SlideShare a Scribd company logo
1 of 60
Noise Addition and Filtering

`

Presented By : Sara El-Masri
Alaa Sababbah
Amna El-Sheikh Ali
Supervised By : Dr. Samy Salamah
Outline
1. Introduction
ā€¢ It is generally desirable for image brightness to be
uniform except where it changes to form an image.
ā€¢ There are factors, however, that tend to produce
variation in the brightness of a displayed image even
when no image detail is present.
ā€¢ This variation is usually random and has no particular
pattern.
1. Introduction (cont.)
In many cases, it reduces image quality and is especially
significant when the objects being imaged are small and have
relatively low contrast.

This random variation in image brightness is
designated noise.
1. Introduction (cont.)
Image on the right has more noise
than the image on the left
Images
ā€¢ There are two types of images :

ļƒ¼

Vector images

ļƒ¼

Digital images
Vector Images
ā€¢ Vector images made up of vectors which lead through
locations called control points.

ā€¢ Each of these control points has define on the x and y axes
of the work plain .
Digital Images
ā€¢ A digital image is 2-dim array of real numbers
ā€¢ 2-D image is divided into N rows and M columns
ā€¢ the intersection of these rows and columns is known as pixels
Types of Digital Images
ā€¢ Binary images (black and white images)
ā€¢ Gray scale images
ā€¢ Color images
Binary Images
ā€¢ Each pixel is just black or white
ā€¢ There is only two possible values for each pixel
i.e. 0 or 1
Gray Scale Images
ā€¢ Each pixel value of gray scale images normally from
0 (black) to 255 (white)
Color images
ā€¢ In color images each pixel has a particular color ; that
color being described by the amount of red , blue and
green in it .
ā€¢ Each of these components has a rang 0-255
2. Image noise
Noise in image , is any degradation in an image signal ,
caused by external disturbance while an image is
being sent from one place to another place via satellite
, wireless and network cable .
We can model a noisy image as follows:
Source of Image Noise
ā€¢ Error occurs in image signal while an image is being sent
electronically from one place to another .
ā€¢ Sensor heat while clicking an image
ā€¢ ISO factor ISO number indicates how quickly a cameraā€™s sensor
absorbs , light , higher ISO used mare chance of noticeable noise
ā€¢ By memory cell failure.
Types of Image Noise
1) Salt and pepper noise
2) Gaussian noise
3) Speckle noise

4) Uniform noise
Salt and pepper noise
ā€¢ It known as shot noise, impulse noise or Spike noise .
ā€¢ Its appearance is randomly scattered white or black or
both pixel over the image .

ā€¢ there are only two possible values exists that is a and b
and the probability of each is less than 0.2 .
Salt and pepper noise (cont.)
Reasons for Salt and Pepper Noise:
1)
2)
3)

By memory cell failure.
By malfunctioning of cameraā€™s sensor cells.
By synchronization errors in image digitizing or transmission.

Where: pa, pb are the Probabilities Density Function (PDF), p(z) is distribution
salt and pepper noise in image and A, B are the arrays size image.
Salt and pepper noise (cont.)
Image with Salt and
Pepper

Original Image
Salt and pepper noise (cont.)
ā€¢ filtering techniques :
ļƒ¼ mean filtering .
ļƒ¼ Median filtering
ļƒ¼ Gaussian filtering
Gaussian Noise
Gaussian noise is caused by random fluctuations in the
signal , its modeled by random values add to an image
This noise has a probability density function [pdf] of the
normal distribution. It is also known as Gaussian
distribution.
Gaussian Noise (cont.)

Without Noise

With Gaussian Noise
Image with Gaussian Noise
Sources of Gaussian Noise
ā€¢ In digital images arise during acquisition .
e.g. Sensor noise caused by poor illumination and/or high
temperature
ā€¢ Transmission
e.g. Electronic circuit noise .
Gaussian Noise (cont.)
ā€¢ filtering techniques :
ļƒ¼mean (convolution) filtering
ļƒ¼Median filtering
ļƒ¼Gaussian filtering
Speckle Noise
ā€¢ Speckle noise can be modeled by random values multiplied
by pixel values of an image
ā€¢ results from random fluctuations in the return signal from
an object that is no bigger than a single image-processing
element.
It increases the mean grey level of a local area.
Speckle Noise
The distribution noise can be expressed by:

