《機器視覺理論、算法與實踐（英文版·第3版）》是機器視覺課程的理想教材，作者清晰、系統地闡述了機器視覺的基本概念，介紹理論的基本元素的同時強調算法和實用設計的約束。書中闡述各個主題時，既闡述了基本算法，又介紹了數學工具。此外，《機器視覺理論、算法與實踐（英文版·第3版）》還使用案例演示具體技術的套用，並闡明設計現實機器視覺系統的關鍵約束。
基本介紹
- 作者：(英國)E.R.Davies
- ISBN：9787115195494
- 定價：128.00 元
- 出版社：人民郵電出版社
- 出版時間：2009
- 開本：16
用途,作者,摘要,目錄,
用途
《機器視覺理論、算法與實踐(英文版·第3版)》適合作為高等院校計算機及電子工程相關專業研究生的教材，更是從事機器視覺、計算機視覺和機器人領域研究的人員不可多得的技術參考書。
作者
E.R.Davies，著名機器視覺專家。英國物理學會會士、IEE會士、英國機器視覺協會的執行委員。畢業於牛津大學，現任倫敦大學皇家霍洛威學院機器視覺教授。在機器視覺、圖像分析、自動視覺檢測、噪聲抑制技術等方面有豐富的教學和科研經驗。
摘要
40年來，機器視覺在各行各業得到了廣泛的套用，包括自動檢測、機器人組裝、行車導引、流量監控、簽名驗證、生物測量、遙感圖像分析等。但是另一方面，面對大量新的研究成果，要充分理解相關的理論和套用，進行算法和系統的設計，卻越來越困難。
《機器視覺理論、算法與實踐(英文版·第3版)》能夠滿足廣大讀者學習和掌握機器視覺知識的需求。全書圖文並茂，清晰、系統地闡述了基本概念，提供了豐富的套用案例和代碼，強調了算法和實用設計的各種約束條件。新版做了全面的更新，反映了最新進展，內容更加全面。《機器視覺理論、算法與實踐(英文版·第3版)》是機器視覺課程的理想教材，已經成為國內外很多名校的指定教學參考書。同時，《機器視覺理論、算法與實踐(英文版·第3版)》也是工程技術人員不可或缺的權威參考書。
目錄
CHAPTER1 Vision,theChallenge
1.1 Introduction-TheSenses 1
1.2 TheNatureofVision 2
1.2.1 TheProcessofRecognition 2
1.2.2 TacklingtheRecognitionProblem 4
1.2.3 ObjectLocation 7
1.2.4 SceneAnalysis 9
1.2.5 VisionasInverseGraphics 10
1.3 FromAutomatedVisualInspectiontoSurveillance 11
1.4 WhatThisBookIsAbout 12
1.5 TheFollowingChapters 14
1.6 BibliographicalNotes 15
PART1 LOW-LEVELVISION 17
CHAPTER2 ImagesandImagingOperations
2.1 Introduction 19
2.1.1 Gray-scaleversusColor 21*
2.2 ImageProcessingOperations 24
2.2.1 SomeBasicOperationsonGray-scaleImages 25
2.2.2 BasicOperationsonBinaryImages 32
2.2.3 NoiseSuppressionbyImageAccumulation 37
2.3 ConvolutionsandPointSpreadFunctions 39
2.4 SequentialversusParallelOperations 41
2.5 ConcludingRemarks 43
2.6 BibliographicalandHistoricalNotes 44
2.7 Problems 44
CHAPTER3 BasicImageFilteringOperations
3.1 Introduction 47
3.2 NoiseSuppressionbyGaussianSmoothing 49
3.3 MedianFilters 51
3.4 ModeFilters 54
3.5 RankOrderFilters 61
3.6 ReducingComputationalLoad 61
3.6.1 ABit-basedMethodforFastMedianFiltering 64
3.7 Sharp-UnsharpMasking 65
3.8 ShiftsIntroducedbyMedianFilters 66
3.8.1 ContinuumModelofMedianShifts 68
3.8.2 GeneralizationtoGray-scaleImages 72
3.8.3 ShiftsArisingwithHybridMedianFilters 75
3.8.4 ProblemswithStatistics 76
3.9 DiscreteModelofMedianShifts 78
3.9.1 GeneralizationtoGray-scaleImages 82
3.10 ShiftsIntroducedbyModeFilters 84
3.11 ShiftsIntroducedbyMeanandGaussianFilters 86
3.12 ShiftsIntroducedbyRankOrderFilters 86
3.12.1 ShiftsinRectangularNeighborhoods 87
3.12.2 CaseofHighCurvature 91
3.12.3 TestoftheModelinaDiscreteCase 91
3.13 TheRoleofFiltersinIndustrialApplicationsofVision 94
3.14 ColorinImageFiltering 94
3.15 ConcludingRemarks 96
3.16 BibliographicalandHistoricalNotes 96
3.17 Problems 98
CHAPTER4 ThresholdingTechniques
4.1 Introduction 103
4.2 Region-growingMethods 104
4.3 Thresholding 105
4.3.1 FindingaSuitableThreshold 105
4.3.2 TacklingtheProblemofBiasinThresholdSelection 107
