Computer vision: models, learning, and inference
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Cambridge
Cambridge University Press
2012
|
| Edition: | First published |
| Subjects: | |
| Online Access: | Inhaltsverzeichnis |
| Item Description: | Hier auch später erschienene, unveränderte Nachdrucke |
| Physical Description: | xviii, 580 Seiten Illustrationen, Diagramme |
| ISBN: | 9781107011793 |
Staff View
MARC
| LEADER | 00000nam a2200000 c 4500 | ||
|---|---|---|---|
| 001 | BV040138483 | ||
| 003 | DE-604 | ||
| 005 | 20240410 | ||
| 007 | t| | ||
| 008 | 120516s2012 xx a||| |||| 00||| eng d | ||
| 020 | |a 9781107011793 |c hbk. |9 978-1-107-01179-3 | ||
| 035 | |a (OCoLC)796227311 | ||
| 035 | |a (DE-599)BVBBV040138483 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-20 |a DE-91G |a DE-91 |a DE-706 |a DE-473 |a DE-11 |a DE-1028 |a DE-634 |a DE-355 |a DE-83 | ||
| 084 | |a ST 330 |0 (DE-625)143663: |2 rvk | ||
| 084 | |a ST 300 |0 (DE-625)143650: |2 rvk | ||
| 084 | |a DAT 760f |2 stub | ||
| 100 | 1 | |a Prince, Simon J. D. |d 1972- |e Verfasser |0 (DE-588)1025919769 |4 aut | |
| 245 | 1 | 0 | |a Computer vision |b models, learning, and inference |c Simon J. D. Prince, University College London |
| 250 | |a First published | ||
| 264 | 1 | |a Cambridge |b Cambridge University Press |c 2012 | |
| 300 | |a xviii, 580 Seiten |b Illustrationen, Diagramme | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 500 | |a Hier auch später erschienene, unveränderte Nachdrucke | ||
| 650 | 0 | 7 | |a Statistisches Modell |0 (DE-588)4121722-6 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Sehen |0 (DE-588)4129594-8 |2 gnd |9 rswk-swf |
| 689 | 0 | 0 | |a Maschinelles Sehen |0 (DE-588)4129594-8 |D s |
| 689 | 0 | |5 DE-604 | |
| 689 | 1 | 0 | |a Maschinelles Sehen |0 (DE-588)4129594-8 |D s |
| 689 | 1 | 1 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 1 | 2 | |a Statistisches Modell |0 (DE-588)4121722-6 |D s |
| 689 | 1 | |5 DE-604 | |
| 856 | 4 | 2 | |m Digitalisierung UB Bamberg |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=024995485&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 943 | 1 | |a oai:aleph.bib-bvb.de:BVB01-024995485 | |
Record in the Search Index
| _version_ | 1817681162409082880 |
|---|---|
| adam_text |
Contents
Acknowledgments page
xiii
Foreword by Andrew Fitzgibbon
xv
Preface
xvii
1
Introduction
1
Organization of the book
. 3
Other books
. 5
1 Probability
2
Introduction to probability
9
2.1
Random variables
. 9
2.2
Joint probability
. 10
2.3
Marginalization
. 10
2.4
Conditional probability
. 12
2.5
Bayes'
rule
. 13
2.6
Independence
. 14
2.7
Expectation
. 14
3
Common probability distributions
17
3.1
Bernoulli distribution
. 18
3.2
Beta distribution
. 19
3.3
Categorical distribution
. 19
3.4
Dirichlet distribution
. 20
3.5
Univariate normal distribution
. 21
3.6
Normal-scaled inverse gamma distribution
. 21
3.7
Multivariate normal distribution
. 22
3.8
Normal inverse
Wishart
distribution
. 23
3.9
Conjugacy
. 24
4
Fitting probability models
28
4.1
Maximum likelihood
. 28
4.2
Maximum a posteriori
. 28
4.3
The Bayesian approach
. 29
4.4
Worked example
1:
Univariate normal
. 30
4.5
Worked example
2:
Categorical distribution
. 38
Contents
Will_^_.------------
5 The normal
distribution
44
5.1
Types of covariance matrix
. 44
5.2
Decomposition of covariance
. 45
5.3
Linear transformations of variables
. 47
5.4
Marginai
distributions
. 47
5.5
Conditional distributions
. 48
5.6
Product of two normals
. 48
5.7
Change of variable
. 50
I! Machine learning for machine vision
6
Learning and inference in vision
55
6.1
Computer vision problems
. 55
6.2
Types of model
. 56
6.3
Exampie
1:
Regression
. 57
6.4
Example
2:
Binary classification
. 60
6.5
Which type of model should we use?
. 63
6.6
Applications
. 64
7
Modeling complex data densities
71
7.1
Normal classification model
. 71
7.2
Hidden variables
. 74
7.3
Expectation maximization
.,. 75
7.4
Mixture of Gaussians
. 77
7.5
The
i-distribution
. 82
7.6
Factor analysis
. 88
7.7
Combining modeis
. 93
7.8
Expectation maximization in detail
. 94
7.9
Applications
. 99
8
Regression modeis
108
8.1
Linear regression
. 108
8.2
Bayesian linear regression
.
Ill
8.3
Nonimear regression
. 114
8.4
Kernels and the kernel trick
. 118
8.5
Gaussian process regression
. 119
8.6
Sparse iinear regression
. 120
8.7
Dual linear regression
. 124
8.8
Relevance vector regression
. 127
8.9
Regression to multivariate data
. 128
8.10
Applications
. 128
9
Classification
modets
133
9.1
Logistic regression
. 133
9.2
Bayesian logistic regression
. 138
9.3
Nonlinear logistic regression
. 142
9.4
Dual logistic regression
.
\44
9.5
Kernel logistic regression
. 146
Contents ix
9.6
Relevance vector classification
. 147
9.7
incremental fitting and boosting
. 150
9.8
Classification trees
. 153
9.9
Multiclass logistic regression
. 156
9.10
Random trees, forests, and ferns
. 158
9.11
Relation to non-probabilistic models
. 159
9.12
Applications
. 160
III Connecting local models
10
Graphical models
173
10.1
Conditional independence
. 173
10.2
Directed graphical models
. 175
10.3
Undirected graphical models
. 178
10.4
Comparing directed and undirected graphical models
. 181
10.5
Graphical models in computer vision
. 181
10.6
Inference in models with many unknowns
. 184
10.7
Drawing samples
. 186
10.8
Learning
. 188
11
Models for chains and trees
195
11.1
Models for chains
. 196
11.2
MAP inference for chains
. 198
11.3
MAP inference for trees
. 202
11.4
Marginal posterior inference for chains
. 205
11.5
Marginal posterior inference for trees
. 211
11.6
Learning in chains and trees
. 212
11.7
Beyond chains and trees
. 213
11.8
Applications
. 216
12
Models for grids
227
12.1
Markov random fields
. 228
12.2
MAP inference for binary pairwise MRFs
. 231
12.3
MAP inference for multilabel pairwise MRFs
. 239
12.4
Multilabel MRFs with non-convex potentials
. 244
12.5
Conditional random fields
. 247
12.6
Higher order models
. 250
12.7
Directed models for grids
. 250
12.8
Applications
. 251
IV Preprocessing
13
Image preprocessing and feature extraction
269
13.1
Per-pixe! transformations
. 269
13.2
Edges, corners, and interest points
. 279
13.3
Descriptors
. 283
13.4
Dimensionality reduction
. 287
Contents
V
Models
for geometry
14
The
pinhole
camera
297
14.1
The pinhole camera
. 297
14.2
Three geometric problems
. 304
14.3
Homogeneous coordinates
. 306
14.4
Learning extrinsic parameters
. 309
14.5
Learning intrinsic parameters
. 311
14.6
Inferring three-dimensional world points
. 312
14.7
Applications
. 314
15
Models for transformations
323
15.1
Two-dimensional transformation models
. 323
15.2
Learning in transformation models
. 330
15.3
inference in transformation models
. 334
15.4
Three geometric problems for planes
. 335
15.5
Transformations between images
. 339
15.6
Robust learning of transformations
. 342
15.7
Applications
. 347
16
Multiple cameras
354
16.1
Two-view geometry
. 355
16.2
The essential matrix
. 357
16.3
The fundamental matrix
. 361
16.4
Two-view reconstruction pipeline
. 364
16.5
Rectification
. 368
16.6
Multiview reconstruction
. 372
16.7
Applications
. 376
VI Models for vision
17
Modefs for shape
387
17.1
Shape and its representation
. 388
17.2
Snakes
. 389
17.3
Shape templates
. 393
17.4
Statistical shape models
. 396
17.5
Subspace shape models
. 399
17.6
Three-dimensional shape models
. 405
17.7
Statistical models for shape and appearance
. 405
17.8
Non-Gaussian statistical shape models
. 410
17.9
Articulated models
. 414
17.10
Applications
.
4J5
18
Models for style and identity
424
18.1
Subspace identity model
. 427
18.2
Probabilistic linear discriminant analysis
. 433
18.3
Nonlinear identity models
. 437
18.4
Asymmetric bilinear modefs
. 43g
Contents xi
18.5 Symmetrie bilinear and multilinear modeis. 443
18.6 Applications. 446
19 Temporal modeis 453
19.1 Temporal
estimation
framework.
453
19.2
Kalman filter
. 455
19.3
Extended
Kalman filter
. 466
19.4
Unscented Kalman filter
. 467
19.5
Particle
filtering
. 472
19.6
Applications
. 476
20
Models for visual words
483
20.1
Images as collections of visual words
. 483
20.2
Bag of words
. 484
20.3
Latent Dirichlet allocation
. 487
20.4
Single author—topic model
. 493
20.5
Constellation models
. 495
20.6
Scene models
. 499
20.7
Applications
. 500
VII
Appendices
A Notation
507
В
Optimization
509
B.I Problem statement
. 509
B.2 Choosing a search direction
. 511
B.3 Line search
. 515
B.4 Reparameterization
. 516
С
Linear algebra
519
C.I Vectors
. 519
C.2 Matrices
. 520
C.3 Tensors
. 522
C.4 Linear transformations
. 522
C.5 Singular value decomposition
. 522
C.6 Matrix calculus
. 527
C.7 Common problems
. 528
C.8 Tricks for inverting large matrices
. 530
Bibliography
533
Index
567 |
| any_adam_object | 1 |
| author | Prince, Simon J. D. 1972- |
| author_GND | (DE-588)1025919769 |
| author_facet | Prince, Simon J. D. 1972- |
| author_role | aut |
| author_sort | Prince, Simon J. D. 1972- |
| author_variant | s j d p sjd sjdp |
| building | Verbundindex |
| bvnumber | BV040138483 |
| classification_rvk | ST 330 ST 300 |
| classification_tum | DAT 760f |
| ctrlnum | (OCoLC)796227311 (DE-599)BVBBV040138483 |
| discipline | Informatik |
| edition | First published |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>00000nam a2200000 c 4500</leader><controlfield tag="001">BV040138483</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20240410</controlfield><controlfield tag="007">t|</controlfield><controlfield tag="008">120516s2012 xx a||| |||| 00||| eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781107011793</subfield><subfield code="c">hbk.</subfield><subfield code="9">978-1-107-01179-3</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)796227311</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV040138483</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-20</subfield><subfield code="a">DE-91G</subfield><subfield code="a">DE-91</subfield><subfield code="a">DE-706</subfield><subfield code="a">DE-473</subfield><subfield code="a">DE-11</subfield><subfield code="a">DE-1028</subfield><subfield code="a">DE-634</subfield><subfield code="a">DE-355</subfield><subfield code="a">DE-83</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 330</subfield><subfield code="0">(DE-625)143663:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 300</subfield><subfield code="0">(DE-625)143650:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 760f</subfield><subfield code="2">stub</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Prince, Simon J. D.</subfield><subfield code="d">1972-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)1025919769</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Computer vision</subfield><subfield code="b">models, learning, and inference</subfield><subfield code="c">Simon J. D. Prince, University College London</subfield></datafield><datafield tag="250" ind1=" " ind2=" "><subfield code="a">First published</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Cambridge</subfield><subfield code="b">Cambridge University Press</subfield><subfield code="c">2012</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">xviii, 580 Seiten</subfield><subfield code="b">Illustrationen, Diagramme</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Hier auch später erschienene, unveränderte Nachdrucke</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Statistisches Modell</subfield><subfield code="0">(DE-588)4121722-6</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelles Sehen</subfield><subfield code="0">(DE-588)4129594-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Maschinelles Sehen</subfield><subfield code="0">(DE-588)4129594-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="689" ind1="1" ind2="0"><subfield code="a">Maschinelles Sehen</subfield><subfield code="0">(DE-588)4129594-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2="1"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2="2"><subfield code="a">Statistisches Modell</subfield><subfield code="0">(DE-588)4121722-6</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">Digitalisierung UB Bamberg</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=024995485&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="943" ind1="1" ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-024995485</subfield></datafield></record></collection> |
| id | DE-604.BV040138483 |
| illustrated | Illustrated |
| indexdate | 2024-12-06T09:03:59Z |
| institution | BVB |
| isbn | 9781107011793 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-024995485 |
| oclc_num | 796227311 |
| open_access_boolean | |
| owner | DE-20 DE-91G DE-BY-TUM DE-91 DE-BY-TUM DE-706 DE-473 DE-BY-UBG DE-11 DE-1028 DE-634 DE-355 DE-BY-UBR DE-83 |
| owner_facet | DE-20 DE-91G DE-BY-TUM DE-91 DE-BY-TUM DE-706 DE-473 DE-BY-UBG DE-11 DE-1028 DE-634 DE-355 DE-BY-UBR DE-83 |
| physical | xviii, 580 Seiten Illustrationen, Diagramme |
| publishDate | 2012 |
| publishDateSearch | 2012 |
| publishDateSort | 2012 |
| publisher | Cambridge University Press |
| record_format | marc |
| spelling | Prince, Simon J. D. 1972- Verfasser (DE-588)1025919769 aut Computer vision models, learning, and inference Simon J. D. Prince, University College London First published Cambridge Cambridge University Press 2012 xviii, 580 Seiten Illustrationen, Diagramme txt rdacontent n rdamedia nc rdacarrier Hier auch später erschienene, unveränderte Nachdrucke Statistisches Modell (DE-588)4121722-6 gnd rswk-swf Maschinelles Lernen (DE-588)4193754-5 gnd rswk-swf Maschinelles Sehen (DE-588)4129594-8 gnd rswk-swf Maschinelles Sehen (DE-588)4129594-8 s DE-604 Maschinelles Lernen (DE-588)4193754-5 s Statistisches Modell (DE-588)4121722-6 s Digitalisierung UB Bamberg application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=024995485&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Prince, Simon J. D. 1972- Computer vision models, learning, and inference Statistisches Modell (DE-588)4121722-6 gnd Maschinelles Lernen (DE-588)4193754-5 gnd Maschinelles Sehen (DE-588)4129594-8 gnd |
| subject_GND | (DE-588)4121722-6 (DE-588)4193754-5 (DE-588)4129594-8 |
| title | Computer vision models, learning, and inference |
| title_auth | Computer vision models, learning, and inference |
| title_exact_search | Computer vision models, learning, and inference |
| title_full | Computer vision models, learning, and inference Simon J. D. Prince, University College London |
| title_fullStr | Computer vision models, learning, and inference Simon J. D. Prince, University College London |
| title_full_unstemmed | Computer vision models, learning, and inference Simon J. D. Prince, University College London |
| title_short | Computer vision |
| title_sort | computer vision models learning and inference |
| title_sub | models, learning, and inference |
| topic | Statistisches Modell (DE-588)4121722-6 gnd Maschinelles Lernen (DE-588)4193754-5 gnd Maschinelles Sehen (DE-588)4129594-8 gnd |
| topic_facet | Statistisches Modell Maschinelles Lernen Maschinelles Sehen |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=024995485&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| work_keys_str_mv | AT princesimonjd computervisionmodelslearningandinference |