SlideShare a Scribd company logo
1 of 41
1

NISHA MENON K
MTECH
ROLL NO: 16

15-Nov-13

NOISE MODELS & RESTORATION
OF NOISY IMAGES
NOISE AND IMAGES
15-Nov-13

The sources of noise in digital images
arise during image acquisition
(digitization) and transmission
Imaging sensors can be affected by
ambient conditions
 Interference can be added
to an image during transmission


2
NOISE MODEL
15-Nov-13

Consider a noisy image is modelled as follows:

g ( x, y)  f ( x, y)   ( x, y)
f(x, y)
η(x, y)
g(x, y)

original image pixel
noise term
resulting noisy pixel

3
NOISE MODELS
Spatially independent noise models










15-Nov-13



Gaussian noise
Rayleigh noise
Erlang (Gamma) noise
Uniform noise
Exponential noise
Impulse (salt-and-pepper) noise

Spatially dependent noise model
4


Periodic noise
Gaussian

NOISE MODELS

Rayleigh



Gaussian









15-Nov-13

There are many different
models for the image
noise term η(x, y):
Most common model

Rayleigh
Erlang
Exponential
Uniform
Impulse


Erlang

Exponential

Uniform

Salt and pepper noise

Impulse
5
Noise cannot be predicted but can be approximately described in
statistical way using the probability density function (PDF)
15-Nov-13

Gaussian noise




Electronic circuit noise, sensor noise due
to poor illumination and/or high
temperature
The PDF of a Gaussian random
1
variable, z,
 ( z   ) 2 / 2 2
p( z ) 
e
2 

μ



Mean:



Standard deviation:



Variance:

σ

2

σ
6
RAYLEIGH NOISE
Range imaging






The PDF of Rayleigh noise,

15-Nov-13



2

ab
( )
z 2
za  / for
( )

e
za

p
( 
z b
)

0
for
za


Mean:
 a  /4
 b
b4 
( )
Variance:
2

7
4
ERLANG (GAMMA) NOISE
The PDF of Erlang noise,
integer,

a  0, b is a positive

15-Nov-13



bb z
a a
z1

e for
z0

p)  
(  b1
z ( )!
 0
for
z0

b




Mean:



Variance:

a

b
σ = 2
a
2

8
Exponential noise
15-Nov-13


p z) aeaz
(

Uniform noise

1


p( a
z b
)

0


for b
az



otherwise

Impulse (salt & pepper) noise

P
a

p ) b
( P
z

0


for a
z

for b
z

otherwise

9
NOISE EXAMPLE

This is a suitable pattern to use because
it is composed of simp1e, constant areas
that span the gray scale from black to
near white in only three increments

15-Nov-13

The test pattern to the right is ideal for
demonstrating the addition of noise

Image

Histogram to go here

10

Histogram
NOISE EXAMPLE (CONT…)
15-Nov-13

11

Gaussian

Rayleigh

Erlang
NOISE EXAMPLE (CONT…)
15-Nov-13

Histogram to go here

12

Exponential

Uniform

Impulse
PERIODIC NOISE
15-Nov-13

Typically arises due to
electrical or electromagnetic
interference
Gives rise to regular noise
patterns in an image
Frequency domain techniques in the
Fourier domain are most effective at
removing periodic noise
Periodic noise can be reduced by setting
frequency components corresponding
to noise to zero

13
HOW TO ESTIMATE NOISE
PARAMETERS?




noise

Analyze the FT

 Noise


15-Nov-13

 Periodic

PDFs

Sensor specification
Crop the vertical strips and obtain the histogram.

μ=

 z p(z )
S

i

i

zi

σ =
2

 (z
S

zi

i

 μ) p(zi )
2

14
15-Nov-13

We cannot use the image
histogram to estimate
noise PDF.

It is better to use the
histogram of one area
of an image that has
constant intensity to
estimate noise PDF. 15
RESTORATION IN PRESENCE OF NOISE BY
SPATIAL FILTERING







15-Nov-13

Spatial filters that are based on ordering the pixel
values that make up the neighbourhood operated on
by the filter
Useful spatial filters include
Mean filter
Median filter
Max and min filter
Midpoint filter
Alpha trimmed mean filter

16
MEAN FILTERS
15-Nov-13

Arithmetic mean filter
(AMF, average)
Geometric mean filter

Harmonic mean filter
Contraharmonic mean filter
17
Original image
subimage
15-Nov-13