Where g(n,m), is the observed image , u(n,m) is the multiplicative
component . and &(n,m) is the additive component of the speckle noise.
Original Image

Image with Noise
Speckle Noise (cont.)
ā€¢ filtering techniques :
ļƒ¼mean (convolution) filtering
ļƒ¼Median filtering
Uniform Noise
ā€¢ The uniform noise cause by quantizing the pixels of image
to a number of distinct levels is known as quantization
noise.
ā€¢ Uniform noise can be analytically described by :

ā€¢ The gray level values of the noise are evenly distributed across
a specific range
Uniform Noise (cont.)
ā€¢ Quantization noise has an approximately uniform
distribution
Uniform Noise (cont.)
3. Filtering
ā€¢ Filtering image data is a standard process used in
almost all image processing systems.
ā€¢ Filters are used to remove noise from digital image
while keeping the details of image preserved.
ā€¢ The choice of filter is determined by
ļƒ¼ the nature of the task performed by filter .
ļƒ¼ Filter behavior .
ļƒ¼ type of the data .
Filtering Techniques

Linear Filtering

Non-Linear Filtering
Linear Filter
ā€¢ Linear filters are used to remove certain type of noise.

ā€¢ The linear filters work best with salt and pepper noise, and
Gaussian noise.
ā€¢ Gaussian and mean filters.

ā€¢ Simple to design .
ā€¢ These filters also
ļƒ¼ tend to blur the sharp edges .
ļƒ¼ destroy the lines and other fine details of image .
Linear Filters ā€“ Example

Filtered Gaussian
noise.
Non-Linear Filters
ā€¢ Can preserve edges .
ā€¢ Very effective at removing impulsive noise .
ā€¢ They are more powerful than linear filters because they
are able to reduce noise levels without blurring edges.
ā€¢ Can be difficult to design.
ā€¢ Median Filter.
Non-linear Filter vs. linear Filter
Filters Types
1)

Median filter .

2)

Wiener Filter .

3)

Mean filter .

4)

Gaussian filter
Median Filter
ā€¢ Median Filter is a simple and powerful non-linear filter .

ā€¢ It is used for reducing the amount of intensity variation
between one pixel and the other pixel.
ā€¢ In this filter, we replaces pixel value with the median value .
ā€¢ The median is calculated by first sorting all the pixel values into
ascending order and then replace the pixel being calculated
with the middle pixel value

ā€¢ Salt and pepper noise.
Median Filter
ā€¢ Advantage:
ļƒ¼ It is easy to implement.
ļƒ¼ Used for de-noising different types of noises.

ā€¢ Disadvantage:
ļƒ¼ Median Filter tends to remove image details when the impulse
noise percentage is more than 0.4 %.
Example : 3x3 Median
Original

Salt & pepper
%20

De-noising by
Median filter

Original

Salt & pepper
%60

De-noising by
Median filter
Wiener Filter
ā€¢ The purpose of the Wiener filter is to filter out the
noise that has corrupted a signal.
ā€¢ This filter is based on a statistical approach.
ā€¢ The goal of wiener filter is reduced the mean square
error (MSE) as much as possible.
ā€¢ Poisson noise , speckle noise .
Wiener Filter
ā€¢ One method that we assume we have knowledge of the
spectral property of the noise and original signal.

ā€¢
ā€¢
ā€¢
ā€¢
ā€¢

The Fourier domain of the Wiener filter is Where :
H*(u, v) = Complex conjugate of degradation function
Pn (u, v) = Power Spectral Density of Noise
Ps (u, v) = Power Spectral Density of non-degraded image
H (u, v) = Degradation function
Wiener filter Example
Mean Filter
ā€¢ Mean Filter (average filter) is a simple linear filter .
ā€¢ Replace each pixel value in an image with the mean value of its
neighbors, including itself.

ā€¢ Gaussian noise .
ā€¢ Advantage:
ļƒ¼ Easy to implement
ļƒ¼ Used to remove the impulse noise.

