SlideShare une entreprise Scribd logo
1  sur  53
SIFT: Scale Invariant Feature Transform Presenter: Michal Erel ,[object Object],[object Object],[object Object]
Object Recognition ,[object Object],[object Object]
Why do we care about matching features? ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Location Recognition
Panoramic Image Matching
We want invariance!!! ,[object Object]
Types of invariance ,[object Object]
Types of invariance ,[object Object],[object Object]
Types of invariance ,[object Object],[object Object],[object Object]
Types of invariance ,[object Object],[object Object],[object Object],[object Object]
Types of invariance ,[object Object],[object Object],[object Object],[object Object],[object Object]
SIFT- Scale Invariant Feature Transform ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Step I: Detection of Scale-Space Extrema ,[object Object],[object Object]
Scale-Space
Scale-Space To scale: take every second pixel in each row and column (another approach: average 4 pixels)
Difference of Gaussians (DOG) Sigma 4 Sigma2-Sigma4 Sigma 2
Scale-Space with DOG
Scale-Space with DOG
Local Extrema Detection ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Keypoints Too many keypoints, some are unstable
Step II: Keypoint Localization Reject points with low contrast  Reject points that are localized along an edge.
Step II: Keypoint Localization ,[object Object],[object Object]
Keypoint Localization ,[object Object],[object Object]
Keypoint Localization Use Quadric Taylor Expansion of the scale-space function, so that the origin is at the sample point: (x is the offset from this point) Calculate extermum: if X > 0.5: the extermum lies closer to a different point (Need to recalculate…) Otherwise: add offset to the sample point location to get the estimated extremum ^
Reject Low Contrast Keypoints Calculate value of D at extremum point X: if |D(X)| < 0.03: discard keypoint for having a low contrast
Reject Low Contrast Keypoints
Eliminate Edge Responses: DoG function might have strong response along edges, even if unstable to small amounts of noise Edge identification: large principal curvature across the edge, but small one in perpendicular direction. Note  ♥ :  It's easy to show that the two principle curvatures (i.e., the min and max curvatures) are always along directions perpendicular to each other.  In general, finding the principle directions amounts to solving a nxn eigenvalue problem
Eliminate Edge Responses: No need to explicitly calculate the eigenvalues – we only need their ratio!! a = small eigenvalue  b = large eigenvalue r = ratio between large and small eigenvalues (r=a/b) (r+1)^2/r is at min when a=b, and increases as the ratio increases
Eliminate Edge Responses: To check if the ratio of the principal curvatures is below a threshold r, we only need to check if:  Use r = 10 to reject keypoints that lay along an edge
Reject Near-Edge Keypoints
832 keypoints 729 keypoints (eliminate low contrast) 536 keypoints (eliminate edge keypoints)
Step III: Orientation Assignment Each keypoint is assigned 1 or more orientations, based on local image gradient directions.  Data is trasformed relative to the assigned orientation, scale and location hence providing invariance to these transformations
Gradient Calculation The scale of the keypoint is used to select the Gaussian image L we’ll work on (image with closest scale) –  All computations are performed in a scale-invariant manner.  We calculate gradient magnitue and orientation using pixel differences:
Gradient Calculation
Gradient Calculation
Orientation Histogram Orientation histogram with 36 bins (each bin covers 10 degrees) Each sample added to the histogram bin is weighted by its gradient magnitude and by a Gaussian weighted circular window with theta = 1.5 times that of the keypoint scale
Orientation Histogram: Detect highest peak and local peaks that are within 80% of the highest peak. Use these to assign (1 or more) orientations
Step IV: Local Image Descriptor Previous operations imposed a local 2D coordination system, which provides invariance to image location, scale and orientation  We wish to compute descriptors for the local image regions: 1. Highly distinctive 2. Invariant as possible to remaining variations (illumination, 3D viewpoint…)
Descriptor Representation Use the scale of the keypoint to select the level of Gaussian blur. Sample the gradient magnitude and orientation around the keypoint Assign weight to magnitude using a Gaussian weighted function with theta = ½ width of descriptor window  (provides gradual change & gives less emphasis to gradients far from the keypoint Use a descriptor array with  histogram bins
Descriptor Representation
Descriptor Representation :
Invariance to Affine Illumination Changes: * Multiplication by a constant: Normalize vector to unit length: A change in each pixel: pixel -> a * pixel (each pixel multiplied by a constant) will result – gradient -> gradient * a. This will be canceled by the normalization * Addition of  a constant: pixel -> pixel + a  Has no effect on the gradient
Partial Invariance To Non Affine Illumination changes: Will cause large change in relative magnitude, but is unlikely to affect gradient orientations. Solution: reduce the influence of large gradient magintudes by thresholding the values to be no larger than 0.2, then normalize them to unit length.
Partial Invariance To Affine Change In Viewpoint Angle:
Object Recognition: Best candidate match for each keypoint is  nearest neighbour in database Problem: many background features will not have a matching pair in database resulting in a false match Global threshold to descriptors does not perform well since some descriptors are more discriminating than others Solution: Compare distance to closet neighbour to that of the second closet neighbour (that comes from a different object)
Results:
More Results:
More Results  (not as successful…):
Image matching:
Sources / Web Sources: ,[object Object],[object Object],[object Object],[object Object]
Slide / Web Sources Continued: ,[object Object],[object Object],[object Object]
Slide / Web Sources Continued: ,[object Object],[object Object],[object Object],[object Object]
The  End…

