SlideShare a Scribd company logo
Numerical method of image registration using
nonlinear geometric transform
Michael Rára
Faculty of Mechanical Engineering, Brno University of Technology
2.11.2018
Michael Rára
Numerical method of image registration using nonlinear geometric
Goals
1 Describe numerical methods for image analysis with
special aim to nonlinear geometric transform.
2 Create software to decrease geometric deformation in set
of images.
3 Find the best estimate of mean value from a set of images
defected by geometric deformation.
Michael Rára
Numerical method of image registration using nonlinear geometric
Entry data set
Michael Rára
Numerical method of image registration using nonlinear geometric
Light refraction
This phenomenon is typical on border of two different
environments (typical example is border between water and
air).
Michael Rára
Numerical method of image registration using nonlinear geometric
Astronomical seeing
Refraction index is influenced by atmospheric pressure,
which is different in every moment. Lets consider bigger
half-circle is border of atmosphere and the second is
surface of Earth.
Thanks to refraction index observer (point P) see source of
light (point Q) in different position (point R) than it really is.
Thanks to time variability of refraction index we have to
deal with problem known as astronomical seeing.
Astronomical seeing causes geometric deformations in
images, that is because refraction index is different in
every moment and that means we see point Q in different
position in every moment.
Michael Rára
Numerical method of image registration using nonlinear geometric
Arithmetic mean of entry data set
We simply calculate arithmetic value of brightness of pixel
at coordinates i,j. Index k means k-th image.
Thanks to arithmetic mean we have good estimate of
mean value of the data set. Unfortunately gain image is
blurred, see next slide.
¯ai,j =
1
n
n
k=1
ai,j;k
Michael Rára
Numerical method of image registration using nonlinear geometric
Michael Rára
Numerical method of image registration using nonlinear geometric
Edge detection in image
Gradient method is used to detect edges in image. f(i, j) is
value of brightness of pixel at coordinates i,j.
| f(i, j)| =
∂f(i, j)
∂i
2
+
∂f(i, j)
∂j
2
Approximation of equations
above for pixels which lie on the
borders of image.
∂f(i, j)
∂i
≈ f(i, j) − f(i − 1, j)
∂f(i, j)
∂i
≈ f(i + 1, j) − f(i, j)
Approximation of equations
above for pixels which do not lie
on the borders of image.
∂f(i, j)
∂i
≈ f(i + 1, j) − f(i − 1, j)
Analogously for ∂f(i,j)
∂j
Michael Rára
Numerical method of image registration using nonlinear geometric
Edges in image gain by arithmetic mean
Michael Rára
Numerical method of image registration using nonlinear geometric
Net of pixels from image on previous slide
Michael Rára
Numerical method of image registration using nonlinear geometric
Phase correlation
Now we investigate movement of every pixel of every image
due to image gain by arithmetic mean of entry data set.
r =
1
n
n
i=1(xi − ¯x)(yi − ¯y)
σ(x)σ(y)
r =
1
n
n
i=1(xi − ¯x)(yi − ¯y)
σ(x)σ(y)
Michael Rára
Numerical method of image registration using nonlinear geometric
Interpolation map
Thanks to phase correlation we know move vectors of all white
pixels. Move vector of green pixels is zero, see the next slide.
Michael Rára
Numerical method of image registration using nonlinear geometric
Michael Rára
Numerical method of image registration using nonlinear geometric
Linear interpolation of function f(x, y)
Function values at points
A, B, C, D are move vectors at
these points. We want to get
move vector at point D with use
of interpolation plane.
Equation of interpolation plane
can be written as determinant of
this matrix:
xD − xA yD − yA f(D)-f(A)
xB − xA yD − yA f(B)-f(A)
xC − xA yD − yA f(C)-f(A)
= 0
Michael Rára
Numerical method of image registration using nonlinear geometric
These images show idea of looking suitable group of pixels to
create matrix from previous slide. We want to interpolate
function value in orange pixel..
In this case we do not
need third pixel. We will
use linear interpolation
over line.
It is obvious we want to
find the nearest pixels to
the orange one, but the
red one can not be used.
In this situation we have
to find first, third and
fourth nearest pixel to the
orange one.
Michael Rára
Numerical method of image registration using nonlinear geometric
Bilinear interpolation of values of brightness.
f(P) = f(Q1,1)
(x2 − x)(y2 − y)
(x2 − x1)(y2 − y1)
+ f(Q2,1)
(x − x1)(y2 − y)
(x2 − x1)(y2 − y1)
+
f(Q1,2)
(x2 − x)(y − y1)
(x2 − x1)(y2 − y1)
+ f(Q2,2)
(x − x1)(y − y1)
(x2 − x1)(y2 − y1)
.
Thanks to phase correlation we know vector
of move of every pixel between original
image and image gain by arithmetic mean
(call it A). This vector can be for example
(0, 01; 1, 4). It means that pixel in image A
with coordinates i, j, can be found in original
image at coordinates i + 0, 01; j + 1, 4 (point
P). To get value of brightness of this pixel
we use bilinear interpolation of surrounded
values (points Q).
Michael Rára
Numerical method of image registration using nonlinear geometric
Corrected set of entry data
Michael Rára
Numerical method of image registration using nonlinear geometric
Arithmetic mean of corrected images
Michael Rára
Numerical method of image registration using nonlinear geometric
Sharpen image
We use discrete 2D convolution.
¯f(i, j) =
1
m=−1
1
n=−1
f(i − m, j − n)h(m, n)
Convolution matrix
h =