ā€¢

Disadvantage:
ļƒ¼ It does not preserve details of image. Some details are removes of image
with using the mean filter.
Mean Filtering Example
Average filtering example using a 3 x 3 sampling window:
Keeping border values unchanged
Mean Filtering - Boundaries
ā€¢ Average filtering example using a 3 x 3 sampling
window:
Extending border values outside with values at boundary
Mean Filter Example
ā€¢ (a) Original Image

ā€¢ (b) Image corrupted by %12
Gaussian noise .
ā€¢ (c)De ā€“noising by mean filter
Gaussian filter
Gaussian noise
ā€¢ Gaussian is smoothing filter in the 2D convolution
operation that is used to remove noise and blur from
image.
ā€¢ Probably the most useful filter (although not the
fastest).
ā€¢ Gaussian filtering is done by convolution each point
in the input array with a Gaussian kernel and then
summing them all to produce the output array.
Gaussian filter Example

(a) Original

(b)Noisy

(c) Gaussian filter

Image corrupted by %60 salt & Pepper Noise
Performance Parameters
ā€¢ For comparing original image and filtered image, we calculate
following parameters:
1) Mean Square Error (MSE): The MSE is the cumulative square error
between the encoded and the original image defined by:

Where, f is the original image and g is the filtered image. The dimension of
the images is m x n. Thus MSE should be as low as possible for effective
filtering .
Performance Parameters
2) Signal to Noise Ratio is defined by the power ratio between a signal
and the background noise.

Where P is average power. Both noise and power must be measured at
the same points in a system, and within system with same bandwidth.
Performance Parameters
3) Peak signal to Noise ratio (PSNR):
ā€“ It is defined by:
PSNR = 10 log (255^2/mse)
Implementation in Matlab
Conclusion
ā€¢ Enhancement of an noisy image is necessary task in
image processing.

ā€¢ Filters are used best for removing noise from the images.
ā€¢ The decision to apply a which particular filter is based on the
different noise level at the different test pixel location or
performance of the filter scheme on a filtering mask.
QUESTIONS ?
Be nice ...
Noise Removal and Filtering Techniques

More Related Content

What's hot

4.intensity transformations
4.intensity transformations4.intensity transformations
4.intensity transformationsYahya Alkhaldi
Ā 
Lecture 15 DCT, Walsh and Hadamard Transform
Lecture 15 DCT, Walsh and Hadamard TransformLecture 15 DCT, Walsh and Hadamard Transform
Lecture 15 DCT, Walsh and Hadamard TransformVARUN KUMAR
Ā 
Histogram Equalization
Histogram EqualizationHistogram Equalization
Histogram EqualizationKalyan Acharjya
Ā 
Smoothing in Digital Image Processing
Smoothing in Digital Image ProcessingSmoothing in Digital Image Processing
Smoothing in Digital Image ProcessingPallavi Agarwal
Ā 
Image enhancement
Image enhancementImage enhancement
Image enhancementAyaelshiwi
Ā 
Spatial Filters (Digital Image Processing)
Spatial Filters (Digital Image Processing)Spatial Filters (Digital Image Processing)
Spatial Filters (Digital Image Processing)Kalyan Acharjya
Ā 
Noise Models
Noise ModelsNoise Models
Noise ModelsSardar Alam
Ā 
Data Redundacy
Data RedundacyData Redundacy
Data RedundacyPoonam Seth
Ā 
Arithmetic coding
Arithmetic codingArithmetic coding
Arithmetic codingVikas Goyal
Ā 
SPATIAL FILTERING IN IMAGE PROCESSING
SPATIAL FILTERING IN IMAGE PROCESSINGSPATIAL FILTERING IN IMAGE PROCESSING
SPATIAL FILTERING IN IMAGE PROCESSINGmuthu181188
Ā 
Unit3 dip
Unit3 dipUnit3 dip
Unit3 dipImran Khan
Ā 
Image Smoothing using Frequency Domain Filters
Image Smoothing using Frequency Domain FiltersImage Smoothing using Frequency Domain Filters
Image Smoothing using Frequency Domain FiltersSuhaila Afzana
Ā 
Color fundamentals and color models - Digital Image Processing
Color fundamentals and color models - Digital Image ProcessingColor fundamentals and color models - Digital Image Processing
Color fundamentals and color models - Digital Image ProcessingAmna
Ā 
Image Enhancement in Spatial Domain
Image Enhancement in Spatial DomainImage Enhancement in Spatial Domain
Image Enhancement in Spatial DomainDEEPASHRI HK
Ā 
Sharpening using frequency Domain Filter
Sharpening using frequency Domain FilterSharpening using frequency Domain Filter
Sharpening using frequency Domain Filterarulraj121
Ā 
Histogram Processing
Histogram ProcessingHistogram Processing
Histogram ProcessingAmnaakhaan
Ā 
Convolution&Correlation
Convolution&CorrelationConvolution&Correlation
Convolution&CorrelationVenkateshPrasadV1
Ā 