Contenu connexe

Tendances

Image Classification And Support Vector Machine
Image Classification And Support Vector MachineImage Classification And Support Vector Machine
Image Classification And Support Vector Machine
Shao-Chuan Wang
 
Image feature extraction
Image feature extractionImage feature extraction
Image feature extraction
Rushin Shah
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extraction
skylian
 
Digital Image Processing 3rd edition Rafael C. Gonzalez, Richard E. Woods.pdf
Digital Image Processing 3rd edition Rafael C. Gonzalez, Richard E. Woods.pdfDigital Image Processing 3rd edition Rafael C. Gonzalez, Richard E. Woods.pdf
Digital Image Processing 3rd edition Rafael C. Gonzalez, Richard E. Woods.pdf
ssuserbe3944
 

Tendances (20)

Canny Edge Detection
Canny Edge DetectionCanny Edge Detection
Canny Edge Detection
 
Feature detection and matching
Feature detection and matchingFeature detection and matching
Feature detection and matching
 
Scale Invariant Feature Transform
Scale Invariant Feature TransformScale Invariant Feature Transform
Scale Invariant Feature Transform
 
Chapter10 image segmentation
Chapter10 image segmentationChapter10 image segmentation
Chapter10 image segmentation
 
Feed forward ,back propagation,gradient descent
Feed forward ,back propagation,gradient descentFeed forward ,back propagation,gradient descent
Feed forward ,back propagation,gradient descent
 
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
 
Image Classification And Support Vector Machine
Image Classification And Support Vector MachineImage Classification And Support Vector Machine
Image Classification And Support Vector Machine
 
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
[PR12] You Only Look Once (YOLO): Unified Real-Time Object Detection
 
Image segmentation
Image segmentationImage segmentation
Image segmentation
 
Chapter 9 morphological image processing
Chapter 9   morphological image processingChapter 9   morphological image processing
Chapter 9 morphological image processing
 
Object Recognition
Object RecognitionObject Recognition
Object Recognition
 
Speaker Recognition using Gaussian Mixture Model
Speaker Recognition using Gaussian Mixture Model Speaker Recognition using Gaussian Mixture Model
Speaker Recognition using Gaussian Mixture Model
 
Edge detection
Edge detectionEdge detection
Edge detection
 
Image feature extraction
Image feature extractionImage feature extraction
Image feature extraction
 
Feature Extraction
Feature ExtractionFeature Extraction
Feature Extraction
 
Features image processing and Extaction
Features image processing and ExtactionFeatures image processing and Extaction
Features image processing and Extaction
 
OpenCV presentation series- part 1
OpenCV presentation series- part 1OpenCV presentation series- part 1
OpenCV presentation series- part 1
 
Computer vision lane line detection
Computer vision lane line detectionComputer vision lane line detection
Computer vision lane line detection
 
Lec13: Clustering Based Medical Image Segmentation Methods
Lec13: Clustering Based Medical Image Segmentation MethodsLec13: Clustering Based Medical Image Segmentation Methods
Lec13: Clustering Based Medical Image Segmentation Methods
 
