Muutke küpsiste eelistusi

E-raamat: Computer Vision Metrics: Survey, Taxonomy, and Analysis

  • Formaat: EPUB+DRM
  • Ilmumisaeg: 14-Jun-2014
  • Kirjastus: APress
  • Keel: eng
  • ISBN-13: 9781430259305
Teised raamatud teemal:
  • Formaat - EPUB+DRM
  • Hind: 4,08 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Computer Vision Metrics: Survey, Taxonomy, and AnalysisSuurem pilt
  • Formaat: EPUB+DRM
  • Ilmumisaeg: 14-Jun-2014
  • Kirjastus: APress
  • Keel: eng
  • ISBN-13: 9781430259305
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

Computer Vision Metrics provides an extensive survey and analysis of over 100 current and historical feature description and machine vision methods, with a detailed taxonomy for local, regional and global features. This book provides necessary background to develop intuition about why interest point detectors and feature descriptors actually work, how they are designed, with observations about tuning the methods for achieving robustness and invariance targets for specific applications. The survey is broader than it is deep, with over 540 references provided to dig deeper. The taxonomy includes search methods, spectra components, descriptor representation, shape, distance functions, accuracy, efficiency, robustness and invariance attributes, and more. Rather than providing ‘how-to’ source code examples and shortcuts, this book provides a counterpoint discussion to the many fine opencv community source code resources available for hands-on practitioners.

Muu info

This is an open access book, the electronic versions are freely accessible online.
About the Author xxvii
Acknowledgments xxix
Introduction xxxi
Chapter 1 Image Capture and Representation
1(38)
Image Sensor Technology
1(7)
Sensor Materials
2(1)
Sensor Photo-Diode Cells
3(1)
Sensor Configurations: Mosaic, Foveon, BSI
4(2)
Dynamic Range and Noise
6(1)
Sensor Processing
6(1)
De-Mosaicking
6(1)
Dead Pixel Correction
7(1)
Color and Lighting Corrections
7(1)
Geometric Corrections
7(1)
Cameras and Computational Imaging
8(16)
Overview of Computational Imaging
8(1)
Single-Pixel Computational Cameras
9(1)
2D Computational Cameras
10(2)
3D Depth Camera Systems
12(2)
Binocular Stereo
14(3)
Structured and Coded Light
17(2)
Optical Coding: Diffraction Gratings
19(1)
Time-of-Flight Sensors
20(2)
Array Cameras
22(1)
Radial Cameras
22(1)
Plenoptics: Light Field Cameras
23(1)
3D Depth Processing
24(11)
Overview of Methods
25(1)
Problems in Depth Sensing and Processing
25(1)
The Geometric Field and Distortions
26(1)
The Horopter Region, Panum's Area, and Depth Fusion
26(1)
Cartesian vs. Polar Coordinates: Spherical Projective Geometry
27(1)
Depth Granularity
28(1)
Correspondence
29(1)
Holes and Occlusion
30(1)
Surface Reconstruction and Fusion
30(2)
Noise
32(1)
Monocular Depth Processing
32(1)
Multi-View Stereo
32(1)
Sparse Methods: PTAM
33(1)
Dense Methods: DTAM
34(1)
Optical Flow, SLAM, and SFM
34(1)
3D Representations: Voxels, Depth Maps, Meshes, and Point Clouds
35(2)
Summary
37(2)
Chapter 2 Image Pre-Processing
39(46)
Perspectives on Image Processing
39(1)
Problems to Solve During Image Pre-Processing
40(10)
Vision Pipelines and Image Pre-Processing
40(2)
Corrections
42(1)
Enhancements
43(1)
Preparing Images for Feature Extraction
43(1)
Local Binary Family Pre-Processing
43(2)
Spectra Family Pre-Processing
45(1)
Basis Space Family Pre-Processing
46(1)
Polygon Shape Family Pre-Processing
47(3)
The Taxonomy of Image Processing Methods
50(1)
Point
50(1)
Line
50(1)
Area
51(1)
Algorithmic
51(1)
Data Conversions
51(1)
Colorimetry
51(6)
Overview of Color Management Systems
52(1)