−1 −1 −1
−1 9 −1
−1 −1 −1


f(i, j) is value of brightness of pixel with coordination (i, j) from
image in previous slide. Result is sharpened image.
The sharpened image ¯f(i, j) is main output of the software. This
image is the best estimate of the mean value of the entry set,
see next slide.
Michael Rára
Numerical method of image registration using nonlinear geometric
Michael Rára
Numerical method of image registration using nonlinear geometric
Map of movements of pixels
−−−−−−−−→
MoveVector := (Px, Py)
Brightness := ||
−−−−−−−−→
MoveVector||
255:=max{Brightness}
Michael Rára
Numerical method of image registration using nonlinear geometric
Maps of movements of pixels between images from
original set and image gain by arithmetic mean of
them.
Please, see the next slide.
Michael Rára
Numerical method of image registration using nonlinear geometric
Michael Rára
Numerical method of image registration using nonlinear geometric
Thank you for attention.
Michael Rára
Numerical method of image registration using nonlinear geometric

More Related Content

What's hot

B. SC CSIT Computer Graphics Unit 4 By Tekendra Nath Yogi
B. SC CSIT Computer Graphics Unit 4 By Tekendra Nath YogiB. SC CSIT Computer Graphics Unit 4 By Tekendra Nath Yogi
B. SC CSIT Computer Graphics Unit 4 By Tekendra Nath Yogi
Tekendra Nath Yogi
 
Fixed point scaling
Fixed point scalingFixed point scaling
Fixed point scaling
rishi ram khanal
 
1422798749.2779lecture 5
1422798749.2779lecture 51422798749.2779lecture 5
1422798749.2779lecture 5
SRM UNIVERSITY, RAMAPURAM
 
Image segmentation 3 morphology
Image segmentation 3 morphologyImage segmentation 3 morphology
Image segmentation 3 morphologyRumah Belajar
 
COM2304: Morphological Image Processing
COM2304: Morphological Image ProcessingCOM2304: Morphological Image Processing
COM2304: Morphological Image Processing
Hemantha Kulathilake
 
FACE RECOGNITION ALGORITHM BASED ON ORIENTATION HISTOGRAM OF HOUGH PEAKS
FACE RECOGNITION ALGORITHM BASED ON ORIENTATION HISTOGRAM OF HOUGH PEAKSFACE RECOGNITION ALGORITHM BASED ON ORIENTATION HISTOGRAM OF HOUGH PEAKS
FACE RECOGNITION ALGORITHM BASED ON ORIENTATION HISTOGRAM OF HOUGH PEAKS
ijaia
 
Digital signal and image processing FAQ
Digital signal and image processing FAQDigital signal and image processing FAQ
Digital signal and image processing FAQ
Mukesh Tekwani
 
In792(2)
In792(2)In792(2)
Boundary Extraction
Boundary ExtractionBoundary Extraction
Boundary Extraction
Maria Akther
 
Point Cloud Processing: Estimating Normal Vectors and Curvature Indicators us...
Point Cloud Processing: Estimating Normal Vectors and Curvature Indicators us...Point Cloud Processing: Estimating Normal Vectors and Curvature Indicators us...
Point Cloud Processing: Estimating Normal Vectors and Curvature Indicators us...
Pirouz Nourian
 
Ijcatr03051008Implementation of Matrix based Mapping Method Using Elliptic Cu...
Ijcatr03051008Implementation of Matrix based Mapping Method Using Elliptic Cu...Ijcatr03051008Implementation of Matrix based Mapping Method Using Elliptic Cu...
Ijcatr03051008Implementation of Matrix based Mapping Method Using Elliptic Cu...
Editor IJCATR
 