Digital Image Processing 3rd edition Rafael C. Gonzalez, Richard E. Woods.pdf
Digital Image Processing 3rd edition Rafael C. Gonzalez, Richard E. Woods.pdfDigital Image Processing 3rd edition Rafael C. Gonzalez, Richard E. Woods.pdf
Digital Image Processing 3rd edition Rafael C. Gonzalez, Richard E. Woods.pdf
 

Similaire à Michal Erel's SIFT presentation

Kulum alin-11 jan2014
Kulum alin-11 jan2014Kulum alin-11 jan2014
Kulum alin-11 jan2014
rolly purnomo
 
Interpolation 2013
Interpolation 2013Interpolation 2013
Interpolation 2013
Atiqa Khan
 

Similaire à Michal Erel's SIFT presentation (20)

06 image features
06 image features06 image features
06 image features
 
CV PPT.pptx
CV PPT.pptxCV PPT.pptx
CV PPT.pptx
 
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
 
Sift detector boosted by adaptive contrast threshold to improve matching robu...
Sift detector boosted by adaptive contrast threshold to improve matching robu...Sift detector boosted by adaptive contrast threshold to improve matching robu...
Sift detector boosted by adaptive contrast threshold to improve matching robu...
 
Sift detector boosted by adaptive contrast threshold to improve matching robu...
Sift detector boosted by adaptive contrast threshold to improve matching robu...Sift detector boosted by adaptive contrast threshold to improve matching robu...
Sift detector boosted by adaptive contrast threshold to improve matching robu...
 
Computer Vision descriptors
Computer Vision descriptorsComputer Vision descriptors
Computer Vision descriptors
 
SIFT.ppt
SIFT.pptSIFT.ppt
SIFT.ppt
 
PPT s11-machine vision-s2
PPT s11-machine vision-s2PPT s11-machine vision-s2
PPT s11-machine vision-s2
 
Ijcatr04041016
Ijcatr04041016Ijcatr04041016
Ijcatr04041016
 
image segmentation by ppres.pptx
image segmentation by ppres.pptximage segmentation by ppres.pptx
image segmentation by ppres.pptx
 
Lec10 alignment
Lec10 alignmentLec10 alignment
Lec10 alignment
 
Kulum alin-11 jan2014
Kulum alin-11 jan2014Kulum alin-11 jan2014
Kulum alin-11 jan2014
 
Real time Canny edge detection
Real time Canny edge detectionReal time Canny edge detection
Real time Canny edge detection
 
Multi-Image Matching
Multi-Image MatchingMulti-Image Matching
Multi-Image Matching
 
Registration & Modeling of Shapes with Uncertainties
Registration & Modeling of Shapes with UncertaintiesRegistration & Modeling of Shapes with Uncertainties
Registration & Modeling of Shapes with Uncertainties
 
Interpolation 2013
Interpolation 2013Interpolation 2013
Interpolation 2013
 
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
 
Image feature extraction
Image feature extractionImage feature extraction
Image feature extraction
 
Estrazione automatica delle linee in un'immagine digitale
Estrazione automatica delle linee in un'immagine digitaleEstrazione automatica delle linee in un'immagine digitale
Estrazione automatica delle linee in un'immagine digitale
 
I010634450
I010634450I010634450
I010634450
 

Plus de wolf

A bayesian framework for unsupervised one-shot learning of object categories
A bayesian framework for unsupervised one-shot learning of object categoriesA bayesian framework for unsupervised one-shot learning of object categories
A bayesian framework for unsupervised one-shot learning of object categories
wolf
 
Moshe Guttmann's slides on eigenface
Moshe Guttmann's slides on eigenfaceMoshe Guttmann's slides on eigenface
Moshe Guttmann's slides on eigenface
wolf
 
Object recognition seminar S2006E01
Object recognition seminar S2006E01Object recognition seminar S2006E01
Object recognition seminar S2006E01
wolf
 

Plus de wolf (12)

Eigenfaces and Fisherfaces
Eigenfaces and FisherfacesEigenfaces and Fisherfaces
Eigenfaces and Fisherfaces
 
Shai Avidan's Support vector tracking and ensemble tracking
Shai Avidan's Support vector tracking and ensemble trackingShai Avidan's Support vector tracking and ensemble tracking
Shai Avidan's Support vector tracking and ensemble tracking
 