What's hot (20)

4.intensity transformations
4.intensity transformations4.intensity transformations
4.intensity transformations
Ā 
Lecture 15 DCT, Walsh and Hadamard Transform
Lecture 15 DCT, Walsh and Hadamard TransformLecture 15 DCT, Walsh and Hadamard Transform
Lecture 15 DCT, Walsh and Hadamard Transform
Ā 
Histogram Equalization
Histogram EqualizationHistogram Equalization
Histogram Equalization
Ā 
Smoothing in Digital Image Processing
Smoothing in Digital Image ProcessingSmoothing in Digital Image Processing
Smoothing in Digital Image Processing
Ā 
Image enhancement
Image enhancementImage enhancement
Image enhancement
Ā 
Spatial Filters (Digital Image Processing)
Spatial Filters (Digital Image Processing)Spatial Filters (Digital Image Processing)
Spatial Filters (Digital Image Processing)
Ā 
Noise
NoiseNoise
Noise
Ā 
Noise Models
Noise ModelsNoise Models
Noise Models
Ā 
Data Redundacy
Data RedundacyData Redundacy
Data Redundacy
Ā 
Arithmetic coding
Arithmetic codingArithmetic coding
Arithmetic coding
Ā 
SPATIAL FILTERING IN IMAGE PROCESSING
SPATIAL FILTERING IN IMAGE PROCESSINGSPATIAL FILTERING IN IMAGE PROCESSING
SPATIAL FILTERING IN IMAGE PROCESSING
Ā 
Unit3 dip
Unit3 dipUnit3 dip
Unit3 dip
Ā 
Image segmentation
Image segmentation Image segmentation
Image segmentation
Ā 
Image Smoothing using Frequency Domain Filters
Image Smoothing using Frequency Domain FiltersImage Smoothing using Frequency Domain Filters
Image Smoothing using Frequency Domain Filters
Ā 
Color fundamentals and color models - Digital Image Processing
Color fundamentals and color models - Digital Image ProcessingColor fundamentals and color models - Digital Image Processing
Color fundamentals and color models - Digital Image Processing
Ā 
Image Enhancement in Spatial Domain
Image Enhancement in Spatial DomainImage Enhancement in Spatial Domain
Image Enhancement in Spatial Domain
Ā 
Sharpening using frequency Domain Filter
Sharpening using frequency Domain FilterSharpening using frequency Domain Filter
Sharpening using frequency Domain Filter
Ā 
Digital Image Processing
Digital Image ProcessingDigital Image Processing
Digital Image Processing
Ā 
Histogram Processing
Histogram ProcessingHistogram Processing
Histogram Processing
Ā 
Convolution&Correlation
Convolution&CorrelationConvolution&Correlation
Convolution&Correlation
Ā 

