Suche senden
Hochladen
13 cv mil_preprocessing
•
Als PPTX, PDF herunterladen
•
1 gefällt mir
•
346 views
Z
zukun
Folgen
Technologie
Bildung
Melden
Teilen
Melden
Teilen
1 von 52
Jetzt herunterladen
Empfohlen
De-convolution on Digital Images
De-convolution on Digital Images
Md. Shohel Rana
Lighting and shading
Lighting and shading
eshveeen
morphological image processing
morphological image processing
Anubhav Kumar
Moshe Guttmann's slides on eigenface
Moshe Guttmann's slides on eigenface
wolf
ResearchPaper
ResearchPaper
Ian Bloom
Digitized images and
Digitized images and
Ashish Kumar
Chapter 9 morphological image processing
Chapter 9 morphological image processing
Ahmed Daoud
Erosion and dilation
Erosion and dilation
Akhil .B
Empfohlen
De-convolution on Digital Images
De-convolution on Digital Images
Md. Shohel Rana
Lighting and shading
Lighting and shading
eshveeen
morphological image processing
morphological image processing
Anubhav Kumar
Moshe Guttmann's slides on eigenface
Moshe Guttmann's slides on eigenface
wolf
ResearchPaper
ResearchPaper
Ian Bloom
Digitized images and
Digitized images and
Ashish Kumar
Chapter 9 morphological image processing
Chapter 9 morphological image processing
Ahmed Daoud
Erosion and dilation
Erosion and dilation
Akhil .B
Morphological image processing
Morphological image processing
Vinayak Narayanan
Chapter 9 morphological image processing
Chapter 9 morphological image processing
asodariyabhavesh
Image segmentation 3 morphology
Image segmentation 3 morphology
Rumah Belajar
Morphological operations
Morphological operations
National Institute of Technology Durgapur
Chapter 9 morphological image processing
Chapter 9 morphological image processing
Ahmed Daoud
Morphological image processing
Morphological image processing
Visvesvaraya National Institute of Technology, Nagpur, Maharashtra, India
04 cv mil_fitting_probability_models
04 cv mil_fitting_probability_models
zukun
GRPHICS06 - Shading
GRPHICS06 - Shading
Michael Heron
Cp31608611
Cp31608611
IJERA Editor
Morphological Image Processing
Morphological Image Processing
kumari36
Morphological image processing
Morphological image processing
Raghu Kumar
"Fundamentals of Monocular SLAM," a Presentation from Cadence
"Fundamentals of Monocular SLAM," a Presentation from Cadence
Edge AI and Vision Alliance
Shadow Mapping with Today's OpenGL Hardware
Shadow Mapping with Today's OpenGL Hardware
Mark Kilgard
Boundary Extraction
Boundary Extraction
Maria Akther
COM2304: Morphological Image Processing
COM2304: Morphological Image Processing
Hemantha Kulathilake
morphological image processing
morphological image processing
John Williams
Hit and-miss transform
Hit and-miss transform
Krish Everglades
Dilation and erosion
Dilation and erosion
Aswin Pv
Morphology in graphics and image processing
Morphology in graphics and image processing
Dheeban Smart
GRPHICS05 - Rendering (2)
GRPHICS05 - Rendering (2)
Michael Heron
Fcv core szeliski_zisserman
Fcv core szeliski_zisserman
zukun
03 history of cv - a personal perspective
03 history of cv - a personal perspective
zukun
Weitere ähnliche Inhalte
Was ist angesagt?