Illuminants, White Point, Black Point, and Neutral Axis
53(1)
Device Color Models
54(1)
Color Spaces and Color Perception
55(1)
Gamut Mapping and Rendering Intent
55(1)
Practical Considerations for Color Enhancements
56(1)
Color Accuracy and Precision
57(1)
Spatial Filtering
57(7)
Convolutional Filtering and Detection
58(2)
Kernel Filtering and Shape Selection
60(1)
Shape Selection or Forming Kernels
61(1)
Point Filtering
61(2)
Noise and Artifact Filtering
63(1)
Integral Images and Box Filters
63(1)
Edge Detectors
64(3)
Kernel Sets: Sobel, Scharr, Prewitt, Roberts, Kirsch, Robinson, and Frei-Chen
64(2)
Canny Detector
66(1)
Transform Filtering, Fourier, and Others
67(4)
Fourier Transform Family
67(1)
Fundamentals
67(3)
Fourier Family of Transforms
70(1)
Other Transforms
70(1)
Morphology and Segmentation
71(6)
Binary Morphology
72(1)
Gray Scale and Color Morphology
73(1)
Morphology Optimizations and Refinements
73(1)
Euclidean Distance Maps
74(1)
Super-Pixel Segmentation
74(1)
Graph-based Super-Pixel Methods
75(1)
Gradient-Ascent-Based Super-Pixel Methods
75(1)
Depth Segmentation
76(1)
Color Segmentation
77(1)
Thresholding
77(6)
Global Thresholding
77(1)
Histogram Peaks and Valleys, and Hysteresis Thresholds
78(1)
LUT Transforms, Contrast Remapping
78(1)
Histogram Equalization and Specification
79(1)
Global Auto Thresholding
80(1)
Local Thresholding
81(1)
Local Histogram Equalization
81(1)
Integral Image Contrast Filters
81(1)
Local Auto Threshold Methods
82(1)
Summary
83(2)
Chapter 3 Global and Regional Features
85(46)
Historical Survey of Features
85(8)
Key Ideas: Global, Regional, and Local
86(1)
1960s, 1970s, 1980s---Whole-Object Approaches
87(1)
Early 1990s---Partial-Object Approaches
87(1)
Mid-1990s---Local Feature Approaches
87(1)
Late 1990s---Classified Invariant Local Feature Approaches
88(1)
Early 2000s---Scene and Object Modeling Approaches
88(1)
Mid-2000s---Finer-Grain Feature and Metric Composition Approaches
88(1)
Post-2010---Multi-Modal Feature Metrics Fusion
88(1)
Textural Analysis
89(1)
1950s thru 1970s---Global Uniform Texture Metrics
90(1)
1980s---Structural and Model-Based Approaches for Texture Classification
91(1)
1990s---Optimizations and Refinements to Texture Metrics
91(1)
2000 to Today---More Robust Invariant Texture Metrics and 3D Texture
92(1)
Statistical Methods
92(1)
Texture Region Metrics
93(16)
Edge Metrics
93(1)
Edge Density
94(1)
Edge Contrast
94(1)
Edge Entropy
94(1)
Edge Directivity
95(1)
Edge Linearity
95(1)
Edge Periodicity
95(1)
Edge Size
95(1)
Edge Primitive Length Total
96(1)
Cross-Correlation and Auto-Correlation
96(1)
Fourier Spectrum, Wavelets, and Basis Signatures
96(1)
Co-Occurrence Matrix, Haralick Features
97(3)
Extended SDM Metrics
100(1)
Metric 1 Centroid
101(1)
Metric 2 Total Coverage
101(1)
Metric 3 Low-Frequency Coverage
102(1)
Metric 4 Corrected Coverage
102(1)
Metric 5 Total Power
102(1)
Metric 6 Relative Power
103(1)
Metric 7 Locus Mean Density
103(1)
Metric 8 Locus Length
103(1)
Metric 9 Bin Mean Density
104(1)
Metric 10 Containment
104(1)
Metric 11 Linearity
104(2)
Metric 12 Linearity Strength
106(1)
Laws Texture Metrics
106(2)
LBP Local Binary Patterns
108(1)
Dynamic Textures
108(1)
Statistical Region Metrics
109(9)
Image Moment Features
109(1)
Point Metric Features
110(2)
Global Histograms
112(1)
Local Region Histograms
113(1)
Scatter Diagrams, 3D Histograms
113(4)
Multi-Resolution, Multi-Scale Histograms
117(1)
Radial Histograms
118(1)
Contour or Edge Histograms
118(1)
Basis Space Metrics
118(11)
Fourier Description
121(1)
Walsh-Hadamard Transform
122(1)
HAAR Transform
123(1)
Slant Transform
123(1)
Zernike Polynomials
124(1)
Steerable Filters