Statistical parameters
Mean, Median, Mode,
Min, Max, Etc.
Moving
window

18

Output image
MEAN FILTERS
15-Nov-13



Arithmetic mean filter

ˆx ) 1 g,)
f ,  
(y
(t
s
mn
(,)S
s
t xy


Geometric mean filter
1
mn



ˆx )  g , )
f(,y t
(
s
(
s
,) S

xy
 t


19
Harmonic mean filter


15-Nov-13



Works well for salt noise, but fails for pepper noise

mn
1
 ( ,t)
s
( ,) S g
st 
xy

ˆx )
f( ,y 

20


Contraharmonic mean filter

: eliminates pepper noise

Q0

15-Nov-13

Q0

: eliminates salt noise

gst Q1
(, ) 


( xy
ˆ xy s,t) S
f( , )
Q
g,
(
 st)
( ,) S
st xy

For Q = 0, the filter reduces to an arithmetic mean filter.
For Q = -1, the filter reduces to a harmonic mean filter.

21
Image
Corrupted by
guassian noise
15-Nov-13

Filtering
with
Arithmetic
mean filter

Filtering with
geometric
mean filter

22
15-Nov-13

Corrupted by
pepper noise

Corrupted by
salt
noise

Contraharmonic
filter Q= -1.5
Contraharmonic
filter Q=1.5

23


Usage


Image
obtained
using a contraharmonic
mean filter
With Q=-1.5

15-Nov-13



Arithmetic and geometric mean filters: suited for
Gaussian or uniform noise
Contraharmonic filters: suited for impulse noise but
necessary to know whether noise is dark or light for
selecting Q value

Image
obtained
using a contraharmonic
mean filter
With Q=1.5

24
ORDER-STATISTICS FILTERS
15-Nov-13

Median filter

Max and min filters

Midpoint filter

Alpha-trimmed mean filter
25
MEDIAN FILTER
15-Nov-13

ˆ
f ( x, y )  median{g ( s, t )}
( s ,t )S xy

Excellent at noise removal, without the smoothing
effects that can occur with other smoothing filters
Particularly good when salt and pepper noise is
present.
26
MIDPOINT FILTER
15-Nov-13

Midpoint Filter:

ˆ ( x, y )  1  max {g ( s, t )}  min {g ( s, t )}
f

( s ,t )S xy
2 ( s ,t )S xy


Good for random Gaussian and uniform noise

27
MAX AND MIN FILTER

ˆ
f ( x, y )  max {g ( s, t )}

15-Nov-13

Max Filter:
( s ,t )S xy

Min Filter:

ˆ
f ( x, y )  min {g ( s, t )}
( s ,t )S xy

Max filter is good for pepper noise and min is good for
salt noise
28
ALPHA-TRIMMED MEAN FILTER

ˆ
f ( x, y) 

1
S gr (s, t )
mn  d ( s ,t ) xy

15-Nov-13

Alpha-Trimmed Mean Filter:

We can delete the d/2 lowest and d/2 highest grey
levels
So gr(s, t) represents the remaining mn – d pixels
Useful in situations involving multiple types of
noise, such as a combination of salt-and-pepper and
Gaussian noise
29
15-Nov-13

Corrupted by
salt and
pepper noise

After
passing
through
Median
filter

30
15-Nov-13

max filter

min filter
31
Image
corrupted
by additive
uniform
noise

Arithmetic mean
filter

Geometric
mean filter

15-Nov-13

Median filter

Image
additionally
corrupted
by additive
salt-andpepper
noise

Alpha trimme
mean filter

32
ADAPTIVE FILTERS
15-Nov-13

The filters discussed so far are applied to an entire
image without any regard for how image
characteristics vary from one point to another
The behaviour of adaptive filters changes depending
on the characteristics of the image inside the filter
region

33
General concept:

-Filter behavior depends on statistical characteristics of local areas
inside mxn moving window

Statistical characteristics:
Local mean:

1
mL =
 g(s,t)
mn (s,t)S xy

Noise variance:



2

Local variance:

1
σ =
(g(s,t)  mL )2

mn (s,t)S xy
2
L

34

15-Nov-13

- More complex but superior performance compared with “fixed”
filters
Adaptive, Local Noise Reduction Filter
Purpose: want to preserve edges
15-Nov-13

Concept:
If 2 is zero,  No noise
the filter should return g(x,y) because g(x,y) = f(x,y)
If L2 is high relative to 2,  Edges (should be preserved),
the filter should return the value close to g(x,y)
If L2 = 2,  Local area has same properties as overall image.
The filter should return the arithmetic mean value mL