Morphological image processing
Morphological image processing
Vinayak Narayanan
Chapter 9 morphological image processing
Chapter 9 morphological image processing
asodariyabhavesh
Image segmentation 3 morphology
Image segmentation 3 morphology
Rumah Belajar
Morphological operations
Morphological operations
National Institute of Technology Durgapur
Chapter 9 morphological image processing
Chapter 9 morphological image processing
Ahmed Daoud
Morphological image processing
Morphological image processing
Visvesvaraya National Institute of Technology, Nagpur, Maharashtra, India
04 cv mil_fitting_probability_models
04 cv mil_fitting_probability_models
zukun
GRPHICS06 - Shading
GRPHICS06 - Shading
Michael Heron
Cp31608611
Cp31608611
IJERA Editor
Morphological Image Processing
Morphological Image Processing
kumari36
Morphological image processing
Morphological image processing
Raghu Kumar
"Fundamentals of Monocular SLAM," a Presentation from Cadence
"Fundamentals of Monocular SLAM," a Presentation from Cadence
Edge AI and Vision Alliance
Shadow Mapping with Today's OpenGL Hardware
Shadow Mapping with Today's OpenGL Hardware
Mark Kilgard
Boundary Extraction
Boundary Extraction
Maria Akther
COM2304: Morphological Image Processing
COM2304: Morphological Image Processing
Hemantha Kulathilake
morphological image processing
morphological image processing
John Williams
Hit and-miss transform
Hit and-miss transform
Krish Everglades
Dilation and erosion
Dilation and erosion
Aswin Pv
Morphology in graphics and image processing
Morphology in graphics and image processing
Dheeban Smart
GRPHICS05 - Rendering (2)
GRPHICS05 - Rendering (2)
Michael Heron
Was ist angesagt?
(20)
Morphological image processing
Morphological image processing
Chapter 9 morphological image processing
Chapter 9 morphological image processing
Image segmentation 3 morphology
Image segmentation 3 morphology
Morphological operations
Morphological operations
Chapter 9 morphological image processing
Chapter 9 morphological image processing
Morphological image processing
Morphological image processing
04 cv mil_fitting_probability_models
04 cv mil_fitting_probability_models
GRPHICS06 - Shading
GRPHICS06 - Shading
Cp31608611
Cp31608611
Morphological Image Processing
Morphological Image Processing
Morphological image processing
Morphological image processing
"Fundamentals of Monocular SLAM," a Presentation from Cadence
"Fundamentals of Monocular SLAM," a Presentation from Cadence
Shadow Mapping with Today's OpenGL Hardware
Shadow Mapping with Today's OpenGL Hardware
Boundary Extraction
Boundary Extraction
COM2304: Morphological Image Processing
COM2304: Morphological Image Processing
morphological image processing
morphological image processing
Hit and-miss transform
Hit and-miss transform
Dilation and erosion
Dilation and erosion
Morphology in graphics and image processing
Morphology in graphics and image processing
GRPHICS05 - Rendering (2)
GRPHICS05 - Rendering (2)
Andere mochten auch
Fcv core szeliski_zisserman
Fcv core szeliski_zisserman
zukun
03 history of cv - a personal perspective
03 history of cv - a personal perspective
zukun
06 history of cv computer vision - toweards a simple bruth-force utility
06 history of cv computer vision - toweards a simple bruth-force utility
zukun
Fcv cross hertzmann
Fcv cross hertzmann
zukun
Fcv bio cv_cottrell
Fcv bio cv_cottrell
zukun
Deep Learning workshop 2010: Deep Learning of Invariant Spatiotemporal Featur...
Deep Learning workshop 2010: Deep Learning of Invariant Spatiotemporal Featur...
zukun
07 history of cv vision paradigms - system - algorithms - applications - eva...
07 history of cv vision paradigms - system - algorithms - applications - eva...
zukun
Lecture 01 internet video search
Lecture 01 internet video search
zukun
From Zero To Visibility
From Zero To Visibility
bridgetkromhout
Andere mochten auch
(9)
Fcv core szeliski_zisserman
Fcv core szeliski_zisserman
03 history of cv - a personal perspective
03 history of cv - a personal perspective
06 history of cv computer vision - toweards a simple bruth-force utility
06 history of cv computer vision - toweards a simple bruth-force utility
Fcv cross hertzmann
Fcv cross hertzmann
Fcv bio cv_cottrell
Fcv bio cv_cottrell
Deep Learning workshop 2010: Deep Learning of Invariant Spatiotemporal Featur...