Constellation Models and Unsupervised Learning for Object Class Recognition
Constellation Models and Unsupervised Learning for Object Class RecognitionConstellation Models and Unsupervised Learning for Object Class Recognition
Constellation Models and Unsupervised Learning for Object Class Recognition
 
A bayesian framework for unsupervised one-shot learning of object categories
A bayesian framework for unsupervised one-shot learning of object categoriesA bayesian framework for unsupervised one-shot learning of object categories
A bayesian framework for unsupervised one-shot learning of object categories
 
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Fe...
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Fe...The Pyramid Match Kernel: Discriminative Classification with Sets of Image Fe...
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Fe...
 
Recovering 3D human body configurations using shape contexts
Recovering 3D human body configurations using shape contextsRecovering 3D human body configurations using shape contexts
Recovering 3D human body configurations using shape contexts
 
Rafi Zachut's slides on class specific segmentation
Rafi Zachut's slides on class specific segmentationRafi Zachut's slides on class specific segmentation
Rafi Zachut's slides on class specific segmentation
 
Avihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slidesAvihu Efrat's Viola and Jones face detection slides
Avihu Efrat's Viola and Jones face detection slides
 
Ala Stolpnik's Standard Model talk
Ala Stolpnik's Standard Model talkAla Stolpnik's Standard Model talk
Ala Stolpnik's Standard Model talk
 
Gil Shapira's Active Appearance Model slides
Gil Shapira's Active Appearance Model slidesGil Shapira's Active Appearance Model slides
Gil Shapira's Active Appearance Model slides
 
Moshe Guttmann's slides on eigenface
Moshe Guttmann's slides on eigenfaceMoshe Guttmann's slides on eigenface
Moshe Guttmann's slides on eigenface
 
Object recognition seminar S2006E01
Object recognition seminar S2006E01Object recognition seminar S2006E01
Object recognition seminar S2006E01
 

Dernier

Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
amitlee9823
 
Call Girls Jp Nagar Just Call 👗 7737669865 👗 Top Class Call Girl Service Bang...
Call Girls Jp Nagar Just Call 👗 7737669865 👗 Top Class Call Girl Service Bang...Call Girls Jp Nagar Just Call 👗 7737669865 👗 Top Class Call Girl Service Bang...
Call Girls Jp Nagar Just Call 👗 7737669865 👗 Top Class Call Girl Service Bang...
amitlee9823
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
dollysharma2066
 
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
lizamodels9
 
FULL ENJOY Call Girls In Majnu Ka Tilla, Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Majnu Ka Tilla, Delhi Contact Us 8377877756FULL ENJOY Call Girls In Majnu Ka Tilla, Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Majnu Ka Tilla, Delhi Contact Us 8377877756
dollysharma2066
 
Quick Doctor In Kuwait +2773`7758`557 Kuwait Doha Qatar Dubai Abu Dhabi Sharj...
Quick Doctor In Kuwait +2773`7758`557 Kuwait Doha Qatar Dubai Abu Dhabi Sharj...Quick Doctor In Kuwait +2773`7758`557 Kuwait Doha Qatar Dubai Abu Dhabi Sharj...
Quick Doctor In Kuwait +2773`7758`557 Kuwait Doha Qatar Dubai Abu Dhabi Sharj...
daisycvs
 
Insurers' journeys to build a mastery in the IoT usage
Insurers' journeys to build a mastery in the IoT usageInsurers' journeys to build a mastery in the IoT usage
Insurers' journeys to build a mastery in the IoT usage
Matteo Carbone
 
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
lizamodels9
 
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
Dipal Arora
 

Dernier (20)

Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
Call Girls Kengeri Satellite Town Just Call 👗 7737669865 👗 Top Class Call Gir...
 
Call Girls Jp Nagar Just Call 👗 7737669865 👗 Top Class Call Girl Service Bang...
Call Girls Jp Nagar Just Call 👗 7737669865 👗 Top Class Call Girl Service Bang...Call Girls Jp Nagar Just Call 👗 7737669865 👗 Top Class Call Girl Service Bang...
Call Girls Jp Nagar Just Call 👗 7737669865 👗 Top Class Call Girl Service Bang...
 