Formula:

x
ˆ,)g ) (y 
f y (y  ,)
(  g m
x
x
,

2

2
L

L

35
Adaptive Median Filtering
15-Nov-13

zmin = minimum gray level value in Sxy
zmax = maximum gray level value in Sxy
zmedian = median of gray levels in Sxy

zxy = gray level value at pixel (x,y)
where

Smax = maximum allowed size of Sxy

36
Algorithm

Return zxy  to preserve original details
Else return zmedian  to remove impulse

15-Nov-13

Level A:
Determine
A1= zmedian – zmin
whether zmedian
A2= zmedian – zmax
is an impulse or not
If A1 > 0 and A 2 < 0,  zmedian is not an impulse
goto level B
Else  Window is not big enough
increase window size
If window size <= Smax repeat level A
Else return zxy
Level B:
Determine
B1= zxy – zmin
whether zxy
B2= zxy – zmax
is an impulse or not
If B1 > 0 and B2 < 0  zxy is not an impulse

37
Purposes of the algorithm
Remove salt-and-pepper (impulse) noise



Provide smoothing of other noise



15-Nov-13



Reduce distortion, such as excessive thinning or
thickening of object boundaries

38
ADAPTIVE FILTERING EXAMPLE
15-Nov-13

Image corrupted by salt
and pepper noise with
probabilities Pa = Pb=0.25

Result of filtering with a 7
* 7 median filter

Result of adaptive
median filtering with
Smax = 7
39
CONCLUSION





Different types of noise pdfs have been discussed
Estimation of noise parameters
Restoration of images using
Order- Statistic filters
Adaptive filters

15-Nov-13



40
15-Nov-13

41

More Related Content

What's hot

Smoothing Filters in Spatial Domain
Smoothing Filters in Spatial DomainSmoothing Filters in Spatial Domain
Smoothing Filters in Spatial DomainMadhu Bala
 
Image Restoration (Digital Image Processing)
Image Restoration (Digital Image Processing)Image Restoration (Digital Image Processing)
Image Restoration (Digital Image Processing)Kalyan Acharjya
 
Image Filtering in the Frequency Domain
Image Filtering in the Frequency DomainImage Filtering in the Frequency Domain
Image Filtering in the Frequency DomainAmnaakhaan
 
Image Enhancement using Frequency Domain Filters
Image Enhancement using Frequency Domain FiltersImage Enhancement using Frequency Domain Filters
Image Enhancement using Frequency Domain FiltersKarthika Ramachandran
 
Image processing second unit Notes
Image processing second unit NotesImage processing second unit Notes
Image processing second unit NotesAAKANKSHA JAIN
 
Histogram Processing
Histogram ProcessingHistogram Processing
Histogram ProcessingAmnaakhaan
 
Noise filtering
Noise filteringNoise filtering
Noise filteringAlaa Ahmed
 
Fundamentals and image compression models
Fundamentals and image compression modelsFundamentals and image compression models
Fundamentals and image compression modelslavanya marichamy
 
Digital Image Processing_ ch2 enhancement spatial-domain
Digital Image Processing_ ch2 enhancement spatial-domainDigital Image Processing_ ch2 enhancement spatial-domain
Digital Image Processing_ ch2 enhancement spatial-domainMalik obeisat
 
Homomorphic filtering
Homomorphic filteringHomomorphic filtering
Homomorphic filteringGautam Saxena
 
Chapter 6 color image processing
Chapter 6 color image processingChapter 6 color image processing
Chapter 6 color image processingasodariyabhavesh
 
08 frequency domain filtering DIP
08 frequency domain filtering DIP08 frequency domain filtering DIP
08 frequency domain filtering DIPbabak danyal
 
Image processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filtersImage processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filtersKuppusamy P
 
1.arithmetic & logical operations
1.arithmetic & logical operations1.arithmetic & logical operations
1.arithmetic & logical operationsmukesh bhardwaj
 

What's hot (20)

Smoothing Filters in Spatial Domain
Smoothing Filters in Spatial DomainSmoothing Filters in Spatial Domain
Smoothing Filters in Spatial Domain
 
Image Restoration (Digital Image Processing)
Image Restoration (Digital Image Processing)Image Restoration (Digital Image Processing)
Image Restoration (Digital Image Processing)
 
Image Filtering in the Frequency Domain
Image Filtering in the Frequency DomainImage Filtering in the Frequency Domain
Image Filtering in the Frequency Domain
 
Image restoration and reconstruction
Image restoration and reconstructionImage restoration and reconstruction
Image restoration and reconstruction
 