124(1)
Karhunen-Loeve Transform and Hotelling Transform
125(1)
Wavelet Transform and Gabor Filters
125(2)
Gabor Functions
127(1)
Hough Transform and Radon Transform
127(2)
Summary
129(2)
Chapter 4 Local Feature Design Concepts, Classification, and Learning
131(60)
Local Features
132(2)
Detectors, Interest Points, Keypoints, Anchor Points, Landmarks
132(1)
Descriptors, Feature Description, Feature Extraction
133(1)
Sparse Local Pattern Methods
133(1)
Local Feature Attributes
134(4)
Choosing Feature Descriptors and Interest Points
134(1)
Feature Descriptors and Feature Matching
134(1)
Criteria for Goodness
134(2)
Repeatability, Easy vs. Hard to Find
136(1)
Distinctive vs. Indistinctive
137(1)
Relative and Absolute Position
137(1)
Matching Cost and Correspondence
137(1)
Distance Functions
138(6)
Early Work on Distance Functions
138(1)
Euclidean or Cartesian Distance Metrics
139(1)
Euclidean Distance
139(1)
Squared Euclidean Distance
140(1)
Cosine Distance or Similarity
140(1)
Sum of Absolute Differences (SAD) or L1 Norm
140(1)
Sum of Squared Differences (SSD) or L2 Norm
140(1)
Correlation Distance
141(1)
Hellinger Distance
141(1)
Grid Distance Metrics
141(1)
Manhattan Distance
141(1)
Chebyshev Distance
142(1)
Statistical Difference Metrics
142(1)
Earth Movers Distance (EMD) or Wasserstein Metric
142(1)
Mahalanobis Distance
143(1)
Bray Curtis Distance
143(1)
Canberra Distance
143(1)
Binary or Boolean Distance Metrics
143(1)
LO Norm
143(1)
Hamming Distance
144(1)
Jaccard Similarity and Dissimilarity
144(1)
Descriptor Representation
144(3)
Coordinate Spaces, Complex Spaces
144(1)
Cartesian Coordinates
145(1)
Polar and Log Polar Coordinates
145(1)
Radial Coordinates
145(1)
Spherical Coordinates
146(1)
Gauge Coordinates
146(1)
Multivariate Spaces, Multimodal Data
146(1)
Feature Pyramids
147(1)
Descriptor Density
147(2)
Interest Point and Descriptor Culling
147(1)
Dense vs. Sparse Feature Description
148(1)
Descriptor Shape Topologies
149(4)
Correlation Templates
149(1)
Patches and Shape
149(1)
Single Patches, Sub-Patches
149(1)
Deformable Patches
149(1)
Multi-Patch Sets
150(1)
TPLBP, FPLBP
150(1)
Strip and Radial Fan Shapes
151(1)
D-NETS Strip Patterns
151(1)
Object Polygon Shapes
152(1)
Morphological Boundary Shapes
152(1)
Texture Structure Shapes
153(1)
Super-Pixel Similarity Shapes
153(1)
Local Binary Descriptor Point-Pair Patterns
153(4)
FREAK Retinal Patterns
154(1)
Brisk Patterns
155(1)
ORB and BRIEF Patterns
156(1)
Descriptor Discrimination
157(9)
Spectra Discrimination
158(1)
Region, Shapes, and Pattern Discrimination
159(1)
Geometric Discrimination Factors
160(1)
Feature Visualization to Evaluate Discrimination
160(1)
Discrimination via Image Reconstruction from HOG
160(1)
Discrimination via Image Reconstruction from Local Binary Patterns
161(1)
Discrimination via Image Reconstruction from SIFT Features
162(1)
Accuracy, Trackability
163(2)
Accuracy Optimizations, Sub-Region Overlap, Gaussian Weighting, and Pooling
165(1)
Sub-Pixel Accuracy
165(1)
Search Strategies and Optimizations
166(6)
Dense Search
166(1)
Grid Search
166(1)
Multi-Scale Pyramid Search
167(1)
Scale Space and Image Pyramids
168(1)
Feature Pyramids
169(1)
Sparse Predictive Search and Tracking
170(1)
Tracking Region-Limited Search
170(1)
Segmentation Limited Search
171(1)
Depth or Z Limited Search
171(1)
Computer Vision, Models, Organization
172(16)
Feature Space
172(1)
Object Models
173(2)
Constraints
175(1)
Selection of Detectors and Features
175(1)
Manually Designed Feature Detectors
175(1)
Statistically Designed Feature Detectors
175(1)
Learned Features
176(1)
Overview of Training
176(1)
Classification of Features and Objects