4.3.3 AConvenientMathematicalModel 111
4.3.4 Summary 114
4.4 AdaptiveThresholding 114
4.4.1 TheChowandKanekoApproach 118
4.4.2 LocalThresholdingMethods 119
4.5 MoreThoroughgoingApproachestoThresholdSelection 122
4.5.1 Variance-basedThresholding 122
4.5.2 Entropy-basedThresholding 123
4.5.3 MaximumLikelihoodThresholding 125
4.6 ConcludingRemarks 126
4.7 BibliographicalandHistoricalNotes 127
4.8 Problems 129
CHAPTER5 EdgeDetection
5.1 Introduction 131
5.2 BasicTheoryofEdgeDetection 132
5.3 TheTemplateMatchingApproach 133
5.4 Theoryof3×3TemplateOperators 135
5.5 Summary-DesignConstraintsandConclusions 140
5.6 TheDesignofDifferentialGradientOperators 141
5.7 TheConceptofaCircularOperator 143
5.8 DetailedImplementationofCircularOperators 144
5.9 StructuredBandsofPixelsinNeighborhoodsofVariousSizes 146
5.10 TheSystematicDesignofDifferentialEdgeOperators 150
5.11 ProblemswiththeaboveApproach-SomeAlternativeSchemes 151
5.12 ConcludingRemarks 155
5.13 BibliographicalandHistoricalNotes 156
5.14 Problems 157
CHAPTER6 BinaryShapeAnalysis
6.1 Introduction 159
6.2 ConnectednessinBinaryImages 160
6.3 ObjectLabelingandCounting 161
6.3.1 SolvingtheLabelingProbleminaMoreComplexCase 164
6.4 MetricPropertiesinDigitalImages 168
6.5 SizeFiltering 169
6.6 TheConvexHullandItsComputation 171
6.7 DistanceFunctionsandTheirUses 177
6.8 SkeletonsandThinning 181
6.8.1 CrossingNumber 183
6.8.2 ParallelandSequentialImplementationsofThinning 186
6.8.3 GuidedThinning 189
6.8.4 ACommentontheNatureoftheSkeleton 189
6.8.5 SkeletonNodeAnalysis 191
6.8.6 ApplicationofSkeletonsforShapeRecognition 192
6.9 SomeSimpleMeasuresforShapeRecognition 193
6.10 ShapeDescriptionbyMoments 194
6.11 BoundaryTrackingProcedures 195
6.12 MoreDetailontheSigmaandChiFunctions 196
6.13 ConcludingRemarks 197
6.14 BibliographicalandHistoricalNotes 199
6.15 Problems 200
CHAPTER7 BoundaryPatternAnalysis
7.1 Introduction 207
7.1.1 HysteresisThresholding 209
7.2 BoundaryTrackingProcedures 212
7.3 TemplateMatching-AReminder 212
7.4 CentroidalProfiles 213
7.5 ProblemswiththeCentroidalProfileApproach 214
7.5.1 SomeSolutions 216
7.6 The(s,ψ)Plot 218
7.7 TacklingtheProblemsofOcclusion 220
7.8 ChainCode 223
7.9 The(r,s)Plot 224
7.10 AccuracyofBoundaryLengthMeasures 225
7.11 ConcludingRemarks 227
7.12 BibliographicalandHistoricalNotes 228
7.13 Problems 229
CHAPTER8 MathematicalMorphology
8.1 Introduction 233
8.2 DilationandErosioninBinaryImages 234
8.2.1 DilationandErosion 234
8.2.2 CancellationEffects 234
8.2.3 ModifiedDilationandErosionOperators 235
8.3 MathematicalMorphology 235
8.3.1 GeneralizedMorphologicalDilation 235
8.3.2 GeneralizedMorphologicalErosion 237
8.3.3 DualitybetweenDilationandErosion 238
8.3.4 PropertiesofDilationandErosionOperators 239
8.3.5 ClosingandOpening 242
8.3.6 SummaryofBasicMorphologicalOperations 245