Image Enhancement using Frequency Domain Filters
Image Enhancement using Frequency Domain FiltersImage Enhancement using Frequency Domain Filters
Image Enhancement using Frequency Domain Filters
 
Image processing second unit Notes
Image processing second unit NotesImage processing second unit Notes
Image processing second unit Notes
 
Histogram Processing
Histogram ProcessingHistogram Processing
Histogram Processing
 
Noise filtering
Noise filteringNoise filtering
Noise filtering
 
Fundamentals and image compression models
Fundamentals and image compression modelsFundamentals and image compression models
Fundamentals and image compression models
 
Digital Image Processing_ ch2 enhancement spatial-domain
Digital Image Processing_ ch2 enhancement spatial-domainDigital Image Processing_ ch2 enhancement spatial-domain
Digital Image Processing_ ch2 enhancement spatial-domain
 
Sharpening spatial filters
Sharpening spatial filtersSharpening spatial filters
Sharpening spatial filters
 
Unit3 dip
Unit3 dipUnit3 dip
Unit3 dip
 
Spatial domain and filtering
Spatial domain and filteringSpatial domain and filtering
Spatial domain and filtering
 
Image compression
Image compressionImage compression
Image compression
 
Homomorphic filtering
Homomorphic filteringHomomorphic filtering
Homomorphic filtering
 
Chapter 6 color image processing
Chapter 6 color image processingChapter 6 color image processing
Chapter 6 color image processing
 
Image compression .
Image compression .Image compression .
Image compression .
 
08 frequency domain filtering DIP
08 frequency domain filtering DIP08 frequency domain filtering DIP
08 frequency domain filtering DIP
 
Image processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filtersImage processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filters
 
1.arithmetic & logical operations
1.arithmetic & logical operations1.arithmetic & logical operations
1.arithmetic & logical operations
 

Viewers also liked

Homomorphic Filtering of Speckle Noise From Computerized Tomography (CT) Imag...
Homomorphic Filtering of Speckle Noise From Computerized Tomography (CT) Imag...Homomorphic Filtering of Speckle Noise From Computerized Tomography (CT) Imag...
Homomorphic Filtering of Speckle Noise From Computerized Tomography (CT) Imag...CSCJournals
 
Image Denoising using Spatial Domain Filters: A Quantitative Study
Image Denoising using Spatial Domain Filters: A Quantitative StudyImage Denoising using Spatial Domain Filters: A Quantitative Study
Image Denoising using Spatial Domain Filters: A Quantitative StudyAnmol Sharma
 
Image degradation and noise by Md.Naseem Ashraf
Image degradation and noise by Md.Naseem AshrafImage degradation and noise by Md.Naseem Ashraf
Image degradation and noise by Md.Naseem AshrafMD Naseem Ashraf
 
Poisson distribution
Poisson distributionPoisson distribution
Poisson distributionAntiqNyke
 
filters for noise in image processing
filters for noise in image processingfilters for noise in image processing
filters for noise in image processingSardar Alam
 
Noise in Communication System
Noise in Communication SystemNoise in Communication System
Noise in Communication SystemIzah Asmadi
 
survey paper for image denoising
survey paper for image denoisingsurvey paper for image denoising
survey paper for image denoisingArti Singh
 

Viewers also liked (8)

Homomorphic Filtering of Speckle Noise From Computerized Tomography (CT) Imag...
Homomorphic Filtering of Speckle Noise From Computerized Tomography (CT) Imag...Homomorphic Filtering of Speckle Noise From Computerized Tomography (CT) Imag...
Homomorphic Filtering of Speckle Noise From Computerized Tomography (CT) Imag...
 
Image Denoising using Spatial Domain Filters: A Quantitative Study
Image Denoising using Spatial Domain Filters: A Quantitative StudyImage Denoising using Spatial Domain Filters: A Quantitative Study
Image Denoising using Spatial Domain Filters: A Quantitative Study
 
Image degradation and noise by Md.Naseem Ashraf
Image degradation and noise by Md.Naseem AshrafImage degradation and noise by Md.Naseem Ashraf
Image degradation and noise by Md.Naseem Ashraf
 
Types of noise
Types of noiseTypes of noise
Types of noise
 
Poisson distribution
Poisson distributionPoisson distribution
Poisson distribution
 
filters for noise in image processing
filters for noise in image processingfilters for noise in image processing
filters for noise in image processing
 
Noise in Communication System
Noise in Communication SystemNoise in Communication System
Noise in Communication System
 
survey paper for image denoising
survey paper for image denoisingsurvey paper for image denoising
survey paper for image denoising
 