177(1)
Group Distance: Clustering, Training, and Statistical Learning
177(1)
Group Distance: Clustering Methods Survey, KNN, RANSAC, K-Means, GMM, SVM, Others
178(2)
Classification Frameworks, REIN, MOPED
180(1)
Kernel Machines
181(1)
Boosting, Weighting
181(1)
Selected Examples of Classification
182(1)
Feature Learning, Sparse Coding, Convolutional Networks
183(1)
Terminology: Codebooks, Visual Vocabulary, Bag of Words, Bag of Features
183(1)
Sparse Coding
184(1)
Visual Vocabularies
185(1)
Learned Detectors via Convolutional Filter Masks
186(1)
Convolutional Neural Networks, Neural Networks
186(2)
Deep Learning, Pooling, Trainable Feature Hierarchies
188(1)
Summary
188(3)
Chapter 5 Taxonomy of Feature Description Attributes
191(26)
Feature Descriptor Families
192(1)
Prior Work on Computer Vision Taxonomies
193(1)
Robustness and Accuracy
194(1)
General Robustness Taxonomy
195(4)
Illumination
196(1)
Color Criteria
196(1)
Incompleteness
197(1)
Resolution and Accuracy
197(1)
Geometric Distortion
198(1)
Efficiency Variables, Costs and Benefits
199(1)
Discrimination and Uniqueness
199(1)
General Vision Metrics Taxonomy
199(13)
Feature Descriptor Family
201(1)
Spectra Dimensions
201(1)
Spectra Type
201(4)
Interest Point
205(1)
Storage Formats
206(1)
Data Types
206(1)
Descriptor Memory
207(1)
Feature Shapes
207(1)
Feature Pattern
207(1)
Feature Density
208(1)
Feature Search Methods
209(1)
Pattern Pair Sampling
210(1)
Pattern Region Size
211(1)
Distance Function
211(1)
Euclidean or Cartesian Distance Family
211(1)
Grid Distance Family
212(1)
Statistical Distance Family
212(1)
Binary or Boolean Distance Family
212(1)
Feature Metric Evaluation
212(4)
Efficiency Variables, Costs and Benefits
213(1)
Image Reconstruction Efficiency Metric
213(1)
Example Feature Metric Evaluations
213(1)
SIFT Example
213(1)
Vision Metric Taxonomy FME
214(1)
General Robustness Attributes
214(1)
LBP Example
214(1)
Vision Metric Taxonomy FME
214(1)
General Robustness Attributes
215(1)
Shape Factors Example
215(1)
Vision Metric Taxonomy FME
215(1)
General Robustness Attributes
216(1)
Summary
216(1)
Chapter 6 Interest Point Detector and Feature Descriptor Survey
217(66)
Interest Point Tuning
218(1)
Interest Point Concepts
218(3)
Interest Point Method Survey
221(6)
Laplacian and Laplacian of Gaussian
222(1)
Moravac Corner Detector
222(1)
Harris Methods, Harris-Stephens, Shi-Tomasi, and Hessian-Type Detectors
222(1)
Hessian Matrix Detector and Hessian-Laplace
223(1)
Difference of Gaussians
223(1)
Salient Regions
224(1)
SUSAN, and Trajkovic and Hedly
224(1)
Fast, Faster, AGHAST
225(1)
Local Curvature Methods
226(1)
Morphological Interest Regions
227(1)
Feature Descriptor Survey
227(14)
Local Binary Descriptors
228(1)
Local Binary Patterns
228(3)
Neighborhood Comparison
231(1)
Histogram Composition
231(1)
Optionally Normalization
232(1)
Descriptor Concatenation
232(1)
Rotation Invariant LBP (RILBP)
232(1)
Dynamic Texture Metric Using 3D LBPs
233(1)
Volume LBP (VLBP)
233(1)
LPB-TOP
234(1)
Other LBP Variants
234(3)
Census
237(1)
Modified Census Transform
237(1)
BRIEF
238(1)
ORB
238(1)
BRISK
239(1)
FREAK
240(1)
Spectra Descriptors
241(28)
SIFT
241(1)
Create a Scale Space Pyramid
242(2)
Identify Scale-Invariant Interest Points
244(1)
Create Feature Descriptors
244(2)
SIFT-PCA
246(1)
SIFT-GLOH
246(1)
SIFT-SIFER Retrofit
247(1)
SIFT CS-LBP Retrofit
247(1)
RootSIFT Retrofit
248(1)
CenSurE and STAR
249(2)
Correlation Templates
251(1)
HAAR Features
252(2)
Viola Jones with HAAR-Like Features
254(1)
SURF
254(2)
Variations on SURF
256(1)
Histogram of Gradients (HOG) and Variants
257(1)
PHOG and Related Methods
258(2)
