SlideShare une entreprise Scribd logo
1  sur  4
Intro: SIFT – (Scale invariant feature transform)
The SIFT algorithm takes an image and transforms it into a collection of local feature vectors.
Each of these feature vectors is supposed to be distinctive and invariant to any scaling, r otation or
translation of the image.
Algorithm:
1 Creating Scale-space and Difference of Gaussian pyramid
2 Extrema detection
3 Noise Elimination
4 Orientation assignment
5 Descriptor Computation
6 Keypoints matching
1. Creating Scale-space and Difference of Gaussian pyramid
The first stage is to construct a Gaussian "scale space" function from the input image . This is
formed by convolution (filtering) of the original image with Gaussian functions of varying widths.
The difference of Gaussian (DoG), D(x, y , σ), is calculated as the difference between two filtered
images, one with k multiplied by scale of the other .
D(x, y , σ) = L(x, y , kσ)-L(x, y , σ)
(1)
These images, L(x, y , σ), are produced from the convolution of Gaussian functions,
G(x, y , kσ), with an input image, I(x, y).
L(x, y , σ) = G(x, y , σ)*I(x, y)

(2)

First, the initial image, I, is convolved with a Gaussian function, G 0 , of width σ 0 . Then we use
this blured image, L0 , as the first image in the Gaussian pyramid and incrementally convolve it with
a Gaussian, Gi, of width σi to create the ith image in the image pyramid, which is equivalent to
the original image filtered with aGaussian, Gk, of width kσ0 .
2. Extrema detection
This stage is to find the extrema points in the DOG pyramid. T o detect the local
maxima and minima of D(x, y , σ), each point is compared with the pixels of all its 26
neighbours . If this value is the minimum or maximum this point is an extrema.

3. Noise Elimination
This stage attempts to eliminate some points from the candidate list of keypoints by
finding those that have low contrast or are poorly localised on an edge.[1]. The value of the
keypoint in the DoG pyramid at the extrema is given by:

If the function value at z is below a threshold value this point is excluded.
T o eliminate poorly localized extrema we use the fact that in these cases there is a
large principle curvature across the edge but a small curvature in the perpendicular
direction in the difference of Gaussian function. A 2x2 Hessian matrix, H, computed at the
location and scale of the keypoint is used to find the curvature. With these fomulas,
the ratio of principal curvature can be checked efficiently .
Tr (H) = Dxx + Dyy
Det(H) = DxxDyy - (Dxy )2
R=Tr(H)^2/Det(H)

Where r= ratio between small and large Eigen value.
So if inequality fails, the key point is removed from the candidate list.
4. Orientation assignment
This step aims to assign a consistent orientation to the keypoints based on local image
properties. An orientation histogram is formed from the gradient orientations of sample points within a
region around the keypoint . A 16x16 square is chosen in this implementation. The
orientation histogram has 36 bins covering the 360 degree range of orientations. The
gradient magnitude, m(x, y), and orientation, θ(x, y), is precomputed using pixel differences:

Each sample is weighted by its gradient magnitude and by a Gaussian-weighted circular window
with a σ that is 1.5 times that of the scale of the keypoint.

5. Descriptor Computation
In this stage, a descriptor is computed for the local image region that is as distinctive as possible at
each candidate keypoint. The image gradient magnitudes and orientations are sampled around the
keypoint location. These values are illustrated with small arrows at each sample location
on the first image of Figures. A Gaussian weighting function with σ related to the scale of the keypoint
is used to assign a weight to the magnitude.We use a σ equal to one half the width of the descriptor
window in this implementation. In order to achieve orientation invariance, the coordinates of
the descriptor and the gradient orientations are rotated relative to the keypoint orientation. This
process is indicated in Figure 5. In our implementation, a 16x16 sample array is computed and a
histogram with 8 bins is used. So a descriptor contains 16x16x8 elements in total. This vector is then
normalized to unit length in order to enhance invariance to affine changes in illumination.
6. Keypoints matching
Knowing the keypoints and descriptors using Euclidean distance ,each keypoint in the original
image (model image) is compared to every keypoints in the transformed image using the
descriptors computed in the previous stage.
The descriptors of the two respective, keypoints must be closest. Then match is found.