QMC: Undergraduate Workshop, Introduction to Monte Carlo Methods with 'R' Sof...
QMC: Undergraduate Workshop, Introduction to Monte Carlo Methods with 'R' Sof...QMC: Undergraduate Workshop, Introduction to Monte Carlo Methods with 'R' Sof...
QMC: Undergraduate Workshop, Introduction to Monte Carlo Methods with 'R' Sof...
The Statistical and Applied Mathematical Sciences Institute
 
B. SC CSIT Computer Graphics Unit 3 By Tekendra Nath Yogi
B. SC CSIT Computer Graphics Unit 3 By Tekendra Nath YogiB. SC CSIT Computer Graphics Unit 3 By Tekendra Nath Yogi
B. SC CSIT Computer Graphics Unit 3 By Tekendra Nath Yogi
Tekendra Nath Yogi
 
Non Deterministic and Deterministic Problems
Non Deterministic and Deterministic Problems Non Deterministic and Deterministic Problems
Non Deterministic and Deterministic Problems
Scandala Tamang
 
AP Calculus Jauary 13, 2009
AP Calculus Jauary 13, 2009AP Calculus Jauary 13, 2009
AP Calculus Jauary 13, 2009
Darren Kuropatwa
 
Computer Graphics
Computer GraphicsComputer Graphics
Computer Graphics
Dhiraj Bhaskar
 
COMPUTER GRAPHICS
COMPUTER GRAPHICSCOMPUTER GRAPHICS
COMPUTER GRAPHICS
Jagan Raja
 
Minimal Introduction to C++ - Part I
Minimal Introduction to C++ - Part IMinimal Introduction to C++ - Part I
Minimal Introduction to C++ - Part I
Michel Alves
 

What's hot (20)

B. SC CSIT Computer Graphics Unit 4 By Tekendra Nath Yogi
B. SC CSIT Computer Graphics Unit 4 By Tekendra Nath YogiB. SC CSIT Computer Graphics Unit 4 By Tekendra Nath Yogi
B. SC CSIT Computer Graphics Unit 4 By Tekendra Nath Yogi
 
Fixed point scaling
Fixed point scalingFixed point scaling
Fixed point scaling
 
1422798749.2779lecture 5
1422798749.2779lecture 51422798749.2779lecture 5
1422798749.2779lecture 5
 
cvpr_15_poster_1200dpi
cvpr_15_poster_1200dpicvpr_15_poster_1200dpi
cvpr_15_poster_1200dpi
 
Image segmentation 3 morphology
Image segmentation 3 morphologyImage segmentation 3 morphology
Image segmentation 3 morphology
 
COM2304: Morphological Image Processing
COM2304: Morphological Image ProcessingCOM2304: Morphological Image Processing
COM2304: Morphological Image Processing
 
FACE RECOGNITION ALGORITHM BASED ON ORIENTATION HISTOGRAM OF HOUGH PEAKS
FACE RECOGNITION ALGORITHM BASED ON ORIENTATION HISTOGRAM OF HOUGH PEAKSFACE RECOGNITION ALGORITHM BASED ON ORIENTATION HISTOGRAM OF HOUGH PEAKS
FACE RECOGNITION ALGORITHM BASED ON ORIENTATION HISTOGRAM OF HOUGH PEAKS
 
Digital signal and image processing FAQ
Digital signal and image processing FAQDigital signal and image processing FAQ
Digital signal and image processing FAQ
 
In792(2)
In792(2)In792(2)
In792(2)
 
Boundary Extraction
Boundary ExtractionBoundary Extraction
Boundary Extraction
 
Point Cloud Processing: Estimating Normal Vectors and Curvature Indicators us...
Point Cloud Processing: Estimating Normal Vectors and Curvature Indicators us...Point Cloud Processing: Estimating Normal Vectors and Curvature Indicators us...
Point Cloud Processing: Estimating Normal Vectors and Curvature Indicators us...
 
Ijcatr03051008Implementation of Matrix based Mapping Method Using Elliptic Cu...
Ijcatr03051008Implementation of Matrix based Mapping Method Using Elliptic Cu...Ijcatr03051008Implementation of Matrix based Mapping Method Using Elliptic Cu...
Ijcatr03051008Implementation of Matrix based Mapping Method Using Elliptic Cu...
 
final_presentation
final_presentationfinal_presentation
final_presentation
 
QMC: Undergraduate Workshop, Introduction to Monte Carlo Methods with 'R' Sof...
QMC: Undergraduate Workshop, Introduction to Monte Carlo Methods with 'R' Sof...QMC: Undergraduate Workshop, Introduction to Monte Carlo Methods with 'R' Sof...
QMC: Undergraduate Workshop, Introduction to Monte Carlo Methods with 'R' Sof...
 