Similar to Restoring Noisy Images Using Noise Models and Spatial Filtering Techniques

restoration_recon_chap5_GW.pdf
restoration_recon_chap5_GW.pdfrestoration_recon_chap5_GW.pdf
restoration_recon_chap5_GW.pdfSUBHASHREEBASU5
 
Digital Image restoration
Digital Image restorationDigital Image restoration
Digital Image restorationMd Shabir Alam
 
Image Restoration
Image RestorationImage Restoration
Image RestorationPoonam Seth
 
Lecture 6-2023.pdf
Lecture 6-2023.pdfLecture 6-2023.pdf
Lecture 6-2023.pdfssuserff72e4
 
Noise Performance of CW system
Noise Performance of CW systemNoise Performance of CW system
Noise Performance of CW systemDr Naim R Kidwai
 
Ch5_Restoration (1).pdf
Ch5_Restoration (1).pdfCh5_Restoration (1).pdf
Ch5_Restoration (1).pdfAlaaElhaddad3
 
Image restoration1
Image restoration1Image restoration1
Image restoration1moorthim7
 
Image Restoration (Order Statistics Filters)
Image Restoration (Order Statistics Filters)Image Restoration (Order Statistics Filters)
Image Restoration (Order Statistics Filters)Kalyan Acharjya
 
Image_filtering (1).pptx
Image_filtering (1).pptxImage_filtering (1).pptx
Image_filtering (1).pptxwdwd10
 
Image Restoration And Reconstruction
Image Restoration And ReconstructionImage Restoration And Reconstruction
Image Restoration And ReconstructionAmnaakhaan
 
Vidyalankar final-essentials of communication systems
Vidyalankar final-essentials of communication systemsVidyalankar final-essentials of communication systems
Vidyalankar final-essentials of communication systemsanilkurhekar
 
Analysis of Non Linear Filters with Various Density of Impulse Noise for Diff...
Analysis of Non Linear Filters with Various Density of Impulse Noise for Diff...Analysis of Non Linear Filters with Various Density of Impulse Noise for Diff...
Analysis of Non Linear Filters with Various Density of Impulse Noise for Diff...IJERA Editor
 
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...Md. Shohel Rana
 

Similar to Restoring Noisy Images Using Noise Models and Spatial Filtering Techniques (20)

Chapter 5
Chapter 5Chapter 5
Chapter 5
 
restoration_recon_chap5_GW.pdf
restoration_recon_chap5_GW.pdfrestoration_recon_chap5_GW.pdf
restoration_recon_chap5_GW.pdf
 
Digital Image restoration
Digital Image restorationDigital Image restoration
Digital Image restoration
 
Gg2411291135
Gg2411291135Gg2411291135
Gg2411291135
 
234456743edc.pdf
234456743edc.pdf234456743edc.pdf
234456743edc.pdf
 
Image Restoration
Image RestorationImage Restoration
Image Restoration
 
Lecture 6-2023.pdf
Lecture 6-2023.pdfLecture 6-2023.pdf
Lecture 6-2023.pdf
 
Noise Performance of CW system
Noise Performance of CW systemNoise Performance of CW system
Noise Performance of CW system
 
D122733
D122733D122733
D122733
 
Ch5_Restoration (1).pdf
Ch5_Restoration (1).pdfCh5_Restoration (1).pdf
Ch5_Restoration (1).pdf
 
Image restoration1
Image restoration1Image restoration1
Image restoration1
 
Image Restoration (Order Statistics Filters)
Image Restoration (Order Statistics Filters)Image Restoration (Order Statistics Filters)
Image Restoration (Order Statistics Filters)
 
Image_filtering (1).pptx
Image_filtering (1).pptxImage_filtering (1).pptx
Image_filtering (1).pptx
 
Image Restoration And Reconstruction
Image Restoration And ReconstructionImage Restoration And Reconstruction
Image Restoration And Reconstruction
 
Chap6 image restoration
Chap6 image restorationChap6 image restoration
Chap6 image restoration
 
Vidyalankar final-essentials of communication systems
Vidyalankar final-essentials of communication systemsVidyalankar final-essentials of communication systems
Vidyalankar final-essentials of communication systems
 
DIP -Unit 3 ppt.pptx
DIP -Unit 3 ppt.pptxDIP -Unit 3 ppt.pptx
DIP -Unit 3 ppt.pptx
 
Analysis of Non Linear Filters with Various Density of Impulse Noise for Diff...
Analysis of Non Linear Filters with Various Density of Impulse Noise for Diff...Analysis of Non Linear Filters with Various Density of Impulse Noise for Diff...
Analysis of Non Linear Filters with Various Density of Impulse Noise for Diff...
 