Contenu connexe

Tendances

Feature Matching using SIFT algorithm
Feature Matching using SIFT algorithmFeature Matching using SIFT algorithm
Feature Matching using SIFT algorithmSajid Pareeth
 
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image DescriptorsPCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image Descriptorswolf
 
Machine learning for high-speed corner detection
Machine learning for high-speed corner detectionMachine learning for high-speed corner detection
Machine learning for high-speed corner detectionbutest
 
Lec07 corner blob
Lec07 corner blobLec07 corner blob
Lec07 corner blobBaliThorat1
 
Literature Survey on Interest Points based Watermarking
Literature Survey on Interest Points based WatermarkingLiterature Survey on Interest Points based Watermarking
Literature Survey on Interest Points based WatermarkingPriyatham Bollimpalli
 
Lighting and shading
Lighting and shadingLighting and shading
Lighting and shadingeshveeen
 
Erosion and dilation
Erosion and dilationErosion and dilation
Erosion and dilationAkhil .B
 
04 image enhancement edge detection
04 image enhancement edge detection04 image enhancement edge detection
04 image enhancement edge detectionRumah Belajar
 
Image Texture Analysis
Image Texture AnalysisImage Texture Analysis
Image Texture Analysislalitxp
 
GRPHICS05 - Rendering (2)
GRPHICS05 - Rendering (2)GRPHICS05 - Rendering (2)
GRPHICS05 - Rendering (2)Michael Heron
 
Phong Shading over any Polygonal Surface
Phong Shading over any Polygonal Surface Phong Shading over any Polygonal Surface
Phong Shading over any Polygonal Surface Bhuvnesh Pratap
 

Tendances (20)

Feature Matching using SIFT algorithm
Feature Matching using SIFT algorithmFeature Matching using SIFT algorithm
Feature Matching using SIFT algorithm
 
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image DescriptorsPCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
 
Machine learning for high-speed corner detection
Machine learning for high-speed corner detectionMachine learning for high-speed corner detection
Machine learning for high-speed corner detection
 
Lec07 corner blob
Lec07 corner blobLec07 corner blob
Lec07 corner blob
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extraction
 
Literature Survey on Interest Points based Watermarking
Literature Survey on Interest Points based WatermarkingLiterature Survey on Interest Points based Watermarking
Literature Survey on Interest Points based Watermarking
 
Orb feature by nitin
Orb feature by nitinOrb feature by nitin
Orb feature by nitin
 
EDGE DETECTION
EDGE DETECTIONEDGE DETECTION
EDGE DETECTION
 
Lighting and shading
Lighting and shadingLighting and shading
Lighting and shading
 
Erosion and dilation
Erosion and dilationErosion and dilation
Erosion and dilation
 
Morphological image processing
Morphological image processingMorphological image processing
Morphological image processing
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 
04 image enhancement edge detection
04 image enhancement edge detection04 image enhancement edge detection
04 image enhancement edge detection
 
Lec06 edge
Lec06 edgeLec06 edge
Lec06 edge
 
Image Texture Analysis
Image Texture AnalysisImage Texture Analysis
Image Texture Analysis
 
Hog and sift
Hog and siftHog and sift
Hog and sift
 
Visual realism
Visual realismVisual realism
Visual realism
 
GRPHICS05 - Rendering (2)
GRPHICS05 - Rendering (2)GRPHICS05 - Rendering (2)
GRPHICS05 - Rendering (2)
 
Phong Shading over any Polygonal Surface
Phong Shading over any Polygonal Surface Phong Shading over any Polygonal Surface
Phong Shading over any Polygonal Surface
 
Canny Edge Detection
Canny Edge DetectionCanny Edge Detection
Canny Edge Detection
 