B. SC CSIT Computer Graphics Unit 3 By Tekendra Nath Yogi
B. SC CSIT Computer Graphics Unit 3 By Tekendra Nath YogiB. SC CSIT Computer Graphics Unit 3 By Tekendra Nath Yogi
B. SC CSIT Computer Graphics Unit 3 By Tekendra Nath Yogi
 
Non Deterministic and Deterministic Problems
Non Deterministic and Deterministic Problems Non Deterministic and Deterministic Problems
Non Deterministic and Deterministic Problems
 
AP Calculus Jauary 13, 2009
AP Calculus Jauary 13, 2009AP Calculus Jauary 13, 2009
AP Calculus Jauary 13, 2009
 
Computer Graphics
Computer GraphicsComputer Graphics
Computer Graphics
 
COMPUTER GRAPHICS
COMPUTER GRAPHICSCOMPUTER GRAPHICS
COMPUTER GRAPHICS
 
Minimal Introduction to C++ - Part I
Minimal Introduction to C++ - Part IMinimal Introduction to C++ - Part I
Minimal Introduction to C++ - Part I
 

Similar to Presentation of my master thesis - Image Processing

Presentation of my master thesis
Presentation of my master thesisPresentation of my master thesis
Presentation of my master thesis
MichaelRra
 
03 digital image fundamentals DIP
03 digital image fundamentals DIP03 digital image fundamentals DIP
03 digital image fundamentals DIP
babak danyal
 
Lec_2_Digital Image Fundamentals.pdf
Lec_2_Digital Image Fundamentals.pdfLec_2_Digital Image Fundamentals.pdf
Lec_2_Digital Image Fundamentals.pdf
nagwaAboElenein
 
On image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDAOn image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDA
Raghu Palakodety
 
3 intensity transformations and spatial filtering slides
3 intensity transformations and spatial filtering slides3 intensity transformations and spatial filtering slides
3 intensity transformations and spatial filtering slides
BHAGYAPRASADBUGGE
 
Presentation 1
Presentation 1Presentation 1
Presentation 1
BCET, Balasore
 
Image processing second unit Notes
Image processing second unit NotesImage processing second unit Notes
Image processing second unit Notes
AAKANKSHA JAIN
 
A decomposition framework for image denoising algorithms...
A decomposition framework for image denoising algorithms...A decomposition framework for image denoising algorithms...
A decomposition framework for image denoising algorithms...
Sujit73031
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
ijceronline
 
Image Enhancement - Point Processing
Image Enhancement - Point ProcessingImage Enhancement - Point Processing
Image Enhancement - Point Processing
Gayathri31093
 
Image Interpolation Techniques with Optical and Digital Zoom Concepts
Image Interpolation Techniques with Optical and Digital Zoom ConceptsImage Interpolation Techniques with Optical and Digital Zoom Concepts
Image Interpolation Techniques with Optical and Digital Zoom Concepts
mmjalbiaty
 
Lecture 5.pptx
Lecture 5.pptxLecture 5.pptx
Lecture 5.pptx
VladsGamerHut
 
chapter-2 SPACIAL DOMAIN.pptx
chapter-2 SPACIAL DOMAIN.pptxchapter-2 SPACIAL DOMAIN.pptx
chapter-2 SPACIAL DOMAIN.pptx
AyeleFeyissa1
 
chapter 4 computervision.pdf IT IS ABOUT COMUTER VISION
chapter 4 computervision.pdf IT IS ABOUT COMUTER VISIONchapter 4 computervision.pdf IT IS ABOUT COMUTER VISION
chapter 4 computervision.pdf IT IS ABOUT COMUTER VISION
shesnasuneer
 
Lec_3_Image Enhancement_spatial Domain.pdf
Lec_3_Image Enhancement_spatial Domain.pdfLec_3_Image Enhancement_spatial Domain.pdf
Lec_3_Image Enhancement_spatial Domain.pdf
nagwaAboElenein
 
Dip mcq1
Dip mcq1Dip mcq1
Dip mcq1
Antony Vigil
 
BASICS OF DIGITAL IMAGE PROCESSING,MARIA PETROU
BASICS OF DIGITAL IMAGE PROCESSING,MARIA PETROUBASICS OF DIGITAL IMAGE PROCESSING,MARIA PETROU
BASICS OF DIGITAL IMAGE PROCESSING,MARIA PETROU
anjunarayanan
 