Image denoising
Image denoisingImage denoising
Image denoising
 
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...
Speckle Noise Reduction in Ultrasound Images using Adaptive and Anisotropic D...
 

More from Nisha Menon K

High capacity optical
High capacity opticalHigh capacity optical
High capacity opticalNisha Menon K
 
non line of sight error detection in mobile communication by nisha menon k
non line of sight error detection in mobile communication by nisha menon knon line of sight error detection in mobile communication by nisha menon k
non line of sight error detection in mobile communication by nisha menon kNisha Menon K
 
cognitive femtocell network by nisha menon k
cognitive femtocell network by nisha menon kcognitive femtocell network by nisha menon k
cognitive femtocell network by nisha menon kNisha Menon K
 
unified threat management by Nisha Menon K
 unified threat management by Nisha Menon K unified threat management by Nisha Menon K
unified threat management by Nisha Menon KNisha Menon K
 
Future of Wireless Technology
Future of Wireless TechnologyFuture of Wireless Technology
Future of Wireless TechnologyNisha Menon K
 
Delta encoding in data compression by Nisha Menon K studying mtech at fisat
Delta encoding in data compression by Nisha Menon K studying mtech at fisat Delta encoding in data compression by Nisha Menon K studying mtech at fisat
Delta encoding in data compression by Nisha Menon K studying mtech at fisat Nisha Menon K
 
Securing underwater wireless communication by Nisha Menon K
Securing underwater wireless communication by Nisha Menon KSecuring underwater wireless communication by Nisha Menon K
Securing underwater wireless communication by Nisha Menon KNisha Menon K
 

More from Nisha Menon K (11)

High capacity optical
High capacity opticalHigh capacity optical
High capacity optical
 
Digital signature
Digital signatureDigital signature
Digital signature
 
non line of sight error detection in mobile communication by nisha menon k
non line of sight error detection in mobile communication by nisha menon knon line of sight error detection in mobile communication by nisha menon k
non line of sight error detection in mobile communication by nisha menon k
 
cognitive femtocell network by nisha menon k
cognitive femtocell network by nisha menon kcognitive femtocell network by nisha menon k
cognitive femtocell network by nisha menon k
 
unified threat management by Nisha Menon K
 unified threat management by Nisha Menon K unified threat management by Nisha Menon K
unified threat management by Nisha Menon K
 
Future of Wireless Technology
Future of Wireless TechnologyFuture of Wireless Technology
Future of Wireless Technology
 
Delta encoding in data compression by Nisha Menon K studying mtech at fisat
Delta encoding in data compression by Nisha Menon K studying mtech at fisat Delta encoding in data compression by Nisha Menon K studying mtech at fisat
Delta encoding in data compression by Nisha Menon K studying mtech at fisat
 
Turbo equalization
Turbo equalizationTurbo equalization
Turbo equalization
 
Securing underwater wireless communication by Nisha Menon K
Securing underwater wireless communication by Nisha Menon KSecuring underwater wireless communication by Nisha Menon K
Securing underwater wireless communication by Nisha Menon K
 
Femtocells
FemtocellsFemtocells
Femtocells
 
Skinput
SkinputSkinput
Skinput
 

Recently uploaded

Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessPixlogix Infotech
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 

Recently uploaded (20)

Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 

Restoring Noisy Images Using Noise Models and Spatial Filtering Techniques

  • 1. 1 NISHA MENON K MTECH ROLL NO: 16 15-Nov-13 NOISE MODELS & RESTORATION OF NOISY IMAGES
  • 2. NOISE AND IMAGES 15-Nov-13 The sources of noise in digital images arise during image acquisition (digitization) and transmission Imaging sensors can be affected by ambient conditions  Interference can be added to an image during transmission  2
  • 3. NOISE MODEL 15-Nov-13 Consider a noisy image is modelled as follows: g ( x, y)  f ( x, y)   ( x, y) f(x, y) η(x, y) g(x, y) original image pixel noise term resulting noisy pixel 3
  • 4. NOISE MODELS Spatially independent noise models        15-Nov-13  Gaussian noise Rayleigh noise Erlang (Gamma) noise Uniform noise Exponential noise Impulse (salt-and-pepper) noise Spatially dependent noise model 4  Periodic noise
  • 5. Gaussian NOISE MODELS Rayleigh  Gaussian       15-Nov-13 There are many different models for the image noise term η(x, y): Most common model Rayleigh Erlang Exponential Uniform Impulse  Erlang Exponential Uniform Salt and pepper noise Impulse 5
  • 6. Noise cannot be predicted but can be approximately described in statistical way using the probability density function (PDF) 15-Nov-13 Gaussian noise   Electronic circuit noise, sensor noise due to poor illumination and/or high temperature The PDF of a Gaussian random 1 variable, z,  ( z   ) 2 / 2 2 p( z )  e 2  μ  Mean:  Standard deviation:  Variance: σ 2 σ 6
  • 7. RAYLEIGH NOISE Range imaging    The PDF of Rayleigh noise, 15-Nov-13  2  ab ( ) z 2 za  / for ( )  e za  p (  z b )  0 for za   Mean:  a  /4  b b4  ( ) Variance: 2  7 4
  • 8. ERLANG (GAMMA) NOISE The PDF of Erlang noise, integer, a  0, b is a positive 15-Nov-13  bb z a a z1  e for z0  p)   (  b1 z ( )!  0 for z0  b   Mean:  Variance: a b σ = 2 a 2 8
  • 9. Exponential noise 15-Nov-13  p z) aeaz ( Uniform noise 1   p( a z b )  0  for b az   otherwise Impulse (salt & pepper) noise P a  p ) b ( P z  0  for a z  for b z  otherwise 9
  • 10. NOISE EXAMPLE This is a suitable pattern to use because it is composed of simp1e, constant areas that span the gray scale from black to near white in only three increments 15-Nov-13 The test pattern to the right is ideal for demonstrating the addition of noise Image Histogram to go here 10 Histogram
  • 12. NOISE EXAMPLE (CONT…) 15-Nov-13 Histogram to go here 12 Exponential Uniform Impulse
  • 13. PERIODIC NOISE 15-Nov-13 Typically arises due to electrical or electromagnetic interference Gives rise to regular noise patterns in an image Frequency domain techniques in the Fourier domain are most effective at removing periodic noise Periodic noise can be reduced by setting frequency components corresponding to noise to zero 13
  • 14. HOW TO ESTIMATE NOISE PARAMETERS?   noise Analyze the FT  Noise  15-Nov-13  Periodic PDFs Sensor specification Crop the vertical strips and obtain the histogram. μ=  z p(z ) S i i zi σ = 2  (z S zi i  μ) p(zi ) 2 14
  • 15. 15-Nov-13 We cannot use the image histogram to estimate noise PDF. It is better to use the histogram of one area of an image that has constant intensity to estimate noise PDF. 15
  • 16. RESTORATION IN PRESENCE OF NOISE BY SPATIAL FILTERING      15-Nov-13 Spatial filters that are based on ordering the pixel values that make up the neighbourhood operated on by the filter Useful spatial filters include Mean filter Median filter Max and min filter Midpoint filter Alpha trimmed mean filter 16
  • 17. MEAN FILTERS 15-Nov-13 Arithmetic mean filter (AMF, average) Geometric mean filter Harmonic mean filter Contraharmonic mean filter 17
  • 18. Original image subimage 15-Nov-13 Statistical parameters Mean, Median, Mode, Min, Max, Etc. Moving window 18 Output image
  • 19. MEAN FILTERS 15-Nov-13  Arithmetic mean filter ˆx ) 1 g,) f ,   (y (t s mn (,)S s t xy  Geometric mean filter 1 mn   ˆx )  g , ) f(,y t ( s ( s ,) S  xy  t  19
  • 20. Harmonic mean filter  15-Nov-13  Works well for salt noise, but fails for pepper noise mn 1  ( ,t) s ( ,) S g st  xy ˆx ) f( ,y  20
  • 21.  Contraharmonic mean filter : eliminates pepper noise Q0 15-Nov-13 Q0 : eliminates salt noise gst Q1 (, )   ( xy ˆ xy s,t) S f( , ) Q g, (  st) ( ,) S st xy For Q = 0, the filter reduces to an arithmetic mean filter. For Q = -1, the filter reduces to a harmonic mean filter. 21