Similar to Noise Removal and Filtering Techniques

Image processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filtersImage processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filtersKuppusamy P
Ā 
Image Restoration and Reconstruction in Digital Image Processing
Image Restoration and Reconstruction in Digital Image ProcessingImage Restoration and Reconstruction in Digital Image Processing
Image Restoration and Reconstruction in Digital Image ProcessingSadia Zafar
Ā 
Image noise reduction
Image noise reductionImage noise reduction
Image noise reductionJksuryawanshi
Ā 
NOISE FILTERS IN IMAGE PROCESSING
NOISE FILTERS IN IMAGE PROCESSINGNOISE FILTERS IN IMAGE PROCESSING
NOISE FILTERS IN IMAGE PROCESSINGAnimesh Singh Sengar
Ā 
Module 31
Module 31Module 31
Module 31UllasSS1
Ā 
Noise Estimation & Filtering_.pptx
Noise Estimation  & Filtering_.pptxNoise Estimation  & Filtering_.pptx
Noise Estimation & Filtering_.pptxSudipKG
Ā 
noiseestimationfiltering-221217050348-c5d1a246.pdf
noiseestimationfiltering-221217050348-c5d1a246.pdfnoiseestimationfiltering-221217050348-c5d1a246.pdf
noiseestimationfiltering-221217050348-c5d1a246.pdfAmrilMukmin2
Ā 
Removal of Salt and Pepper Noise in images
Removal of Salt and Pepper Noise in imagesRemoval of Salt and Pepper Noise in images
Removal of Salt and Pepper Noise in imagesMurali Siva
Ā 
Iaetsd literature review on efficient detection and filtering of high
Iaetsd literature review on efficient detection and filtering of highIaetsd literature review on efficient detection and filtering of high
Iaetsd literature review on efficient detection and filtering of highIaetsd Iaetsd
Ā 
Image denoising
Image denoisingImage denoising
Image denoisingHaitham Ahmed
Ā 
IMAGE DENOISING USING HYBRID FILTER
IMAGE DENOISING USING HYBRID FILTERIMAGE DENOISING USING HYBRID FILTER
IMAGE DENOISING USING HYBRID FILTERPushparaj Pal
Ā 
ModuleII091.pdf
ModuleII091.pdfModuleII091.pdf
ModuleII091.pdfSamrajECE
Ā 
Performance Comparison of Various Filters and Wavelet Transform for Image De-...
Performance Comparison of Various Filters and Wavelet Transform for Image De-...Performance Comparison of Various Filters and Wavelet Transform for Image De-...
Performance Comparison of Various Filters and Wavelet Transform for Image De-...IOSR Journals
Ā 
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...CSCJournals
Ā 
reducing noises in images
reducing noises in imagesreducing noises in images
reducing noises in imagesaswathdas
Ā 
survey paper for image denoising
survey paper for image denoisingsurvey paper for image denoising
survey paper for image denoisingArti Singh
Ā 
Review Paper on Image Denoising Techniques
Review Paper  on Image Denoising TechniquesReview Paper  on Image Denoising Techniques
Review Paper on Image Denoising TechniquesIRJET Journal
Ā 

Similar to Noise Removal and Filtering Techniques (20)

Image processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filtersImage processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filters
Ā 
Image Restoration and Reconstruction in Digital Image Processing
Image Restoration and Reconstruction in Digital Image ProcessingImage Restoration and Reconstruction in Digital Image Processing
Image Restoration and Reconstruction in Digital Image Processing
Ā 
Image noise reduction
Image noise reductionImage noise reduction
Image noise reduction
Ā 
NOISE FILTERS IN IMAGE PROCESSING
NOISE FILTERS IN IMAGE PROCESSINGNOISE FILTERS IN IMAGE PROCESSING
NOISE FILTERS IN IMAGE PROCESSING
Ā 
Module 31
Module 31Module 31
Module 31
Ā 
Noise Estimation & Filtering_.pptx
Noise Estimation  & Filtering_.pptxNoise Estimation  & Filtering_.pptx
Noise Estimation & Filtering_.pptx
Ā 
noiseestimationfiltering-221217050348-c5d1a246.pdf
noiseestimationfiltering-221217050348-c5d1a246.pdfnoiseestimationfiltering-221217050348-c5d1a246.pdf
noiseestimationfiltering-221217050348-c5d1a246.pdf
Ā 
DIP -Unit 3 ppt.pptx
DIP -Unit 3 ppt.pptxDIP -Unit 3 ppt.pptx
DIP -Unit 3 ppt.pptx
Ā 
Removal of Salt and Pepper Noise in images
Removal of Salt and Pepper Noise in imagesRemoval of Salt and Pepper Noise in images
Removal of Salt and Pepper Noise in images
Ā 
Image Filtering
Image FilteringImage Filtering
Image Filtering
Ā 
Iaetsd literature review on efficient detection and filtering of high
Iaetsd literature review on efficient detection and filtering of highIaetsd literature review on efficient detection and filtering of high
Iaetsd literature review on efficient detection and filtering of high
Ā 
Image denoising
Image denoisingImage denoising
Image denoising
Ā 
IMAGE DENOISING USING HYBRID FILTER
IMAGE DENOISING USING HYBRID FILTERIMAGE DENOISING USING HYBRID FILTER
IMAGE DENOISING USING HYBRID FILTER
Ā 
ModuleII091.pdf
ModuleII091.pdfModuleII091.pdf
ModuleII091.pdf
Ā 
Performance Comparison of Various Filters and Wavelet Transform for Image De-...
Performance Comparison of Various Filters and Wavelet Transform for Image De-...Performance Comparison of Various Filters and Wavelet Transform for Image De-...
Performance Comparison of Various Filters and Wavelet Transform for Image De-...
Ā 
L011117884
L011117884L011117884
L011117884
Ā 
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...
Image Restoration Using Particle Filters By Improving The Scale Of Texture Wi...
Ā 
reducing noises in images
reducing noises in imagesreducing noises in images
reducing noises in images
Ā 
survey paper for image denoising
survey paper for image denoisingsurvey paper for image denoising
survey paper for image denoising
Ā 
Review Paper on Image Denoising Techniques
Review Paper  on Image Denoising TechniquesReview Paper  on Image Denoising Techniques
Review Paper on Image Denoising Techniques
Ā 