Image Restitution Using Non-Locally Centralized Sparse Representation Model
Image Restitution Using Non-Locally Centralized Sparse Representation ModelImage Restitution Using Non-Locally Centralized Sparse Representation Model
Image Restitution Using Non-Locally Centralized Sparse Representation Model
IJERA Editor
 

Similar to Presentation of my master thesis - Image Processing (20)

Presentation of my master thesis
Presentation of my master thesisPresentation of my master thesis
Presentation of my master thesis
 
03 digital image fundamentals DIP
03 digital image fundamentals DIP03 digital image fundamentals DIP
03 digital image fundamentals DIP
 
Lec_2_Digital Image Fundamentals.pdf
Lec_2_Digital Image Fundamentals.pdfLec_2_Digital Image Fundamentals.pdf
Lec_2_Digital Image Fundamentals.pdf
 
Lec-3 DIP.pptx
Lec-3 DIP.pptxLec-3 DIP.pptx
Lec-3 DIP.pptx
 
On image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDAOn image intensities, eigenfaces and LDA
On image intensities, eigenfaces and LDA
 
3 intensity transformations and spatial filtering slides
3 intensity transformations and spatial filtering slides3 intensity transformations and spatial filtering slides
3 intensity transformations and spatial filtering slides
 
Presentation 1
Presentation 1Presentation 1
Presentation 1
 
mini prjt
mini prjtmini prjt
mini prjt
 
Image processing second unit Notes
Image processing second unit NotesImage processing second unit Notes
Image processing second unit Notes
 
A decomposition framework for image denoising algorithms...
A decomposition framework for image denoising algorithms...A decomposition framework for image denoising algorithms...
A decomposition framework for image denoising algorithms...
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
 
Image Enhancement - Point Processing
Image Enhancement - Point ProcessingImage Enhancement - Point Processing
Image Enhancement - Point Processing
 
Image Interpolation Techniques with Optical and Digital Zoom Concepts
Image Interpolation Techniques with Optical and Digital Zoom ConceptsImage Interpolation Techniques with Optical and Digital Zoom Concepts
Image Interpolation Techniques with Optical and Digital Zoom Concepts
 
Lecture 5.pptx
Lecture 5.pptxLecture 5.pptx
Lecture 5.pptx
 
chapter-2 SPACIAL DOMAIN.pptx
chapter-2 SPACIAL DOMAIN.pptxchapter-2 SPACIAL DOMAIN.pptx
chapter-2 SPACIAL DOMAIN.pptx
 
chapter 4 computervision.pdf IT IS ABOUT COMUTER VISION
chapter 4 computervision.pdf IT IS ABOUT COMUTER VISIONchapter 4 computervision.pdf IT IS ABOUT COMUTER VISION
chapter 4 computervision.pdf IT IS ABOUT COMUTER VISION
 
Lec_3_Image Enhancement_spatial Domain.pdf
Lec_3_Image Enhancement_spatial Domain.pdfLec_3_Image Enhancement_spatial Domain.pdf
Lec_3_Image Enhancement_spatial Domain.pdf
 
Dip mcq1
Dip mcq1Dip mcq1
Dip mcq1
 
BASICS OF DIGITAL IMAGE PROCESSING,MARIA PETROU
BASICS OF DIGITAL IMAGE PROCESSING,MARIA PETROUBASICS OF DIGITAL IMAGE PROCESSING,MARIA PETROU
BASICS OF DIGITAL IMAGE PROCESSING,MARIA PETROU
 
Image Restitution Using Non-Locally Centralized Sparse Representation Model
Image Restitution Using Non-Locally Centralized Sparse Representation ModelImage Restitution Using Non-Locally Centralized Sparse Representation Model
Image Restitution Using Non-Locally Centralized Sparse Representation Model
 

Recently uploaded

Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024
Paco van Beckhoven
 
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdf
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdfAutomated software refactoring with OpenRewrite and Generative AI.pptx.pdf
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdf
timtebeek1
 
GraphSummit Paris - The art of the possible with Graph Technology
GraphSummit Paris - The art of the possible with Graph TechnologyGraphSummit Paris - The art of the possible with Graph Technology
GraphSummit Paris - The art of the possible with Graph Technology
Neo4j
 
Introducing Crescat - Event Management Software for Venues, Festivals and Eve...
Introducing Crescat - Event Management Software for Venues, Festivals and Eve...Introducing Crescat - Event Management Software for Venues, Festivals and Eve...
Introducing Crescat - Event Management Software for Venues, Festivals and Eve...
Crescat
 