8.3.7 Hit-and-MissTransform 248
8.3.8 TemplateMatching 249
8.4 Connectivity-basedAnalysisofImages 249
8.4.1 SkeletonsandThinning 250
8.5 Gray-scaleProcessing 251
8.5.1 MorphologicalEdgeEnhancement 252
8.5.2 FurtherRemarksontheGeneralizationtoGray-scaleProcessing 252
8.6 EffectofNoiseonMorphologicalGroupingOperations 255
8.6.1 DetailedAnalysis 257
8.6.2 Discussion 259
8.7 ConcludingRemarks 259
8.8 BibliographicalandHistoricalNotes 260
8.9 Problem 261
PART2 INTERMEDIATE-LEVELVISION 263
CHAPTER9 LineDetection
9.1 Introduction 265
9.2 ApplicationoftheHoughTransformtoLineDetection 265
9.3 TheFoot-of-NormalMethod 269
9.3.1 ErrorAnalysis 272
9.3.2 QualityoftheResultingData 274
9.3.3 ApplicationoftheFoot-of-NormalMethod 276
9.4 LongitudinalLineLocalization 276
9.5 FinalLineFitting 277
9.6 ConcludingRemarks 277
9.7 BibliographicalandHistoricalNotes 278
9.8 Problems 280
CHAPTER10 CircleDetection
10.1 Introduction 283
10.2 Hough-basedSchemesforCircularObjectDetection 284
10.3 TheProblemofUnknownCircleRadius 288
10.3.1 ExperimentalResults 290
10.4 TheProblemofAccurateCenterLocation 295
10.4.1 ObtainingaMethodforReducingComputationalLoad 296
10.4.2 ImprovementsontheBasicScheme 299
10.4.3 Discussion 300
10.4.4 PracticalDetails 300
10.5 OvercomingtheSpeedProblem 302
10.5.1 MoreDetailedEstimatesofSpeed 303
10.5.2 Robustness 305
10.5.3 ExperimentalResults 306
10.5.4 Summary 307
10.6 ConcludingRemarks 310
10.7 BibliographicalandHistoricalNotes 311
10.8 Problems 312
CHAPTER11 TheHoughTransformandItsNature
11.1 Introduction 315
11.2 TheGeneralizedHoughTransform 315
11.3 SettingUptheGeneralizedHoughTransform-SomeRelevantQuestions 317
11.4 SpatialMatchedFilteringinImages 318
11.5 FromSpatialMatchedFilterstoGeneralizedHoughTransforms 319
11.6 GradientWeightingversusUniformWeighting 320
11.6.1 CalculationofSensitivityandComputationalLoad 323
11.7 Summary 324
11.8 ApplyingtheGeneralizedHoughTransformtoLineDetection 325
11.9 TheEffectsofOcclusionsforObjectswithStraightEdges 327
11.10 FastImplementationsoftheHoughTransform 329
11.11 TheApproachofGerigandKlein 332
11.12 ConcludingRemarks 333
11.13 BibliographicalandHistoricalNotes 334
11.14 Problem 337
CHAPTER12 EllipseDetection
12.1 Introduction 339
12.2 TheDiameterBisectionMethod 339
12.3 TheChord-TangentMethod 341
12.4 FindingtheRemainingEllipseParameters 343
12.5 ReducingComputationalLoadfortheGeneralizedHoughTransformMethod 345
12.5.1 PracticalDetails 349
12.6 ComparingtheVariousMethods 353
12.7 ConcludingRemarks 355
12.8 BibliographicalandHistoricalNotes 357
12.9 Problems 358
CHAPTER13 HoleDetection
13.1 Introduction 361
13.2 TheTemplateMatchingApproach 361
13.3 TheLateralHistogramTechnique 363
13.4 TheRemovalofAmbiguitiesintheLateralHistogramTechnique 363
13.4.1 ComputationalImplicationsoftheNeedtoCheckforAmbiguities 364