En vedette

SIFT Algorithm Introduction
SIFT Algorithm IntroductionSIFT Algorithm Introduction
SIFT Algorithm IntroductionTruong LD
 
2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - English
2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - English2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - English
2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - EnglishCIARD
 
Predicting crop yield and response to Nutrients from soil spectra at WCSS 201...
Predicting crop yield and response to Nutrients from soil spectra at WCSS 201...Predicting crop yield and response to Nutrients from soil spectra at WCSS 201...
Predicting crop yield and response to Nutrients from soil spectra at WCSS 201...CIAT
 
T16 multiple regression
T16 multiple regressionT16 multiple regression
T16 multiple regressionkompellark
 
Regression analysis
Regression analysisRegression analysis
Regression analysisSubin Raj
 
Contextless Object Recognition with Shape-enriched SIFT and Bags of Features
Contextless Object Recognition with Shape-enriched SIFT and Bags of FeaturesContextless Object Recognition with Shape-enriched SIFT and Bags of Features
Contextless Object Recognition with Shape-enriched SIFT and Bags of FeaturesUniversitat Politècnica de Catalunya
 
DOSUG Intro to google prediction api
DOSUG Intro to google prediction apiDOSUG Intro to google prediction api
DOSUG Intro to google prediction apiGabriel Hamilton
 
Analysis of crop yield prediction using data mining techniques
Analysis of crop yield prediction using data mining techniquesAnalysis of crop yield prediction using data mining techniques
Analysis of crop yield prediction using data mining techniqueseSAT Journals
 
Predicting the future with Google Prediction API
Predicting the future with Google Prediction APIPredicting the future with Google Prediction API
Predicting the future with Google Prediction APIRadu-Sebastian Amarie
 
Prediction of house price using multiple regression
Prediction of house price using multiple regressionPrediction of house price using multiple regression
Prediction of house price using multiple regressionvinovk
 
fMRI preprocessing steps (in SPM8)
fMRI preprocessing steps (in SPM8)fMRI preprocessing steps (in SPM8)
fMRI preprocessing steps (in SPM8)Sunghyon Kyeong
 
Face recogntion Using PCA Algorithm
Face recogntion Using PCA Algorithm Face recogntion Using PCA Algorithm
Face recogntion Using PCA Algorithm Ashwini Awatare
 
face recognition system using LBP
face recognition system using LBPface recognition system using LBP
face recognition system using LBPMarwan H. Noman
 
PCA Based Face Recognition System
PCA Based Face Recognition SystemPCA Based Face Recognition System
PCA Based Face Recognition SystemMd. Atiqur Rahman
 

En vedette (20)

Ijetcas14 379
Ijetcas14 379Ijetcas14 379
Ijetcas14 379
 
SIFT Algorithm Introduction
SIFT Algorithm IntroductionSIFT Algorithm Introduction
SIFT Algorithm Introduction
 
Preprocessing
PreprocessingPreprocessing
Preprocessing
 
Lec07 aggregation-and-retrieval-system
Lec07 aggregation-and-retrieval-systemLec07 aggregation-and-retrieval-system
Lec07 aggregation-and-retrieval-system
 
Dsip and its biometrics appln
Dsip and its biometrics applnDsip and its biometrics appln
Dsip and its biometrics appln
 
2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - English
2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - English2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - English
2010-11 CIARD - Bridging Rural Digital Divide (Brasil) - English
 
Predicting crop yield and response to Nutrients from soil spectra at WCSS 201...
Predicting crop yield and response to Nutrients from soil spectra at WCSS 201...Predicting crop yield and response to Nutrients from soil spectra at WCSS 201...
Predicting crop yield and response to Nutrients from soil spectra at WCSS 201...
 