Navigating the Metaverse: A Journey into Virtual Evolution"
Navigating the Metaverse: A Journey into Virtual Evolution"Navigating the Metaverse: A Journey into Virtual Evolution"
Navigating the Metaverse: A Journey into Virtual Evolution"
Donna Lenk
 
Graspan: A Big Data System for Big Code Analysis
Graspan: A Big Data System for Big Code AnalysisGraspan: A Big Data System for Big Code Analysis
Graspan: A Big Data System for Big Code Analysis
Aftab Hussain
 
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing SuiteAI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
Google
 
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptxTop Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
rickgrimesss22
 
Quarkus Hidden and Forbidden Extensions
Quarkus Hidden and Forbidden ExtensionsQuarkus Hidden and Forbidden Extensions
Quarkus Hidden and Forbidden Extensions
Max Andersen
 
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
A Study of Variable-Role-based Feature Enrichment in Neural Models of CodeA Study of Variable-Role-based Feature Enrichment in Neural Models of Code
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
Aftab Hussain
 
Transform Your Communication with Cloud-Based IVR Solutions
Transform Your Communication with Cloud-Based IVR SolutionsTransform Your Communication with Cloud-Based IVR Solutions
Transform Your Communication with Cloud-Based IVR Solutions
TheSMSPoint
 
Enterprise Resource Planning System in Telangana
Enterprise Resource Planning System in TelanganaEnterprise Resource Planning System in Telangana
Enterprise Resource Planning System in Telangana
NYGGS Automation Suite
 
2024 eCommerceDays Toulouse - Sylius 2.0.pdf
2024 eCommerceDays Toulouse - Sylius 2.0.pdf2024 eCommerceDays Toulouse - Sylius 2.0.pdf
2024 eCommerceDays Toulouse - Sylius 2.0.pdf
Łukasz Chruściel
 
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Mind IT Systems
 
Artificia Intellicence and XPath Extension Functions
Artificia Intellicence and XPath Extension FunctionsArtificia Intellicence and XPath Extension Functions
Artificia Intellicence and XPath Extension Functions
Octavian Nadolu
 
E-commerce Application Development Company.pdf
E-commerce Application Development Company.pdfE-commerce Application Development Company.pdf
E-commerce Application Development Company.pdf
Hornet Dynamics
 
Using Xen Hypervisor for Functional Safety
Using Xen Hypervisor for Functional SafetyUsing Xen Hypervisor for Functional Safety
Using Xen Hypervisor for Functional Safety
Ayan Halder
 
Fundamentals of Programming and Language Processors
Fundamentals of Programming and Language ProcessorsFundamentals of Programming and Language Processors
Fundamentals of Programming and Language Processors
Rakesh Kumar R
 
Mobile App Development Company In Noida | Drona Infotech
Mobile App Development Company In Noida | Drona InfotechMobile App Development Company In Noida | Drona Infotech
Mobile App Development Company In Noida | Drona Infotech
Drona Infotech
 
A Sighting of filterA in Typelevel Rite of Passage
A Sighting of filterA in Typelevel Rite of PassageA Sighting of filterA in Typelevel Rite of Passage
A Sighting of filterA in Typelevel Rite of Passage
Philip Schwarz
 

Recently uploaded (20)

Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024Cracking the code review at SpringIO 2024
Cracking the code review at SpringIO 2024
 
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdf
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdfAutomated software refactoring with OpenRewrite and Generative AI.pptx.pdf
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdf
 
GraphSummit Paris - The art of the possible with Graph Technology
GraphSummit Paris - The art of the possible with Graph TechnologyGraphSummit Paris - The art of the possible with Graph Technology
GraphSummit Paris - The art of the possible with Graph Technology
 
Introducing Crescat - Event Management Software for Venues, Festivals and Eve...
Introducing Crescat - Event Management Software for Venues, Festivals and Eve...Introducing Crescat - Event Management Software for Venues, Festivals and Eve...
Introducing Crescat - Event Management Software for Venues, Festivals and Eve...
 