13.4.2 FurtherDetailoftheSubimageMethod 366
13.5 ApplicationoftheLateralHistogramTechniqueforObjectLocation 368
13.5.1 LimitationsoftheApproach 370
13.6 AppraisaloftheHoleDetectionProblem 372
13.7 ConcludingRemarks 374
13.8 BibliographicalandHistoricalNotes 375
13.9 Problems 376
CHAPTER14 PolygonandCornerDetection
14.1 Introduction 379
14.2 TheGeneralizedHoughTransform 380
14.2.1 StraightEdgeDetection 380
14.3 ApplicationtoPolygonDetection 381
14.3.1 TheCaseofanArbitraryTriangle 382
14.3.2 TheCaseofanArbitraryRectangle 383
14.3.3 LowerBoundsontheNumbersofParameterPlanes 385
14.4 DeterminingPolygonOrientation 387
14.5 WhyCornerDetection? 389
14.6 TemplateMatching 390
14.7 Second-orderDerivativeSchemes 391
14.8 AMedian-Filter-BasedCornerDetector 393
14.8.1 AnalyzingtheOperationoftheMedianDetector 394
14.8.2 PracticalResults 396
14.9 TheHoughTransformApproachtoCornerDetection 399
14.10 ThePlesseyCornerDetector 402
14.11 CornerOrientation 404
14.12 ConcludingRemarks 406
14.13 BibliographicalandHistoricalNotes 407
14.14 Problems 410
CHAPTER15 AbstractPatternMatchingTechniques
15.1 Introduction 413
15.2 AGraph-theoreticApproachtoObjectLocation 414
15.2.1 APracticalExample-LocatingCreamBiscuits 419
15.3 PossibilitiesforSavingComputation 422
15.4 UsingtheGeneralizedHoughTransformforFeatureCollation 424
15.4.1 ComputationalLoad 426
15.5 GeneralizingtheMaximalCliqueandOtherApproaches 427
15.6 RelationalDescriptors 428
15.7 Search 432
15.8 ConcludingRemarks 433
15.9 BibliographicalandHistoricalNotes 434
15.10 Problems 437
PART3 3-DVISIONANDMOTION 443
CHAPTER16 TheThree-dimensionalWorld
16.1 Introduction 445
16.2 Three-DimensionalVision-TheVarietyofMethods 446
16.3 ProjectionSchemesforThree-dimensionalVision 448
16.3.1 BinocularImages 450
16.3.2 TheCorrespondenceProblem 452
16.4 ShapefromShading 454
16.5 PhotometricStereo 459
16.6 TheAssumptionofSurfaceSmoothness 462
16.7 ShapefromTexture 464
16.8 UseofStructuredLighting 464
16.9 Three-DimensionalObjectRecognitionSchemes 466
16.10 TheMethodofBallardandSabbah 468
16.11 TheMethodofSilberbergetal. 470
16.12 Horaud’sJunctionOrientationTechnique 472
16.13 AnImportantParadigm-LocationofIndustrialParts 476
16.14 ConcludingRemarks 478
16.15 BibliographicalandHistoricalNotes 480
16.16 Problems 482
CHAPTER17 TacklingthePerspectiven-PointProblem
17.1 Introduction 487
17.2 ThePhenomenonofPerspectiveInversion 487
17.3 AmbiguityofPoseunderWeakPerspectiveProjection 489
17.4 ObtainingUniqueSolutionstothePoseProblem 493
17.4.1 Solutionofthe 3-PointProblem 497
17.4.2 UsingSymmetricalTrapeziaforEstimatingPose 498
17.5 ConcludingRemarks 498
17.6 BibliographicalandHistoricalNotes 501
17.7 Problems 502
CHAPTER18 Motion
18.1 Introduction 505
18.2 OpticalFlow 505
18.3 InterpretationofOpticalFlowFields 509
18.4 UsingFocusofExpansiontoAvoidCollision 511