  • 22. Image Corrupted by guassian noise 15-Nov-13 Filtering with Arithmetic mean filter Filtering with geometric mean filter 22
  • 23. 15-Nov-13 Corrupted by pepper noise Corrupted by salt noise Contraharmonic filter Q= -1.5 Contraharmonic filter Q=1.5 23
  • 24.  Usage  Image obtained using a contraharmonic mean filter With Q=-1.5 15-Nov-13  Arithmetic and geometric mean filters: suited for Gaussian or uniform noise Contraharmonic filters: suited for impulse noise but necessary to know whether noise is dark or light for selecting Q value Image obtained using a contraharmonic mean filter With Q=1.5 24
  • 25. ORDER-STATISTICS FILTERS 15-Nov-13 Median filter Max and min filters Midpoint filter Alpha-trimmed mean filter 25
  • 26. MEDIAN FILTER 15-Nov-13 ˆ f ( x, y )  median{g ( s, t )} ( s ,t )S xy Excellent at noise removal, without the smoothing effects that can occur with other smoothing filters Particularly good when salt and pepper noise is present. 26
  • 27. MIDPOINT FILTER 15-Nov-13 Midpoint Filter: ˆ ( x, y )  1  max {g ( s, t )}  min {g ( s, t )} f  ( s ,t )S xy 2 ( s ,t )S xy   Good for random Gaussian and uniform noise 27
  • 28. MAX AND MIN FILTER ˆ f ( x, y )  max {g ( s, t )} 15-Nov-13 Max Filter: ( s ,t )S xy Min Filter: ˆ f ( x, y )  min {g ( s, t )} ( s ,t )S xy Max filter is good for pepper noise and min is good for salt noise 28
  • 29. ALPHA-TRIMMED MEAN FILTER ˆ f ( x, y)  1 S gr (s, t ) mn  d ( s ,t ) xy 15-Nov-13 Alpha-Trimmed Mean Filter: We can delete the d/2 lowest and d/2 highest grey levels So gr(s, t) represents the remaining mn – d pixels Useful in situations involving multiple types of noise, such as a combination of salt-and-pepper and Gaussian noise 29
  • 30. 15-Nov-13 Corrupted by salt and pepper noise After passing through Median filter 30
  • 32. Image corrupted by additive uniform noise Arithmetic mean filter Geometric mean filter 15-Nov-13 Median filter Image additionally corrupted by additive salt-andpepper noise Alpha trimme mean filter 32
  • 33. ADAPTIVE FILTERS 15-Nov-13 The filters discussed so far are applied to an entire image without any regard for how image characteristics vary from one point to another The behaviour of adaptive filters changes depending on the characteristics of the image inside the filter region 33
  • 34. General concept: -Filter behavior depends on statistical characteristics of local areas inside mxn moving window Statistical characteristics: Local mean: 1 mL =  g(s,t) mn (s,t)S xy Noise variance:  2 Local variance: 1 σ = (g(s,t)  mL )2  mn (s,t)S xy 2 L 34 15-Nov-13 - More complex but superior performance compared with “fixed” filters
  • 35. Adaptive, Local Noise Reduction Filter Purpose: want to preserve edges 15-Nov-13 Concept: If 2 is zero,  No noise the filter should return g(x,y) because g(x,y) = f(x,y) If L2 is high relative to 2,  Edges (should be preserved), the filter should return the value close to g(x,y) If L2 = 2,  Local area has same properties as overall image. The filter should return the arithmetic mean value mL Formula: x ˆ,)g ) (y  f y (y  ,) (  g m x x ,  2 2 L L 35
  • 36. Adaptive Median Filtering 15-Nov-13 zmin = minimum gray level value in Sxy zmax = maximum gray level value in Sxy zmedian = median of gray levels in Sxy zxy = gray level value at pixel (x,y) where Smax = maximum allowed size of Sxy 36
  • 37. Algorithm Return zxy  to preserve original details Else return zmedian  to remove impulse 15-Nov-13 Level A: Determine A1= zmedian – zmin whether zmedian A2= zmedian – zmax is an impulse or not If A1 > 0 and A 2 < 0,  zmedian is not an impulse goto level B Else  Window is not big enough increase window size If window size <= Smax repeat level A Else return zxy Level B: Determine B1= zxy – zmin whether zxy B2= zxy – zmax is an impulse or not If B1 > 0 and B2 < 0  zxy is not an impulse 37
  • 38. Purposes of the algorithm Remove salt-and-pepper (impulse) noise  Provide smoothing of other noise  15-Nov-13  Reduce distortion, such as excessive thinning or thickening of object boundaries 38
  • 39. ADAPTIVE FILTERING EXAMPLE 15-Nov-13 Image corrupted by salt and pepper noise with probabilities Pa = Pb=0.25 Result of filtering with a 7 * 7 median filter Result of adaptive median filtering with Smax = 7 39
  • 40. CONCLUSION   Different types of noise pdfs have been discussed Estimation of noise parameters Restoration of images using Order- Statistic filters Adaptive filters 15-Nov-13  40