Navigating the Metaverse: A Journey into Virtual Evolution"
Navigating the Metaverse: A Journey into Virtual Evolution"Navigating the Metaverse: A Journey into Virtual Evolution"
Navigating the Metaverse: A Journey into Virtual Evolution"
 
Graspan: A Big Data System for Big Code Analysis
Graspan: A Big Data System for Big Code AnalysisGraspan: A Big Data System for Big Code Analysis
Graspan: A Big Data System for Big Code Analysis
 
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing SuiteAI Pilot Review: The World’s First Virtual Assistant Marketing Suite
AI Pilot Review: The World’s First Virtual Assistant Marketing Suite
 
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptxTop Features to Include in Your Winzo Clone App for Business Growth (4).pptx
Top Features to Include in Your Winzo Clone App for Business Growth (4).pptx
 
Quarkus Hidden and Forbidden Extensions
Quarkus Hidden and Forbidden ExtensionsQuarkus Hidden and Forbidden Extensions
Quarkus Hidden and Forbidden Extensions
 
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
A Study of Variable-Role-based Feature Enrichment in Neural Models of CodeA Study of Variable-Role-based Feature Enrichment in Neural Models of Code
A Study of Variable-Role-based Feature Enrichment in Neural Models of Code
 
Transform Your Communication with Cloud-Based IVR Solutions
Transform Your Communication with Cloud-Based IVR SolutionsTransform Your Communication with Cloud-Based IVR Solutions
Transform Your Communication with Cloud-Based IVR Solutions
 
Enterprise Resource Planning System in Telangana
Enterprise Resource Planning System in TelanganaEnterprise Resource Planning System in Telangana
Enterprise Resource Planning System in Telangana
 
2024 eCommerceDays Toulouse - Sylius 2.0.pdf
2024 eCommerceDays Toulouse - Sylius 2.0.pdf2024 eCommerceDays Toulouse - Sylius 2.0.pdf
2024 eCommerceDays Toulouse - Sylius 2.0.pdf
 
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
Custom Healthcare Software for Managing Chronic Conditions and Remote Patient...
 
Artificia Intellicence and XPath Extension Functions
Artificia Intellicence and XPath Extension FunctionsArtificia Intellicence and XPath Extension Functions
Artificia Intellicence and XPath Extension Functions
 
E-commerce Application Development Company.pdf
E-commerce Application Development Company.pdfE-commerce Application Development Company.pdf
E-commerce Application Development Company.pdf
 
Using Xen Hypervisor for Functional Safety
Using Xen Hypervisor for Functional SafetyUsing Xen Hypervisor for Functional Safety
Using Xen Hypervisor for Functional Safety
 
Fundamentals of Programming and Language Processors
Fundamentals of Programming and Language ProcessorsFundamentals of Programming and Language Processors
Fundamentals of Programming and Language Processors
 
Mobile App Development Company In Noida | Drona Infotech
Mobile App Development Company In Noida | Drona InfotechMobile App Development Company In Noida | Drona Infotech
Mobile App Development Company In Noida | Drona Infotech
 
A Sighting of filterA in Typelevel Rite of Passage
A Sighting of filterA in Typelevel Rite of PassageA Sighting of filterA in Typelevel Rite of Passage
A Sighting of filterA in Typelevel Rite of Passage
 