Mysore Call Girls 8617370543 WhatsApp Number 24x7 Best Services
Mysore Call Girls 8617370543 WhatsApp Number 24x7 Best ServicesMysore Call Girls 8617370543 WhatsApp Number 24x7 Best Services
Mysore Call Girls 8617370543 WhatsApp Number 24x7 Best Services
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
 
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
Call Girls In DLf Gurgaon ➥99902@11544 ( Best price)100% Genuine Escort In 24...
 
RSA Conference Exhibitor List 2024 - Exhibitors Data
RSA Conference Exhibitor List 2024 - Exhibitors DataRSA Conference Exhibitor List 2024 - Exhibitors Data
RSA Conference Exhibitor List 2024 - Exhibitors Data
 
Cracking the Cultural Competence Code.pptx
Cracking the Cultural Competence Code.pptxCracking the Cultural Competence Code.pptx
Cracking the Cultural Competence Code.pptx
 
John Halpern sued for sexual assault.pdf
John Halpern sued for sexual assault.pdfJohn Halpern sued for sexual assault.pdf
John Halpern sued for sexual assault.pdf
 
Business Model Canvas (BMC)- A new venture concept
Business Model Canvas (BMC)-  A new venture conceptBusiness Model Canvas (BMC)-  A new venture concept
Business Model Canvas (BMC)- A new venture concept
 
It will be International Nurses' Day on 12 May
It will be International Nurses' Day on 12 MayIt will be International Nurses' Day on 12 May
It will be International Nurses' Day on 12 May
 
Phases of Negotiation .pptx
 Phases of Negotiation .pptx Phases of Negotiation .pptx
Phases of Negotiation .pptx
 
FULL ENJOY Call Girls In Majnu Ka Tilla, Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Majnu Ka Tilla, Delhi Contact Us 8377877756FULL ENJOY Call Girls In Majnu Ka Tilla, Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Majnu Ka Tilla, Delhi Contact Us 8377877756
 
Katrina Personal Brand Project and portfolio 1
Katrina Personal Brand Project and portfolio 1Katrina Personal Brand Project and portfolio 1
Katrina Personal Brand Project and portfolio 1
 
Quick Doctor In Kuwait +2773`7758`557 Kuwait Doha Qatar Dubai Abu Dhabi Sharj...
Quick Doctor In Kuwait +2773`7758`557 Kuwait Doha Qatar Dubai Abu Dhabi Sharj...Quick Doctor In Kuwait +2773`7758`557 Kuwait Doha Qatar Dubai Abu Dhabi Sharj...
Quick Doctor In Kuwait +2773`7758`557 Kuwait Doha Qatar Dubai Abu Dhabi Sharj...
 
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service AvailableCall Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
Call Girls Ludhiana Just Call 98765-12871 Top Class Call Girl Service Available
 
Insurers' journeys to build a mastery in the IoT usage
Insurers' journeys to build a mastery in the IoT usageInsurers' journeys to build a mastery in the IoT usage
Insurers' journeys to build a mastery in the IoT usage
 
BAGALUR CALL GIRL IN 98274*61493 ❤CALL GIRLS IN ESCORT SERVICE❤CALL GIRL
BAGALUR CALL GIRL IN 98274*61493 ❤CALL GIRLS IN ESCORT SERVICE❤CALL GIRLBAGALUR CALL GIRL IN 98274*61493 ❤CALL GIRLS IN ESCORT SERVICE❤CALL GIRL
BAGALUR CALL GIRL IN 98274*61493 ❤CALL GIRLS IN ESCORT SERVICE❤CALL GIRL
 
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
Russian Call Girls In Gurgaon ❤️8448577510 ⊹Best Escorts Service In 24/7 Delh...
 
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
Call Girls Navi Mumbai Just Call 9907093804 Top Class Call Girl Service Avail...
 