T16 multiple regression
T16 multiple regressionT16 multiple regression
T16 multiple regression
 
Regression analysis
Regression analysisRegression analysis
Regression analysis
 
Contextless Object Recognition with Shape-enriched SIFT and Bags of Features
Contextless Object Recognition with Shape-enriched SIFT and Bags of FeaturesContextless Object Recognition with Shape-enriched SIFT and Bags of Features
Contextless Object Recognition with Shape-enriched SIFT and Bags of Features
 
Face recognition
Face recognitionFace recognition
Face recognition
 
DOSUG Intro to google prediction api
DOSUG Intro to google prediction apiDOSUG Intro to google prediction api
DOSUG Intro to google prediction api
 
Analysis of crop yield prediction using data mining techniques
Analysis of crop yield prediction using data mining techniquesAnalysis of crop yield prediction using data mining techniques
Analysis of crop yield prediction using data mining techniques
 
Predicting the future with Google Prediction API
Predicting the future with Google Prediction APIPredicting the future with Google Prediction API
Predicting the future with Google Prediction API
 
Prediction of house price using multiple regression
Prediction of house price using multiple regressionPrediction of house price using multiple regression
Prediction of house price using multiple regression
 
fMRI preprocessing steps (in SPM8)
fMRI preprocessing steps (in SPM8)fMRI preprocessing steps (in SPM8)
fMRI preprocessing steps (in SPM8)
 
Face recogntion Using PCA Algorithm
Face recogntion Using PCA Algorithm Face recogntion Using PCA Algorithm
Face recogntion Using PCA Algorithm
 
face recognition system using LBP
face recognition system using LBPface recognition system using LBP
face recognition system using LBP
 
PCA Based Face Recognition System
PCA Based Face Recognition SystemPCA Based Face Recognition System
PCA Based Face Recognition System
 
Local binary pattern
Local binary patternLocal binary pattern
Local binary pattern
 

Similaire à Scale Invariant Feature Tranform

Image Processing
Image ProcessingImage Processing
Image ProcessingTuyen Pham
 
Image feature extraction
Image feature extractionImage feature extraction
Image feature extractionRishabh shah
 
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 PEAKSijaia
 
ImageSegmentation (1).ppt
ImageSegmentation (1).pptImageSegmentation (1).ppt
ImageSegmentation (1).pptNoorUlHaq47
 
ImageSegmentation.ppt
ImageSegmentation.pptImageSegmentation.ppt
ImageSegmentation.pptAVUDAI1
 
ImageSegmentation.ppt
ImageSegmentation.pptImageSegmentation.ppt
ImageSegmentation.pptDEEPUKUMARR
 
Module-5-1_230523_171754 (1).pdf
Module-5-1_230523_171754 (1).pdfModule-5-1_230523_171754 (1).pdf
Module-5-1_230523_171754 (1).pdfvikasmittal92
 
geostatistics_for introduction and analysis
geostatistics_for introduction and analysisgeostatistics_for introduction and analysis
geostatistics_for introduction and analysisGadisaGeremewNegasa
 
GEOMETRIC TAMPERING ESTIMATION BY MEANS OF A SIFT-BASED FORENSIC ANALYSIS
GEOMETRIC TAMPERING ESTIMATION  BY MEANS OF A SIFT-BASED FORENSIC ANALYSISGEOMETRIC TAMPERING ESTIMATION  BY MEANS OF A SIFT-BASED FORENSIC ANALYSIS
GEOMETRIC TAMPERING ESTIMATION BY MEANS OF A SIFT-BASED FORENSIC ANALYSISICL - Image Communication Laboratory
 
Chapter10 image segmentation
Chapter10 image segmentationChapter10 image segmentation
Chapter10 image segmentationasodariyabhavesh
 
image segmentation image segmentation.pptx
image segmentation image segmentation.pptximage segmentation image segmentation.pptx
image segmentation image segmentation.pptxNaveenKumar5162
 
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
 
SIFT/SURF can achieve scale, rotation and illumination invariant during image...
SIFT/SURF can achieve scale, rotation and illumination invariant during image...SIFT/SURF can achieve scale, rotation and illumination invariant during image...
SIFT/SURF can achieve scale, rotation and illumination invariant during image...National Cheng Kung University
 