Daisy and O-Daisy
260(1)
CARD
261(2)
Robust Fast Feature Matching
263(1)
RIFF, CHOG
264(2)
Chain Code Histograms
266(1)
D-NETS
266(1)
Local Gradient Pattern
267(1)
Local Phase Quantization
268(1)
Basis Space Descriptors
269(3)
Fourier Descriptors
269(2)
Other Basis Functions for Descriptor Building
271(1)
Sparse Coding Methods
271(1)
Examples of Sparse Coding Methods
271(1)
Polygon Shape Descriptors
272(6)
MSER Method
273(1)
Object Shape Metrics for Blobs and Polygons
274(3)
Shape Context
277(1)
3D, 4D, Volumetric, and Multimodal Descriptors
278(4)
3D HOG
279(1)
HON 4D
280(1)
3D SIFT
280(2)
Summary
282(1)
Chapter 7 Ground Truth Data, Content, Metrics, and Analysis
283(30)
What Is Ground Truth Data?
284(2)
Previous Work on Ground Truth Data: Art vs. Science
286(3)
General Measures of Quality Performance
286(1)
Measures of Algorithm Performance
286(1)
Rosin's Work on Corners
287(2)
Key Questions For Constructing Ground Truth Data
289(5)
Content: Adopt, Modify, or Create
289(1)
Survey Of Available Ground Truth Data
289(1)
Fitting Data to Algorithms
290(1)
Scene Composition and Labeling
291(1)
Composition
292(1)
Labeling
293(1)
Defining the Goals and Expectations
294(2)
Mikolajczyk and Schmid Methodology
295(1)
Open Rating Systems
295(1)
Corner Cases and Limits
295(1)
Interest Points and Features
295(1)
Robustness Criteria for Ground Truth Data
296(4)
Illustrated Robustness Criteria
296(3)
Using Robustness Criteria for Real Applications
299(1)
Pairing Metrics with Ground Truth
300(3)
Pairing and Tuning Interest Points, Features, and Ground Truth
301(1)
Examples Using The General Vision Taxonomy
301(2)
Synthetic Feature Alphabets
303(7)
Goals for the Synthetic Dataset
304(1)
Accuracy of Feature Detection via Location Grid
305(1)
Rotational Invariance via Rotated Image Set
305(1)
Scale Invariance via Thickness and Bounding Box Size
305(1)
Noise and Blur Invariance
305(1)
Repeatabilty
306(1)
Real Image Overlays of Synthetic Features
306(1)
Synthetic Interest Point Alphabet
306(1)
Synthetic Corner Alphabet
307(2)
Hybrid Synthetic Overlays on Real Images
309(1)
Method for Creating the Overlays
310(1)
Summary
310(3)
Chapter 8 Vision Pipelines and Optimizations
313(52)
Stages, Operations, and Resources
314(1)
Compute Resource Budgets
315(8)
Compute Units, ALUs, and Accelerators
317(1)
Power Use
318(1)
Memory Use
319(3)
I/O Performance
322(1)
The Vision Pipeline Examples
323(27)
Automobile Recognition
323(2)
Segmenting the Automobiles
325(1)
Matching the Paint Color
326(1)
Measuring the Automobile Size and Shape
326(1)
Feature Descriptors
327(1)
Calibration, Set-up, and Ground Truth Data
328(1)
Pipeline Stages and Operations
329(1)
Operations and Compute Resources
330(1)
Criteria for Resource Assignments
330(1)
Face, Emotion, and Age Recognition
331(2)
Calibration and Ground Truth Data
333(1)
Interest Point Position Prediction
334(1)
Segmenting the Head and Face Using the Bounding Box
335(1)
Face Landmark Identification and Compute Features
336(2)
Pipeline Stages and Operations
338(1)
Operations and Compute Resources
339(1)
Criteria for Resource Assignments
339(1)
Image Classification
340(1)
Segmenting Images and Feature Descriptors
341(2)
Pipeline Stages and Operations
343(1)
Mapping Operations to Resources
343(1)
Criteria for Resource Assignments
344(1)
Augmented Reality
345(1)
Calibration and Ground Truth Data
346(1)
Feature and Object Description
346(1)
Overlays and Tracking
347(1)
Pipeline Stages and Operations
348(1)
Mapping Operations to Resources
348(1)
Criteria for Resource Assignments
349(1)
Acceleration Alternatives
350(8)
Memory Optimizations
351(1)
Minimizing Memory Transfers Between Compute Units