Deep Learning workshop 2010: Deep Learning of Invariant Spatiotemporal Featur...
07 history of cv vision paradigms - system - algorithms - applications - eva...
07 history of cv vision paradigms - system - algorithms - applications - eva...
Lecture 01 internet video search
Lecture 01 internet video search
From Zero To Visibility
From Zero To Visibility
Ähnlich wie 13 cv mil_preprocessing
17 cv mil_models_for_shape
17 cv mil_models_for_shape
zukun
09 cv mil_classification
09 cv mil_classification
zukun
08 cv mil_regression
08 cv mil_regression
zukun
20 cv mil_models_for_words
20 cv mil_models_for_words
zukun
15 cv mil_models_for_transformations
15 cv mil_models_for_transformations
zukun
14 cv mil_the_pinhole_camera
14 cv mil_the_pinhole_camera
zukun
07 cv mil_modeling_complex_densities
07 cv mil_modeling_complex_densities
zukun
11 cv mil_models_for_chains_and_trees
11 cv mil_models_for_chains_and_trees
zukun
16 cv mil_multiple_cameras
16 cv mil_multiple_cameras
zukun
03 cv mil_probability_distributions
03 cv mil_probability_distributions
zukun
12 cv mil_models_for_grids
12 cv mil_models_for_grids
zukun
Common Probability Distibution
Common Probability Distibution
Lukas Tencer
18 cv mil_style_and_identity
18 cv mil_style_and_identity
zukun
10 cv mil_graphical_models
10 cv mil_graphical_models
zukun
Introduction to Probability
Introduction to Probability
Lukas Tencer
02 cv mil_intro_to_probability
02 cv mil_intro_to_probability
zukun
06 cv mil_learning_and_inference
06 cv mil_learning_and_inference
zukun
Graphical Models for chains, trees and grids
Graphical Models for chains, trees and grids
potaters
05 cv mil_normal_distribution
05 cv mil_normal_distribution
zukun
Introduction to 3D Computer Vision and Differentiable Rendering
Introduction to 3D Computer Vision and Differentiable Rendering
Preferred Networks
Ähnlich wie 13 cv mil_preprocessing
(20)
17 cv mil_models_for_shape
17 cv mil_models_for_shape
09 cv mil_classification
09 cv mil_classification
08 cv mil_regression
08 cv mil_regression
20 cv mil_models_for_words
20 cv mil_models_for_words
15 cv mil_models_for_transformations
15 cv mil_models_for_transformations
14 cv mil_the_pinhole_camera
14 cv mil_the_pinhole_camera
07 cv mil_modeling_complex_densities
07 cv mil_modeling_complex_densities
11 cv mil_models_for_chains_and_trees
11 cv mil_models_for_chains_and_trees
16 cv mil_multiple_cameras
16 cv mil_multiple_cameras
03 cv mil_probability_distributions
03 cv mil_probability_distributions
12 cv mil_models_for_grids
12 cv mil_models_for_grids
Common Probability Distibution
Common Probability Distibution
18 cv mil_style_and_identity
18 cv mil_style_and_identity
10 cv mil_graphical_models
10 cv mil_graphical_models
Introduction to Probability
Introduction to Probability
02 cv mil_intro_to_probability
02 cv mil_intro_to_probability
06 cv mil_learning_and_inference
06 cv mil_learning_and_inference
Graphical Models for chains, trees and grids
Graphical Models for chains, trees and grids
05 cv mil_normal_distribution
05 cv mil_normal_distribution
Introduction to 3D Computer Vision and Differentiable Rendering
Introduction to 3D Computer Vision and Differentiable Rendering
Mehr von zukun
My lyn tutorial 2009
My lyn tutorial 2009
zukun
ETHZ CV2012: Tutorial openCV
ETHZ CV2012: Tutorial openCV
zukun
ETHZ CV2012: Information
ETHZ CV2012: Information
zukun
Siwei lyu: natural image statistics
Siwei lyu: natural image statistics
zukun
Lecture9 camera calibration
Lecture9 camera calibration
zukun
Brunelli 2008: template matching techniques in computer vision
Brunelli 2008: template matching techniques in computer vision
zukun
Modern features-part-4-evaluation
Modern features-part-4-evaluation
zukun
Modern features-part-3-software
Modern features-part-3-software
zukun
Modern features-part-2-descriptors
Modern features-part-2-descriptors
zukun
Modern features-part-1-detectors
Modern features-part-1-detectors
zukun
Modern features-part-0-intro
Modern features-part-0-intro
zukun
Lecture 02 internet video search
Lecture 02 internet video search
zukun
Lecture 03 internet video search
Lecture 03 internet video search
zukun
Icml2012 tutorial representation_learning
Icml2012 tutorial representation_learning
zukun