18.5 Time-to-AdjacencyAnalysis 513
18.6 BasicDifficultieswiththeOpticalFlowModel 515
18.7 StereofromMotion 516
18.8 ApplicationstotheMonitoringofTrafficFlow 518
18.8.1 TheSystemofBascleetal. 518
18.8.2 TheSystemofKolleretal. 520
18.9 PeopleTracking 524
18.9.1 SomeBasicTechniques 526
18.9.2 Within-vehiclePedestrianTracking 528
18.10 HumanGaitAnalysis 530
18.11 Model-basedTrackingofAnimals-ACaseStudy 533
18.12 Snakes 536
18.13 TheKalmanFilter 538
18.14 ConcludingRemarks 540
18.15 BibliographicalandHistoricalNotes 542
18.16 Problem 543
CHAPTER19 InvariantsandTheirApplications
19.1 Introduction 545
19.2 CrossRatios:The“RatioofRatios”Concept 547
19.3 InvariantsforNoncollinearPoints 552
19.3.1 FurtherRemarksaboutthe 5-PointConfiguration 554
19.4 InvariantsforPointsonConics 556
19.5 DifferentialandSemidifferentialInvariants 560
19.6 SymmetricalCrossRatioFunctions 562
19.7 ConcludingRemarks 564
19.8 BibliographicalandHistoricalNotes 566
19.9 Problems 567
CHAPTER20 EgomotionandRelatedTasks
20.1 Introduction 571
20.2 AutonomousMobileRobots 572
20.3 ActiveVision 573
20.4 VanishingPointDetection 574
20.5 NavigationforAutonomousMobileRobots 576
20.6 ConstructingthePlanViewofGroundPlane 579
20.7 FurtherFactorsInvolvedinMobileRobotNavigation 581
20.8 MoreonVanishingPoints 583
20.9 CentersofCirclesandEllipses 585
20.10 VehicleGuidanceinAgriculture-ACaseStudy 588
20.10.1 3-DAspectsoftheTask 590
20.10.2 Real-timeImplementation 591
20.11 ConcludingRemarks 592
20.12 BibliographicalandHistoricalNotes 592
20.13 Problems 593
CHAPTER21 ImageTransformationsandCameraCalibration
21.1 Introduction 595
21.2 ImageTransformations 596
21.3 CameraCalibration 601
21.4 IntrinsicandExtrinsicParameters 604
21.5 CorrectingforRadialDistortions 607
21.6 Multiple-viewVision 609
21.7 GeneralizedEpipolarGeometry 610
21.8 TheEssentialMatrix 611
21.9 TheFundamentalMatrix 613
21.10 PropertiesoftheEssentialandFundamentalMatrices 614
21.11 EstimatingtheFundamentalMatrix 615
21.12 ImageRectification 616
21.13 3-DReconstruction 617
21.14 AnUpdateonthe 8-PointAlgorithm 619
21.15 ConcludingRemarks 621
21.16 BibliographicalandHistoricalNotes 622
21.17 Problems 623
PART4 TOWARDREAL-TIMEPATTERNRECOGNITIONSYSTEMS 625
CHAPTER22 AutomatedVisualInspection
22.1 Introduction 627
22.2 TheProcessofInspection 628
22.3 ReviewoftheTypesofObjectstoBeInspected 629
22.3.1 FoodProducts 629
22.3.2 PrecisionComponents 630
22.3.3 DifferingRequirementsforSizeMeasurement 630
22.3.4 Three-dimensionalObjects 631
22.3.5 OtherProductsandMaterialsforInspection 632
22.4 Summary-TheMainCategoriesofInspection 632
22.5 ShapeDeviationsRelativetoaStandardTemplate 634
22.6 InspectionofCircularProducts 635
22.6.1 ComputationoftheRadialHistogram:StatisticalProblems 636
22.6.2 ApplicationofRadialHistograms 641