351(1)
Memory Tiling
352(1)
DMA, Data Copy, and Conversions
352(1)
Register Files, Memory Caching, and Pinning
352(1)
Data Structures, Packing, and Vector vs. Scatter-Gather Data Organization
353(1)
Coarse-Grain Parallelism
353(1)
Compute-Centric vs. Data-Centric
353(1)
Threads and Multiple Cores
354(1)
Fine-Grain Data Parallelism
354(1)
SIMD, SIMT, and SPMD Fundamentals
355(1)
Shader Kernel Languages and GPGPU
356(1)
Advanced Instruction Sets and Accelerators
357(1)
Vision Algorithm Optimizations and Tuning
358(4)
Compiler And Manual Optimizations
359(1)
Tuning
360(1)
Feature Descriptor Retrofit, Detectors, Distance Functions
360(1)
Boxlets and Convolution Acceleration
361(1)
Data-Type Optimizations, Integer vs. Float
361(1)
Optimization Resources
362(1)
Summary
363(2)
Appendix A Synthetic Feature Analysis
365(36)
Background Goals and Expectations
366(2)
Test Methodology and Results
368(2)
Detector Parameters Are Not Tuned for the Synthetic Alphabets
369(1)
Expectations for Test Results
370(1)
Summary of Synthetic Alphabet Ground Truth Images
370(2)
Synthetic Interest Point Alphabet
371(1)
Synthetic Corner Point Alphabet
371(1)
Synthetic Alphabet Overlays
371(1)
Test 1 Synthetic Interest Point Alphabet Detection
372(11)
Annotated Synthetic Interest Point Detector Results
374(1)
Entire Images Available Online
375(8)
Test 2 Synthetic Corner Point Alphabet Detection
383(10)
Annotated Synthetic Corner Point Detector Results
384(1)
Entire Images Available Online
384(9)
Test 3 Synthetic Alphabets Overlaid on Real Images
393(1)
Annotated Detector Results on Overlay Images
393(1)
Test 4 Rotational Invariance for Each Alphabet
394(4)
Methodology for Determining Rotational Invariance
394(4)
Analysis of Results and Non-Repeatability Anomalies
398(3)
Caveats
398(1)
Non-Repeatability in Tests 1 and 2
399(1)
Other Non-Repeatability in Test 3
400(1)
Test Summary
400(1)
Future Work
400(1)
Appendix B Survey of Ground Truth Datasets
401(10)
Appendix C Imaging and Computer Vision Resources
411(8)
Commercial Products
411(1)
Open Source
412(3)
Organizations, Institutions, and Standards
415(2)
Journals and Their Abbreviations
417(1)
Conferences and Their Abbreviations
417(1)
Online Resources
418(1)
Appendix D Extended SDM Metrics
419(18)
Bibliography 437(28)
Index 465
Scott Krig is a pioneer in computer imaging, computer vision, and graphics visualization. He founded Krig Research in 1988 (krigresearch.com), providing the worlds first imaging and vision systems based onhigh-performance engineering workstations, super-computers, and dedicated imaging hardware, serving customers worldwide in 25 countries. Scott has provided imaging and vision solutions around the globe, and has worked closely with many industries, including aerospace, military, intelligence, law enforcement, government research, and academic organizations.More recently, Scott has worked for major corporations and startups serving commercial markets, solving problems in the areas of computer vision, imaging, graphics, visualization, robotics, process control, industrial automation, computer security, cryptography, and consumer applications of imaging and machine vision to PCs, laptops, mobile phones, and tablets. Most recently, Scott provided direction for Intel Corporation in the area of depth-sensing and computer vision methods for embedded systems and mobile platforms.Scott is the author of many patent applications worldwide in the areas of embedded systems, imaging, computer vision, DRM, and computer security, and studied at Stanford.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97814302593056e.html
Märksõnad: