Unit-4 Image Restoration
Unit-4 Image Restoration
UNIT - 4
Image Restoration
2
Image restoration
Recover / restore image which has been
degraded by some function or method
Image restoration
g
Degradation Restoration
Function Function ^𝑓 (𝑥 , 𝑦)
𝑓 (𝑥 , 𝑦) +
H S
noise
4
Image restoration
Degraded Degraded Original Noise
image function Image
function
Three methods
1. By observation
function
Three methods
1. By observation
2. By experimentation
function
Three methods
1. By observation
2. By experimentation
3. By modeling
NOISE MODELS
9
Source of Noise
Principle source of noise in digital images
During acquisition
Environmental conditions during image acquisition
Quality of sensor element
During transmission
In wireless network image may be corrupted by
atmospheric disturbance
10
White noise
Fourier spectrum of noise is constant
Different noise
1. Gaussian noise
2. Rayleigh noise
3. Erlang noise (Gamma noise)
4. Exponential noise
5. Uniform noise
6. Impulse noise (salt-and-pepper noise)
13
1. Gaussian noise
Also called Normal noise
Tractable in spatial and frequency domain
because of that mostly used in practice
PDF (probability density function) of
Gaussian random variable z is :
2. Rayleigh noise
PDF
Mean
Variance
15
3. Erlang noise
PDF
Mean
Variance
4. Exponential noise
PDF
Mean
Variance
a>0
Special case of Gamma noise with b=1
17
5. Uniform noise
PDF
Mean
Variance
18
6. Impulse noise
PDF
b>a
Gray-level b appeared as light dot in image
Gray-level a appeared as dark dot in image
This is bipolar impulse noise
If Pa or Pb is zero then called unipolar
impulse noise
Also called “ salt-and-pepper noise ”
19
Example
Image
Without noise
21
Example
Images
With
noise
Histogram
Example
Images
With
noise
Histogram
Spatial Domain
RESTORATION IN THE
PRESENCE OF NOISE
24
2. Order-Statistic filter
1. Median filter
2. Max & Min filter
3. Midpoint filter
4. Alpha-trimmed filter
3. Adaptive filter
1. Local noise reduction filter
2. Median filter
26
1. Mean filter
1. Arithmetic mean filter
1. Mean filter
2. Geometric mean filter
1. Mean filter
29
1. Mean filter
3. Harmonic mean filter
1. Mean filter
4. Contraharmonic mean filter
1. Mean filter
32
1. Mean filter
33
2. Order-Statistic filter
1. Median filter
2. Order-Statistic filter
35
2. Order-Statistic filter
2. Max & Min filter
2. Order-Statistic filter
37
2. Order-Statistic filter
3. Midpoint filter
2. Order-Statistic filter
4. Alpha-trimmed filter
2. Order-Statistic filter
4. Alpha-trimmed filter
d=0
arithmetic filter
d=(mn-1)/2
median filter
other values of d
useful when multiple types of noise is present
like combination of salt-and-pepper and Gaussian
noise
40
2. Order-Statistic filter
41
3. Adaptive Filter
Behavior of filter changes based on
statistical characteristics of the image
inside the filter region defined by Sxy
42
3. Adaptive Filter
1. Adaptive, Local noise reduction filter
3. Adaptive Filter
1. Adaptive, Local noise reduction filter
3. Adaptive Filter
1. Adaptive, Local noise reduction filter
Filter need to behave as follow:
1. If is zero, the filter should return g(x,y)
3. Adaptive Filter
1. Adaptive, Local noise reduction filter
46
3. Adaptive Filter
47
3. Adaptive Filter
2. Adaptive median filter
3. Adaptive Filter
2. Adaptive median filter
3. Adaptive Filter
2. Adaptive median filter
3. Adaptive Filter
2. Adaptive median filter
3. Adaptive Filter
52
Frequency Domain
RESTORATION IN THE
PRESENCE OF NOISE
53
2. Bandpass filter
3. Notch filter
1. Butterworth notch filter
2. Gaussian notch filter
54
1. Bandreject filter
Remove a band of frequencies above the
origin of the Fourier transform
1. Bandreject filter
1. Butterworth bandreject filter of order “n”
1. Bandreject filter
57
2. Bandpass filter
Opposite operation of bandreject filter
2. Bandpass filter
59
3. Notch filter
Rejects or passes frequencies in
predefined neighborhoods about a center
frequency
Due to symmetry in
Fourier transform,
notch filter must
appear in symmetric
pair about the origin
60
3. Notch filter
1. Ideal notch reject filter
Radius D0
Centers at (u0,v0) and (-u0,v0)
where
and
61
3. Notch filter
2. Butterworth notch reject filter with order
“n”
3. Notch filter
Transfer function for notch pass filter can
be obtain from notch reject filter
63
INVERSE FILTERING
64
Inverse filtering
Study restoration of image degraded by
degradation function H
WIENER FILTERING
66
Minimum Mean Square Error
Filtering
This approach incorporates both
degradation function and statistical
characteristic of noise into restoration
process
Consider images and noise as random
variable
Objective to estimate so that mean
square error between and is minimum
Error given by
67
Minimum Mean Square Error
Filtering
Assume image and noise are not
correlated
Compare results
70
Compare results
71
Compare results
72
END
OF
UNIT-4