features that are important for differentiating one

class of objects from another
19
Pupil Dilation
RECOGNITION & INTERPRETATION
• To assign a label to an object based on
information provided by the descriptors
• To assign meaning to a group of recognized

objects
21
Normalization
Normalization
KNOWLEDGE BASE
• Knowledge database
– Guides the operation of each processing module
and controls the interaction between modules
25
Iris Template Aging
• The rate of change of pupil diameter with age
decreased from 0.043 mm per year at the
lowest illuminance level to 0.015 mm per year
at the highest.
Human Visual Perception
27
28
Function Distribution Comments
Rods Sensitive to low Found Night vision,
light intensity. throughout recognize
Detect shades retina not at the shapes not
of grey center of blind colors
spot
Cones Sensitive to high Concentrated in Sensitive to red,

light intensity. the fovea green and blue
Detect colour. light
Do not operate
under poor light
29
The Human Eye
• Diameter: 20 mm
• 3 membranes enclose the eye

– Cornea & sclera
– Choroid
– Retina
30
The cornea and Sclera
• Cornea is the tough transparent tissue that
covers the anterior surface of the eye.
• Continuous with the cornea, the sclera is an

opaque membrane that encloses the
remainder of the optic globe
31
The choroid
• The choroid contains blood vessels for eye
nutrition and is heavily pigmented to reduce
extraneous light entrance and backscatter.
• It is divided into the ciliary body and the iris
diaphragm, which controls the amount of light
that enters the pupil (2 mm ~ 8 mm).
32
The lens
• The lens is made up of fibrous cells and is
suspended by fibers that attach it to the ciliary
body. 60-70% of water, 6% of fat and more
protein. It is coloured which increases with
age.
• It is slightly yellow and absorbs approx. 8% of
the visible light spectrum.
33
The Retina
• The retina lines the entire posterior portion.
• Discrete light receptors are distributed over

the surface of the retina:
– cones (6-7 million per eye) and

– rods (75-150 million per eye)
34
Cones
• Cones are located in the fovea and are highly
sensitive to color.
• Each one is connected to its own nerve end.
• Cone vision is called photopic (or bright-light

vision).
35
Rods
• Rods are giving a general, overall picture of
the field of view and are not involved in color
vision.
• Several rods are connected to a single nerve

and are sensitive to low levels of illumination
(scotopic or dim-light vision).
36
Receptor Distribution
• The distribution of receptors is radially
symmetric about the fovea.
• Cones are most dense in the center of the

fovea while rods increase in density from the
center out to approximately 20% off axis and
then decrease.
37
Cones and Rods
38
Spectral Response of Cones
39
Spectral Response of Cones
40
Brightness Adaptation &
Discrimination
• For any given set of conditions, the current

sensitivity level of Human Visual System is
called the brightness adaptation level.
41
Discrimination
• For a given background level b, the value of an
object in the foreground f is increased
gradually from the same level as b to a level
when the object is just perceived.
• The value (f-b)/b at the level of minimal
perception of the object is the Just-Noticeable
Difference(JND) for the background level b
42
Discrimination
43
Discrimination
44
Discrimination
45
Discrimination
• The value (f-
b)/b at the level
of minimal
perception of
the object is
the (JND) for
the background
level b
46
Discrimination
47
Discrimination
48
Discrimination
49
Discrimination
50
Discrimination
51
Discrimination
52
Discrimination
53
Discrimination
54
Discrimination
55
Discrimination
• The eye also discriminates between

changes in brightness at any specific
adaptation level.
I c
 Weber ratio
I
Where: Ic: the increment of illumination
discriminable 50% of the time and
I : background illumination
56
Discrimination
• Small values of Weber ratio mean good

brightness discrimination (and vice versa).
• At low levels of illumination brightness

discrimination is poor (rods) and it improves
significantly as background illumination
increases (cones).
57
Discrimination
• The typical observer can discern one to two

dozen different intensity changes
– i.e. the number of different intensities a person

can see at any one point in a monochrome image
58
Discrimination
• Overall intensity discrimination is broad due

to different set of incremental changes to be
detected at each new adaptation level.
• Perceived brightness is not a simple function

of intensity
– Scalloped effect, Mach band pattern
– Simultaneous contrast
59
Radiance, Luminance and Brightness
• RADIANCE is the total amount of energy that
flows from the light source
• LUMINANCE gives the measure of the amount
of energy an observer perceives from a light
source.( IR more R and L is 0)
• BRIGHTNESS is a subjective descriptor of light
perception that is practically impossible to
measure.
60
Perceived Brightness
61
Simultaneous Contrast
62
Illusions
63
Elements of Visual Perception of the
Image
CONTRAST
BORDER SHAPE
VISUAL PERCEPTION
BRIGHTNESS
BACKGROUND
TEXTURE
64
Contrast
Objects in an image can be identified only when it is
distinguished from its background
CONTRAST CONTRAST CONTRAST
Local change in the brightness of and object and the

background.
Higher the brightness, more is the contrast.

Brightness depends on the brightness of the local
surroundings – conditional contrast
LUMINANCE it describes the amount of light that passes
through or is emitted from a particular area and falls within
a given solid angle.
65
Acuity
Ability to detect details in an image.
Human eye – sensitive to slow and fast changes
increasing distance from optical axis
Sensitive to intermediate changes
66
Best Resolution
60wt
400mm
500lux
N 250mm J
67
Border
Object borders carry a lot of information for humans.

It enables adaptation effects - Ebbinghaus illusion.
68
Perceptual Grouping
To aggregate elements provided by low-level operations –

grouping according to
Properties of elements
parallelism
symmetry
continuity
Closure
not grouped
Proximity
Similarity
direction
69
Perceptual Grouping
Not grouped
Proximity
Similariy
70
Perceptual Grouping
D
1. Closure
2. Parallelism
3. Symmetry
4. Continuity
C 71

Img Mod1 Session3 PDF

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Img Mod1 Session3 PDF

Uploaded by

Copyright:

Available Formats

CSE4019 Image Processing

– Autonomous segmentation (very difficult)

– features that result in quantitative information of

– features that are important for differentiating one

• To assign meaning to a group of recognized

Cones Sensitive to high Concentrated in Sensitive to red,

• 3 membranes enclose the eye

• Continuous with the cornea, the sclera is an

• Discrete light receptors are distributed over

– cones (6-7 million per eye) and

• Each one is connected to its own nerve end.

• Cone vision is called photopic (or bright-light

• Several rods are connected to a single nerve

• Cones are most dense in the center of the

• For any given set of conditions, the current

• The eye also discriminates between

• Small values of Weber ratio mean good

• At low levels of illumination brightness

• The typical observer can discern one to two

– i.e. the number of different intensities a person

• Overall intensity discrimination is broad due

• Perceived brightness is not a simple function

CONTRAST CONTRAST CONTRAST

Local change in the brightness of and object and the

Higher the brightness, more is the contrast.

Human eye – sensitive to slow and fast changes

increasing distance from optical axis

Sensitive to intermediate changes

Object borders carry a lot of information for humans.

To aggregate elements provided by low-level operations –

You might also like