Recently uploaded

Kalyanpur ) Call Girls in Lucknow Finest Escorts Service šŸø 8923113531 šŸŽ° Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service šŸø 8923113531 šŸŽ° Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service šŸø 8923113531 šŸŽ° Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service šŸø 8923113531 šŸŽ° Avail...gurkirankumar98700
Ā 
šŸ¬ The future of MySQL is Postgres šŸ˜
šŸ¬  The future of MySQL is Postgres   šŸ˜šŸ¬  The future of MySQL is Postgres   šŸ˜
šŸ¬ The future of MySQL is Postgres šŸ˜RTylerCroy
Ā 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
Ā 
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
Ā 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
Ā 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
Ā 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
Ā 
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
Ā 
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
Ā 
[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
Ā 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
Ā 
WhatsApp 9892124323 āœ“Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 āœ“Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 āœ“Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 āœ“Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
Ā 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
Ā 
Scaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organizationScaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organizationRadu Cotescu
Ā 
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
Ā 
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 AraĆŗjo
Ā 
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
Ā 
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
Ā 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
Ā 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
Ā 

Recently uploaded (20)

Kalyanpur ) Call Girls in Lucknow Finest Escorts Service šŸø 8923113531 šŸŽ° Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service šŸø 8923113531 šŸŽ° Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service šŸø 8923113531 šŸŽ° Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service šŸø 8923113531 šŸŽ° Avail...
Ā 
šŸ¬ The future of MySQL is Postgres šŸ˜
šŸ¬  The future of MySQL is Postgres   šŸ˜šŸ¬  The future of MySQL is Postgres   šŸ˜
šŸ¬ The future of MySQL is Postgres šŸ˜
Ā 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
Ā 
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
Ā 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
Ā 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Ā 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
Ā 
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
Ā 
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
Ā 
[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
Ā 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
Ā 
WhatsApp 9892124323 āœ“Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 āœ“Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 āœ“Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 āœ“Call Girls In Kalyan ( Mumbai ) secure service
Ā 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
Ā 
Scaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organizationScaling API-first ā€“ The story of a global engineering organization
Scaling API-first ā€“ The story of a global engineering organization
Ā 
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
Ā 
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...
Ā 
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
Ā 
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
Ā 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
Ā 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
Ā 