Comparison of Distance Transform Based Features
Comparison of Distance Transform Based FeaturesComparison of Distance Transform Based Features
Comparison of Distance Transform Based FeaturesIJERA Editor
 
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 slidesBHAGYAPRASADBUGGE
 
Introduction to Support Vector Machines
Introduction to Support Vector MachinesIntroduction to Support Vector Machines
Introduction to Support Vector MachinesSilicon Mentor
 
Statistical Inference Part II: Types of Sampling Distribution
Statistical Inference Part II: Types of Sampling DistributionStatistical Inference Part II: Types of Sampling Distribution
Statistical Inference Part II: Types of Sampling DistributionDexlab Analytics
 

Similaire à Scale Invariant Feature Tranform (20)

Image segmentation
Image segmentationImage segmentation
Image segmentation
 
Image Processing
Image ProcessingImage Processing
Image Processing
 
Image feature extraction
Image feature extractionImage feature extraction
Image feature extraction
 
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
 
ImageSegmentation (1).ppt
ImageSegmentation (1).pptImageSegmentation (1).ppt
ImageSegmentation (1).ppt
 
ImageSegmentation.ppt
ImageSegmentation.pptImageSegmentation.ppt
ImageSegmentation.ppt
 
ImageSegmentation.ppt
ImageSegmentation.pptImageSegmentation.ppt
ImageSegmentation.ppt
 
Module-5-1_230523_171754 (1).pdf
Module-5-1_230523_171754 (1).pdfModule-5-1_230523_171754 (1).pdf
Module-5-1_230523_171754 (1).pdf
 
geostatistics_for introduction and analysis
geostatistics_for introduction and analysisgeostatistics_for introduction and analysis
geostatistics_for introduction and analysis
 
GEOMETRIC TAMPERING ESTIMATION BY MEANS OF A SIFT-BASED FORENSIC ANALYSIS
GEOMETRIC TAMPERING ESTIMATION  BY MEANS OF A SIFT-BASED FORENSIC ANALYSISGEOMETRIC TAMPERING ESTIMATION  BY MEANS OF A SIFT-BASED FORENSIC ANALYSIS
GEOMETRIC TAMPERING ESTIMATION BY MEANS OF A SIFT-BASED FORENSIC ANALYSIS
 
Test
TestTest
Test
 
Chapter10 image segmentation
Chapter10 image segmentationChapter10 image segmentation
Chapter10 image segmentation
 
image segmentation image segmentation.pptx
image segmentation image segmentation.pptximage segmentation image segmentation.pptx
image segmentation image segmentation.pptx
 
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)
 
SIFT/SURF can achieve scale, rotation and illumination invariant during image...
SIFT/SURF can achieve scale, rotation and illumination invariant during image...SIFT/SURF can achieve scale, rotation and illumination invariant during image...
SIFT/SURF can achieve scale, rotation and illumination invariant during image...
 
Comparison of Distance Transform Based Features
Comparison of Distance Transform Based FeaturesComparison of Distance Transform Based Features
Comparison of Distance Transform Based Features
 
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
 
3rd unit.pptx
3rd unit.pptx3rd unit.pptx
3rd unit.pptx
 
Introduction to Support Vector Machines
Introduction to Support Vector MachinesIntroduction to Support Vector Machines
Introduction to Support Vector Machines
 
Statistical Inference Part II: Types of Sampling Distribution
Statistical Inference Part II: Types of Sampling DistributionStatistical Inference Part II: Types of Sampling Distribution
Statistical Inference Part II: Types of Sampling Distribution
 

Dernier

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
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024The Digital Insurer
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
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
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
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
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
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
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
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
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 

Dernier (20)

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
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
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
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
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
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
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
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
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
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 