Presentation of my master thesis - Image Processing

  • 1. Numerical method of image registration using nonlinear geometric transform Michael Rára Faculty of Mechanical Engineering, Brno University of Technology 2.11.2018 Michael Rára Numerical method of image registration using nonlinear geometric
  • 2. Goals 1 Describe numerical methods for image analysis with special aim to nonlinear geometric transform. 2 Create software to decrease geometric deformation in set of images. 3 Find the best estimate of mean value from a set of images defected by geometric deformation. Michael Rára Numerical method of image registration using nonlinear geometric
  • 3. Entry data set Michael Rára Numerical method of image registration using nonlinear geometric
  • 4. Light refraction This phenomenon is typical on border of two different environments (typical example is border between water and air). Michael Rára Numerical method of image registration using nonlinear geometric
  • 5. Astronomical seeing Refraction index is influenced by atmospheric pressure, which is different in every moment. Lets consider bigger half-circle is border of atmosphere and the second is surface of Earth. Thanks to refraction index observer (point P) see source of light (point Q) in different position (point R) than it really is. Thanks to time variability of refraction index we have to deal with problem known as astronomical seeing. Astronomical seeing causes geometric deformations in images, that is because refraction index is different in every moment and that means we see point Q in different position in every moment. Michael Rára Numerical method of image registration using nonlinear geometric
  • 6. Arithmetic mean of entry data set We simply calculate arithmetic value of brightness of pixel at coordinates i,j. Index k means k-th image. Thanks to arithmetic mean we have good estimate of mean value of the data set. Unfortunately gain image is blurred, see next slide. ¯ai,j = 1 n n k=1 ai,j;k Michael Rára Numerical method of image registration using nonlinear geometric
  • 7. Michael Rára Numerical method of image registration using nonlinear geometric
  • 8. Edge detection in image Gradient method is used to detect edges in image. f(i, j) is value of brightness of pixel at coordinates i,j. | f(i, j)| = ∂f(i, j) ∂i 2 + ∂f(i, j) ∂j 2 Approximation of equations above for pixels which lie on the borders of image. ∂f(i, j) ∂i ≈ f(i, j) − f(i − 1, j) ∂f(i, j) ∂i ≈ f(i + 1, j) − f(i, j) Approximation of equations above for pixels which do not lie on the borders of image. ∂f(i, j) ∂i ≈ f(i + 1, j) − f(i − 1, j) Analogously for ∂f(i,j) ∂j Michael Rára Numerical method of image registration using nonlinear geometric
  • 9. Edges in image gain by arithmetic mean Michael Rára Numerical method of image registration using nonlinear geometric
  • 10. Net of pixels from image on previous slide Michael Rára Numerical method of image registration using nonlinear geometric
  • 11. Phase correlation Now we investigate movement of every pixel of every image due to image gain by arithmetic mean of entry data set. r = 1 n n i=1(xi − ¯x)(yi − ¯y) σ(x)σ(y) r = 1 n n i=1(xi − ¯x)(yi − ¯y) σ(x)σ(y) Michael Rára Numerical method of image registration using nonlinear geometric
  • 12. Interpolation map Thanks to phase correlation we know move vectors of all white pixels. Move vector of green pixels is zero, see the next slide. Michael Rára Numerical method of image registration using nonlinear geometric
  • 13. Michael Rára Numerical method of image registration using nonlinear geometric
  • 14. Linear interpolation of function f(x, y) Function values at points A, B, C, D are move vectors at these points. We want to get move vector at point D with use of interpolation plane. Equation of interpolation plane can be written as determinant of this matrix: xD − xA yD − yA f(D)-f(A) xB − xA yD − yA f(B)-f(A) xC − xA yD − yA f(C)-f(A) = 0 Michael Rára Numerical method of image registration using nonlinear geometric
  • 15. These images show idea of looking suitable group of pixels to create matrix from previous slide. We want to interpolate function value in orange pixel.. In this case we do not need third pixel. We will use linear interpolation over line. It is obvious we want to find the nearest pixels to the orange one, but the red one can not be used. In this situation we have to find first, third and fourth nearest pixel to the orange one. Michael Rára Numerical method of image registration using nonlinear geometric
  • 16. Bilinear interpolation of values of brightness. f(P) = f(Q1,1) (x2 − x)(y2 − y) (x2 − x1)(y2 − y1) + f(Q2,1) (x − x1)(y2 − y) (x2 − x1)(y2 − y1) + f(Q1,2) (x2 − x)(y − y1) (x2 − x1)(y2 − y1) + f(Q2,2) (x − x1)(y − y1) (x2 − x1)(y2 − y1) . Thanks to phase correlation we know vector of move of every pixel between original image and image gain by arithmetic mean (call it A). This vector can be for example (0, 01; 1, 4). It means that pixel in image A with coordinates i, j, can be found in original image at coordinates i + 0, 01; j + 1, 4 (point P). To get value of brightness of this pixel we use bilinear interpolation of surrounded values (points Q). Michael Rára Numerical method of image registration using nonlinear geometric
  • 17. Corrected set of entry data Michael Rára Numerical method of image registration using nonlinear geometric
  • 18. Arithmetic mean of corrected images Michael Rára Numerical method of image registration using nonlinear geometric
  • 19. Sharpen image We use discrete 2D convolution. ¯f(i, j) = 1 m=−1 1 n=−1 f(i − m, j − n)h(m, n) Convolution matrix h =   −1 −1 −1 −1 9 −1 −1 −1 −1   f(i, j) is value of brightness of pixel with coordination (i, j) from image in previous slide. Result is sharpened image. The sharpened image ¯f(i, j) is main output of the software. This image is the best estimate of the mean value of the entry set, see next slide. Michael Rára Numerical method of image registration using nonlinear geometric
  • 20. Michael Rára Numerical method of image registration using nonlinear geometric
  • 21. Map of movements of pixels −−−−−−−−→ MoveVector := (Px, Py) Brightness := || −−−−−−−−→ MoveVector|| 255:=max{Brightness} Michael Rára Numerical method of image registration using nonlinear geometric
  • 22. Maps of movements of pixels between images from original set and image gain by arithmetic mean of them. Please, see the next slide. Michael Rára Numerical method of image registration using nonlinear geometric
  • 23. Michael Rára Numerical method of image registration using nonlinear geometric
  • 24. Thank you for attention. Michael Rára Numerical method of image registration using nonlinear geometric