Noise Removal and Filtering Techniques

  • 1. Noise Addition and Filtering ` Presented By : Sara El-Masri Alaa Sababbah Amna El-Sheikh Ali Supervised By : Dr. Samy Salamah
  • 3. 1. Introduction ā€¢ It is generally desirable for image brightness to be uniform except where it changes to form an image. ā€¢ There are factors, however, that tend to produce variation in the brightness of a displayed image even when no image detail is present. ā€¢ This variation is usually random and has no particular pattern.
  • 4. 1. Introduction (cont.) In many cases, it reduces image quality and is especially significant when the objects being imaged are small and have relatively low contrast. This random variation in image brightness is designated noise.
  • 5. 1. Introduction (cont.) Image on the right has more noise than the image on the left
  • 6. Images ā€¢ There are two types of images : ļƒ¼ Vector images ļƒ¼ Digital images
  • 7. Vector Images ā€¢ Vector images made up of vectors which lead through locations called control points. ā€¢ Each of these control points has define on the x and y axes of the work plain .
  • 8. Digital Images ā€¢ A digital image is 2-dim array of real numbers ā€¢ 2-D image is divided into N rows and M columns ā€¢ the intersection of these rows and columns is known as pixels
  • 9. Types of Digital Images ā€¢ Binary images (black and white images) ā€¢ Gray scale images ā€¢ Color images
  • 10. Binary Images ā€¢ Each pixel is just black or white ā€¢ There is only two possible values for each pixel i.e. 0 or 1
  • 11. Gray Scale Images ā€¢ Each pixel value of gray scale images normally from 0 (black) to 255 (white)
  • 12. Color images ā€¢ In color images each pixel has a particular color ; that color being described by the amount of red , blue and green in it . ā€¢ Each of these components has a rang 0-255
  • 13. 2. Image noise Noise in image , is any degradation in an image signal , caused by external disturbance while an image is being sent from one place to another place via satellite , wireless and network cable . We can model a noisy image as follows:
  • 14. Source of Image Noise ā€¢ Error occurs in image signal while an image is being sent electronically from one place to another . ā€¢ Sensor heat while clicking an image ā€¢ ISO factor ISO number indicates how quickly a cameraā€™s sensor absorbs , light , higher ISO used mare chance of noticeable noise ā€¢ By memory cell failure.
  • 15. Types of Image Noise 1) Salt and pepper noise 2) Gaussian noise 3) Speckle noise 4) Uniform noise
  • 16. Salt and pepper noise ā€¢ It known as shot noise, impulse noise or Spike noise . ā€¢ Its appearance is randomly scattered white or black or both pixel over the image . ā€¢ there are only two possible values exists that is a and b and the probability of each is less than 0.2 .
  • 17. Salt and pepper noise (cont.) Reasons for Salt and Pepper Noise: 1) 2) 3) By memory cell failure. By malfunctioning of cameraā€™s sensor cells. By synchronization errors in image digitizing or transmission. Where: pa, pb are the Probabilities Density Function (PDF), p(z) is distribution salt and pepper noise in image and A, B are the arrays size image.
  • 18. Salt and pepper noise (cont.)
  • 19. Image with Salt and Pepper Original Image
  • 20. Salt and pepper noise (cont.) ā€¢ filtering techniques : ļƒ¼ mean filtering . ļƒ¼ Median filtering ļƒ¼ Gaussian filtering
  • 21. Gaussian Noise Gaussian noise is caused by random fluctuations in the signal , its modeled by random values add to an image This noise has a probability density function [pdf] of the normal distribution. It is also known as Gaussian distribution.
  • 22.
  • 23. Gaussian Noise (cont.) Without Noise With Gaussian Noise
  • 25. Sources of Gaussian Noise ā€¢ In digital images arise during acquisition . e.g. Sensor noise caused by poor illumination and/or high temperature ā€¢ Transmission e.g. Electronic circuit noise .
  • 26. Gaussian Noise (cont.) ā€¢ filtering techniques : ļƒ¼mean (convolution) filtering ļƒ¼Median filtering ļƒ¼Gaussian filtering
  • 27. Speckle Noise ā€¢ Speckle noise can be modeled by random values multiplied by pixel values of an image ā€¢ results from random fluctuations in the return signal from an object that is no bigger than a single image-processing element. It increases the mean grey level of a local area.
  • 28. Speckle Noise The distribution noise can be expressed by: Where g(n,m), is the observed image , u(n,m) is the multiplicative component . and &(n,m) is the additive component of the speckle noise.
  • 30. Speckle Noise (cont.) ā€¢ filtering techniques : ļƒ¼mean (convolution) filtering ļƒ¼Median filtering
  • 31. Uniform Noise ā€¢ The uniform noise cause by quantizing the pixels of image to a number of distinct levels is known as quantization noise. ā€¢ Uniform noise can be analytically described by : ā€¢ The gray level values of the noise are evenly distributed across a specific range
  • 32. Uniform Noise (cont.) ā€¢ Quantization noise has an approximately uniform distribution