Scale Invariant Feature Tranform

  • 1. Intro: SIFT – (Scale invariant feature transform) The SIFT algorithm takes an image and transforms it into a collection of local feature vectors. Each of these feature vectors is supposed to be distinctive and invariant to any scaling, r otation or translation of the image. Algorithm: 1 Creating Scale-space and Difference of Gaussian pyramid 2 Extrema detection 3 Noise Elimination 4 Orientation assignment 5 Descriptor Computation 6 Keypoints matching 1. Creating Scale-space and Difference of Gaussian pyramid The first stage is to construct a Gaussian "scale space" function from the input image . This is formed by convolution (filtering) of the original image with Gaussian functions of varying widths. The difference of Gaussian (DoG), D(x, y , σ), is calculated as the difference between two filtered images, one with k multiplied by scale of the other . D(x, y , σ) = L(x, y , kσ)-L(x, y , σ) (1) These images, L(x, y , σ), are produced from the convolution of Gaussian functions, G(x, y , kσ), with an input image, I(x, y). L(x, y , σ) = G(x, y , σ)*I(x, y) (2) First, the initial image, I, is convolved with a Gaussian function, G 0 , of width σ 0 . Then we use this blured image, L0 , as the first image in the Gaussian pyramid and incrementally convolve it with a Gaussian, Gi, of width σi to create the ith image in the image pyramid, which is equivalent to the original image filtered with aGaussian, Gk, of width kσ0 .
  • 2. 2. Extrema detection This stage is to find the extrema points in the DOG pyramid. T o detect the local maxima and minima of D(x, y , σ), each point is compared with the pixels of all its 26 neighbours . If this value is the minimum or maximum this point is an extrema. 3. Noise Elimination This stage attempts to eliminate some points from the candidate list of keypoints by finding those that have low contrast or are poorly localised on an edge.[1]. The value of the keypoint in the DoG pyramid at the extrema is given by: If the function value at z is below a threshold value this point is excluded. T o eliminate poorly localized extrema we use the fact that in these cases there is a large principle curvature across the edge but a small curvature in the perpendicular direction in the difference of Gaussian function. A 2x2 Hessian matrix, H, computed at the location and scale of the keypoint is used to find the curvature. With these fomulas, the ratio of principal curvature can be checked efficiently . Tr (H) = Dxx + Dyy Det(H) = DxxDyy - (Dxy )2 R=Tr(H)^2/Det(H) Where r= ratio between small and large Eigen value. So if inequality fails, the key point is removed from the candidate list.
  • 3. 4. Orientation assignment This step aims to assign a consistent orientation to the keypoints based on local image properties. An orientation histogram is formed from the gradient orientations of sample points within a region around the keypoint . A 16x16 square is chosen in this implementation. The orientation histogram has 36 bins covering the 360 degree range of orientations. The gradient magnitude, m(x, y), and orientation, θ(x, y), is precomputed using pixel differences: Each sample is weighted by its gradient magnitude and by a Gaussian-weighted circular window with a σ that is 1.5 times that of the scale of the keypoint. 5. Descriptor Computation In this stage, a descriptor is computed for the local image region that is as distinctive as possible at each candidate keypoint. The image gradient magnitudes and orientations are sampled around the keypoint location. These values are illustrated with small arrows at each sample location on the first image of Figures. A Gaussian weighting function with σ related to the scale of the keypoint is used to assign a weight to the magnitude.We use a σ equal to one half the width of the descriptor window in this implementation. In order to achieve orientation invariance, the coordinates of the descriptor and the gradient orientations are rotated relative to the keypoint orientation. This process is indicated in Figure 5. In our implementation, a 16x16 sample array is computed and a histogram with 8 bins is used. So a descriptor contains 16x16x8 elements in total. This vector is then normalized to unit length in order to enhance invariance to affine changes in illumination.
  • 4. 6. Keypoints matching Knowing the keypoints and descriptors using Euclidean distance ,each keypoint in the original image (model image) is compared to every keypoints in the transformed image using the descriptors computed in the previous stage. The descriptors of the two respective, keypoints must be closest. Then match is found.