Falcon's Invoice Discounting: Your Path to Prosperity
Falcon's Invoice Discounting: Your Path to ProsperityFalcon's Invoice Discounting: Your Path to Prosperity
Falcon's Invoice Discounting: Your Path to Prosperity
 

Michal Erel's SIFT presentation

  • 1.
  • 2.
  • 3.
  • 6.
  • 7.
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 13.
  • 15. Scale-Space To scale: take every second pixel in each row and column (another approach: average 4 pixels)
  • 16. Difference of Gaussians (DOG) Sigma 4 Sigma2-Sigma4 Sigma 2
  • 19.
  • 20. Keypoints Too many keypoints, some are unstable
  • 21. Step II: Keypoint Localization Reject points with low contrast Reject points that are localized along an edge.
  • 22.
  • 23.
  • 24. Keypoint Localization Use Quadric Taylor Expansion of the scale-space function, so that the origin is at the sample point: (x is the offset from this point) Calculate extermum: if X > 0.5: the extermum lies closer to a different point (Need to recalculate…) Otherwise: add offset to the sample point location to get the estimated extremum ^
  • 25. Reject Low Contrast Keypoints Calculate value of D at extremum point X: if |D(X)| < 0.03: discard keypoint for having a low contrast
  • 26. Reject Low Contrast Keypoints
  • 27. Eliminate Edge Responses: DoG function might have strong response along edges, even if unstable to small amounts of noise Edge identification: large principal curvature across the edge, but small one in perpendicular direction. Note ♥ : It's easy to show that the two principle curvatures (i.e., the min and max curvatures) are always along directions perpendicular to each other.  In general, finding the principle directions amounts to solving a nxn eigenvalue problem
  • 28. Eliminate Edge Responses: No need to explicitly calculate the eigenvalues – we only need their ratio!! a = small eigenvalue b = large eigenvalue r = ratio between large and small eigenvalues (r=a/b) (r+1)^2/r is at min when a=b, and increases as the ratio increases
  • 29. Eliminate Edge Responses: To check if the ratio of the principal curvatures is below a threshold r, we only need to check if: Use r = 10 to reject keypoints that lay along an edge
  • 31. 832 keypoints 729 keypoints (eliminate low contrast) 536 keypoints (eliminate edge keypoints)
  • 32. Step III: Orientation Assignment Each keypoint is assigned 1 or more orientations, based on local image gradient directions. Data is trasformed relative to the assigned orientation, scale and location hence providing invariance to these transformations
  • 33. Gradient Calculation The scale of the keypoint is used to select the Gaussian image L we’ll work on (image with closest scale) – All computations are performed in a scale-invariant manner. We calculate gradient magnitue and orientation using pixel differences:
  • 36. Orientation Histogram Orientation histogram with 36 bins (each bin covers 10 degrees) Each sample added to the histogram bin is weighted by its gradient magnitude and by a Gaussian weighted circular window with theta = 1.5 times that of the keypoint scale
  • 37. Orientation Histogram: Detect highest peak and local peaks that are within 80% of the highest peak. Use these to assign (1 or more) orientations
  • 38. Step IV: Local Image Descriptor Previous operations imposed a local 2D coordination system, which provides invariance to image location, scale and orientation We wish to compute descriptors for the local image regions: 1. Highly distinctive 2. Invariant as possible to remaining variations (illumination, 3D viewpoint…)
  • 39. Descriptor Representation Use the scale of the keypoint to select the level of Gaussian blur. Sample the gradient magnitude and orientation around the keypoint Assign weight to magnitude using a Gaussian weighted function with theta = ½ width of descriptor window (provides gradual change & gives less emphasis to gradients far from the keypoint Use a descriptor array with histogram bins
  • 42. Invariance to Affine Illumination Changes: * Multiplication by a constant: Normalize vector to unit length: A change in each pixel: pixel -> a * pixel (each pixel multiplied by a constant) will result – gradient -> gradient * a. This will be canceled by the normalization * Addition of a constant: pixel -> pixel + a Has no effect on the gradient
  • 43. Partial Invariance To Non Affine Illumination changes: Will cause large change in relative magnitude, but is unlikely to affect gradient orientations. Solution: reduce the influence of large gradient magintudes by thresholding the values to be no larger than 0.2, then normalize them to unit length.
  • 44. Partial Invariance To Affine Change In Viewpoint Angle:
  • 45. Object Recognition: Best candidate match for each keypoint is nearest neighbour in database Problem: many background features will not have a matching pair in database resulting in a false match Global threshold to descriptors does not perform well since some descriptors are more discriminating than others Solution: Compare distance to closet neighbour to that of the second closet neighbour (that comes from a different object)
  • 48. More Results (not as successful…):
  • 50.
  • 51.
  • 52.