  • 34. 3. Filtering ā€¢ Filtering image data is a standard process used in almost all image processing systems. ā€¢ Filters are used to remove noise from digital image while keeping the details of image preserved. ā€¢ The choice of filter is determined by ļƒ¼ the nature of the task performed by filter . ļƒ¼ Filter behavior . ļƒ¼ type of the data .
  • 36. Linear Filter ā€¢ Linear filters are used to remove certain type of noise. ā€¢ The linear filters work best with salt and pepper noise, and Gaussian noise. ā€¢ Gaussian and mean filters. ā€¢ Simple to design . ā€¢ These filters also ļƒ¼ tend to blur the sharp edges . ļƒ¼ destroy the lines and other fine details of image .
  • 37. Linear Filters ā€“ Example Filtered Gaussian noise.
  • 38. Non-Linear Filters ā€¢ Can preserve edges . ā€¢ Very effective at removing impulsive noise . ā€¢ They are more powerful than linear filters because they are able to reduce noise levels without blurring edges. ā€¢ Can be difficult to design. ā€¢ Median Filter.
  • 39. Non-linear Filter vs. linear Filter
  • 40. Filters Types 1) Median filter . 2) Wiener Filter . 3) Mean filter . 4) Gaussian filter
  • 41. Median Filter ā€¢ Median Filter is a simple and powerful non-linear filter . ā€¢ It is used for reducing the amount of intensity variation between one pixel and the other pixel. ā€¢ In this filter, we replaces pixel value with the median value . ā€¢ The median is calculated by first sorting all the pixel values into ascending order and then replace the pixel being calculated with the middle pixel value ā€¢ Salt and pepper noise.
  • 42. Median Filter ā€¢ Advantage: ļƒ¼ It is easy to implement. ļƒ¼ Used for de-noising different types of noises. ā€¢ Disadvantage: ļƒ¼ Median Filter tends to remove image details when the impulse noise percentage is more than 0.4 %.
  • 43. Example : 3x3 Median
  • 44. Original Salt & pepper %20 De-noising by Median filter Original Salt & pepper %60 De-noising by Median filter
  • 45. Wiener Filter ā€¢ The purpose of the Wiener filter is to filter out the noise that has corrupted a signal. ā€¢ This filter is based on a statistical approach. ā€¢ The goal of wiener filter is reduced the mean square error (MSE) as much as possible. ā€¢ Poisson noise , speckle noise .
  • 46. Wiener Filter ā€¢ One method that we assume we have knowledge of the spectral property of the noise and original signal. ā€¢ ā€¢ ā€¢ ā€¢ ā€¢ The Fourier domain of the Wiener filter is Where : H*(u, v) = Complex conjugate of degradation function Pn (u, v) = Power Spectral Density of Noise Ps (u, v) = Power Spectral Density of non-degraded image H (u, v) = Degradation function
  • 48. Mean Filter ā€¢ Mean Filter (average filter) is a simple linear filter . ā€¢ Replace each pixel value in an image with the mean value of its neighbors, including itself. ā€¢ Gaussian noise . ā€¢ Advantage: ļƒ¼ Easy to implement ļƒ¼ Used to remove the impulse noise. ā€¢ Disadvantage: ļƒ¼ It does not preserve details of image. Some details are removes of image with using the mean filter.
  • 49. Mean Filtering Example Average filtering example using a 3 x 3 sampling window: Keeping border values unchanged
  • 50. Mean Filtering - Boundaries ā€¢ Average filtering example using a 3 x 3 sampling window: Extending border values outside with values at boundary
  • 51. Mean Filter Example ā€¢ (a) Original Image ā€¢ (b) Image corrupted by %12 Gaussian noise . ā€¢ (c)De ā€“noising by mean filter
  • 52. Gaussian filter Gaussian noise ā€¢ Gaussian is smoothing filter in the 2D convolution operation that is used to remove noise and blur from image. ā€¢ Probably the most useful filter (although not the fastest). ā€¢ Gaussian filtering is done by convolution each point in the input array with a Gaussian kernel and then summing them all to produce the output array.
  • 53. Gaussian filter Example (a) Original (b)Noisy (c) Gaussian filter Image corrupted by %60 salt & Pepper Noise
  • 54. Performance Parameters ā€¢ For comparing original image and filtered image, we calculate following parameters: 1) Mean Square Error (MSE): The MSE is the cumulative square error between the encoded and the original image defined by: Where, f is the original image and g is the filtered image. The dimension of the images is m x n. Thus MSE should be as low as possible for effective filtering .
  • 55. Performance Parameters 2) Signal to Noise Ratio is defined by the power ratio between a signal and the background noise. Where P is average power. Both noise and power must be measured at the same points in a system, and within system with same bandwidth.
  • 56. Performance Parameters 3) Peak signal to Noise ratio (PSNR): ā€“ It is defined by: PSNR = 10 log (255^2/mse)
  • 58. Conclusion ā€¢ Enhancement of an noisy image is necessary task in image processing. ā€¢ Filters are used best for removing noise from the images. ā€¢ The decision to apply a which particular filter is based on the different noise level at the different test pixel location or performance of the filter scheme on a filtering mask.