Advances in discrete energy minimisation for computer vision
Advances in discrete energy minimisation for computer vision
zukun
Gephi tutorial: quick start
Gephi tutorial: quick start
zukun
EM algorithm and its application in probabilistic latent semantic analysis
EM algorithm and its application in probabilistic latent semantic analysis
zukun
Object recognition with pictorial structures
Object recognition with pictorial structures
zukun
Iccv2011 learning spatiotemporal graphs of human activities
Iccv2011 learning spatiotemporal graphs of human activities
zukun
Icml2012 learning hierarchies of invariant features
Icml2012 learning hierarchies of invariant features
zukun
Mehr von zukun
(20)
My lyn tutorial 2009
My lyn tutorial 2009
ETHZ CV2012: Tutorial openCV
ETHZ CV2012: Tutorial openCV
ETHZ CV2012: Information
ETHZ CV2012: Information
Siwei lyu: natural image statistics
Siwei lyu: natural image statistics
Lecture9 camera calibration
Lecture9 camera calibration
Brunelli 2008: template matching techniques in computer vision
Brunelli 2008: template matching techniques in computer vision
Modern features-part-4-evaluation
Modern features-part-4-evaluation
Modern features-part-3-software
Modern features-part-3-software
Modern features-part-2-descriptors
Modern features-part-2-descriptors
Modern features-part-1-detectors
Modern features-part-1-detectors
Modern features-part-0-intro
Modern features-part-0-intro
Lecture 02 internet video search
Lecture 02 internet video search
Lecture 03 internet video search
Lecture 03 internet video search
Icml2012 tutorial representation_learning
Icml2012 tutorial representation_learning
Advances in discrete energy minimisation for computer vision
Advances in discrete energy minimisation for computer vision
Gephi tutorial: quick start
Gephi tutorial: quick start
EM algorithm and its application in probabilistic latent semantic analysis
EM algorithm and its application in probabilistic latent semantic analysis
Object recognition with pictorial structures
Object recognition with pictorial structures
Iccv2011 learning spatiotemporal graphs of human activities
Iccv2011 learning spatiotemporal graphs of human activities
Icml2012 learning hierarchies of invariant features
Icml2012 learning hierarchies of invariant features
Kürzlich hochgeladen
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
RankYa
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
UiPathCommunity
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
Fwdays
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
charlottematthew16
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
hariprasad279825
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
charlottematthew16
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
ScyllaDB
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
Mark Billinghurst
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
Stephanie Beckett
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
Alex Barbosa Coqueiro
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
carlostorres15106
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Patryk Bandurski
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
Dubai Multi Commodity Centre
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector Databases
Zilliz
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Mark Simos
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
Mattias Andersson
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Safe Software
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
Padma Pradeep
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache Maven
Hervé Boutemy
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
Enterprise Knowledge
Kürzlich hochgeladen
(20)
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
Powerpoint exploring the locations used in television show Time Clash
Powerpoint exploring the locations used in television show Time Clash
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector Databases
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
DevoxxFR 2024 Reproducible Builds with Apache Maven
DevoxxFR 2024 Reproducible Builds with Apache Maven
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
13 cv mil_preprocessing
1.
Computer vision: models,
learning and inference Chapter 13 Image preprocessing and feature extraction Please send errata to s.prince@cs.ucl.ac.uk
2.
Preprocessing • The goal
of pre-processing is – to try to reduce unwanted variation in image due to lighting, scale, deformation etc. – to reduce data to a manageable size • Give the subsequent model a chance • Preprocessing definition: deterministic transformation to pixels p to create data vector x • Usually heuristics based on experience Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 2
3.
Structure •
Per-pixel transformations • Edges, corners, and interest points • Descriptors • Dimensionality reduction Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 3
4.
Normalization • Fix first
and second moments to standard values • Remove contrast and constant additive luminance variations Before After Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 4
5.
Histogram Equalization Make all
of the moments the same by forcing the histogram of intensities to be the same Before/ normalized/ Histogram Equalized Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 5
6.
Histogram Equalization Computer vision:
models, learning and inference. ©2011 Simon J.D. Prince 6
7.
Convolution Takes pixel image
P and applies a filter F Computes weighted sum of pixel values, where weights given by filter. Easiest to see with a concrete example Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 7
8.
Blurring (convolve with
Gaussian) Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 8
9.
Gradient Filters • Rule
of thumb: big response when image matches filter Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 9
10.
Gabor Filters Computer vision:
models, learning and inference. ©2011 Simon J.D. Prince 10
11.
Haar Filters Computer vision:
models, learning and inference. ©2011 Simon J.D. Prince 11
12.
Local binary patterns Computer
vision: models, learning and inference. ©2011 Simon J.D. Prince 12
13.
Textons • An attempt
to characterize texture • Replace each pixel with integer representing the texture ‘type’ Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 13
14.
Computing Textons Take a
bank of filters and apply Cluster in filter space to lots of images For new pixel, filter surrounding region with same bank, and assign to nearest cluster Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 14
15.
Structure •
Per-pixel transformations • Edges, corners, and interest points • Descriptors • Dimensionality reduction Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 15
16.
Edges
(from Elder and Goldberg 2000) Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 16
17.
Canny Edge Detector Computer
vision: models, learning and inference. ©2011 Simon J.D. Prince 17
18.
Canny Edge Detector Compute
horizontal and vertical gradient images h and v Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 18
19.
Canny Edge Detector
Quantize to 4 directions Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 19
20.
Canny Edge Detector
Non-maximal suppression Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 20
21.
Canny Edge Detector
Hysteresis Thresholding Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 21
22.
Harris Corner Detector Make
decision based on image structure tensor Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 22
23.
SIFT Detector Filter with
difference of Gaussian filters at increasing scales Build image stack (scale space) Find extrema in this 3D volume Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 23
24.
SIFT Detector Identified Corners
Remove those on Remove those edges where contrast is low Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 24
25.
Assign Orientation
Orientation assigned by looking at intensity gradients in region around point Form a histogram of these gradients by binning. Set orientation to peak of histogram. Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 25
26.
Structure •
Per-pixel transformations • Edges, corners, and interest points • Descriptors • Dimensionality reduction Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 26
27.
Sift Descriptor Goal: produce
a vector that describes the region around the interest point. All calculations are relative to the orientation and scale of the keypoint Makes descriptor invariant to rotation and scale Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 27
28.
Sift Descriptor 1. Compute
image gradients 2. Pool into local histograms 3. Concatenate histograms 4. Normalize histograms Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 28
29.
HoG Descriptor Computer vision:
models, learning and inference. ©2011 Simon J.D. Prince 29
30.
Bag of words
descriptor • Compute visual features in image • Compute descriptor around each • Find closest match in library and assign index • Compute histogram of these indices over the region • Dictionary computed using K-means Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 30
31.
Shape context descriptor
Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 31
32.
Structure •
Per-pixel transformations • Edges, corners, and interest points • Descriptors • Dimensionality reduction Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 32
33.
Dimensionality Reduction Dimensionality reduction
attempt to find a low dimensional (or hidden) representation h which can approximately explain the data x so that where is a function that takes the hidden variable and a set of parameters q. Typically, we choose the function family and then learn h and q from training data Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 33
34.
Least Squares Criterion Choose
the parameters q and the hidden variables h so that they minimize the least squares approximation error (a measure of how well they can reconstruct the data x). Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 34
35.
Simple Example Approximate each
data example x with a scalar value h. Data is reconstructed by multiplying h by a parameter f and adding the mean vector m. ... or even better, lets subtract m from each data example to get mean-zero data Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 35
36.
Simple Example Approximate each
data example x with a scalar value h. Data is reconstructed by multiplying h by a factor f. Criterion: Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 36
37.
Criterion Problem: the problem
is non-unique. If we multiply f by any constant a and divide each of the hidden variables h1...I by the same constant we get the same cost. (i.e. (fa) (hi/a) = fhi) Solution: We make the solution unique by constraining the length of f to be 1 using a Lagrange multiplier. Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 37
38.
Criterion Now we have
the new cost function: To optimize this we take derivatives with respect to f and hi, equate the resulting expressions to zero and re-arrange. Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 38
39.
Solution To compute the
hidden value, take dot product with the vector f Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 39
40.
Solution To compute the
hidden value, take dot product with the vector f or where To compute the vector f, compute the first eigenvector of the scatter matrix . Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 40
41.
Computing h To compute
the hidden value, take dot product with the vector f Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 41
42.
Reconstruction To reconstruct, multiply
the hidden variable h by vector f. Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 42
43.
Principal Components Analysis Same
idea, but not the hidden variable h is multi-dimensional. Each components weights one column of matrix F so that data is approximated as This leads to cost function: This has a non-unique optimum so we enforce the constraint that F should be a (truncated) rotation matrix and FTF=I Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 43
44.
PCA Solution To compute
the hidden vector, take dot product with each column of F. To compute the matrix F, compute the first eigenvectors of the scatter matrix . The basis functions in the columns of F are called principal components and the entries of h are called loadings Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 44
45.
Dual PCA Problem: PCA
as described has a major drawback. We need to compute the eigenvectors of the scatter matrix But this has size Dx x Dx. Visual data tends to be very high dimensional, so this may be extremely large. Solution: Reparameterize the principal components as weighted sums of the data ...and solve for the new variables Y. Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 45
46.
Geometric Interpretation Each column
of F can be described as a weighted sum of the original datapoints. Weights given in the corresponding columns of the new variable Y. Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 46
47.
Motivation Solution: Reparameterize the
principal components as weighted sums of the data ...and solve for the new variables Y. Why? If the number of datapoints I is less than the number of observed dimension Dx then the Y will be smaller than F and the resulting optimization becomes easier. Intuition: we are not interested in principal components that are not in the subspace spanned by the data anyway. Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 47
48.
Cost functions Principal components
analysis ...subject to FTF=I. Dual principal components analysis ...subject to FTF=I or YTXTXY=I. Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 48
49.
Solution To compute the
hidden vector, take dot product with each column of F=YX. Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 49
50.
Solution To compute the
hidden vector, take dot product with each column of F=YX. To compute the matrix Y, compute the first eigenvectors of the inner product matrix XTX. The inner product matrix has size I x I. If the number of examples I is less than the dimensionality of the data Dx then this is a smaller eigenproblem. Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 50
51.
K-Means algorithm Approximate data
with a set of means Least squares criterion Alternate minimization Computer vision: models, learning and inference. ©2011 Simon J.D. Prince 51
52.
Computer vision: models,
learning and inference. ©2011 Simon J.D. Prince 52
Jetzt herunterladen