22.7 InspectionofPrintedCircuits 642
22.8 SteelStripandWoodInspection 643
22.9 InspectionofProductswithHighLevelsofVariability 644
22.10 X-rayInspection 648
22.11 TheImportanceofColorinInspection 651
22.12 BringingInspectiontotheFactory 653
22.13 ConcludingRemarks 654
22.14 BibliographicalandHistoricalNotes 656
CHAPTER23 InspectionofCerealGrains
23.1 Introduction 659
23.2 CaseStudy1:LocationofDarkContaminantsinCereals 660
23.2.1 ApplicationofMorphologicalandNonlinearFilterstoLocateRodentDroppings 663
23.2.2 AppraisaloftheVariousSchemas 664
23.2.3 ProblemswithClosing 665
23.3 CaseStudy2:LocationofInsects 665
23.3.1 TheVectorialStrategyforLinearFeatureDetection 666
23.3.2 DesigningLinearFeatureDetectionMasksforLargerWindows 669
23.3.3 ApplicationtoCerealInspection 670
23.3.4 ExperimentalResults 671
23.4 CaseStudy3:High-speedGrainLocation 673
23.4.1 ExtendinganEarlierSamplingApproach 673
23.4.2 ApplicationtoGrainInspection 675
23.4.3 Summary 679
23.5 OptimizingtheOutputforSetsofDirectionalTemplateMasks 680
23.5.1 ApplicationoftheFormulas 682
23.5.2 Discussion 683
23.6 ConcludingRemarks 683
23.7 BibliographicalandHistoricalNotes 684
CHAPTER24 StatisticalPatternRecognition
24.1 Introduction 687
24.2 TheNearestNeighborAlgorithm 688
24.3 Bayes’DecisionTheory 691
24.4 RelationoftheNearestNeighborandBayes’Approaches 693
24.4.1 MathematicalStatementoftheProblem 693
24.4.2 TheImportanceoftheNearestNeighborClassifier 696
24.5 TheOptimumNumberofFeatures 696
24.6 CostFunctionsandError-RejectTradeoff 697
24.7 TheReceiver-OperatorCharacteristic 699
24.8 MultipleClassifiers 702
24.9 ClusterAnalysis 705
24.9.1 SupervisedandUnsupervisedLearning 705
24.9.2 ClusteringProcedures 706
24.10 PrincipalComponentsAnalysis 710
24.11 TheRelevanceofProbabilityinImageAnalysis 713
24.12 TheRoutetoFaceRecognition 715
24.12.1 TheFaceasPartofa 3-DObject 716
24.13 AnotherLookatStatisticalPatternRecognition:TheSupportVectorMachine 719
24.14 ConcludingRemarks 720
24.15 BibliographicalandHistoricalNotes 722
24.16 Problems 723
CHAPTER25 BiologicallyInspiredRecognitionSchemes
25.1 Introduction 725
25.2 ArtificialNeuralNetworks 726
25.3 TheBackpropagationAlgorithm 731
25.4 MLPArchitectures 735
25.5 OverfittingtotheTrainingData 736
25.6 OptimizingtheNetworkArchitecture 739
25.7 HebbianLearning 740
25.8 CaseStudy:NoiseSuppressionUsingANNs 745
25.9 GeneticAlgorithms 750
25.10 ConcludingRemarks 752
25.11 BibliographicalandHistoricalNotes 753
CHAPTER26 Texture
26.1 Introduction 757
26.2 SomeBasicApproachestoTextureAnalysis 763
26.3 Gray-levelCo-occurrenceMatrices 764
26.4 Laws’TextureEnergyApproach 768
26.5 Ade’sEigenfilterApproach 771
26.6 AppraisaloftheLawsandAdeApproaches 772
26.7 Fractal-basedMeasuresofTexture 774
26.8 ShapefromTexture 775
26.9 MarkovRandomFieldModelsofTexture 776
26.10 StructuralApproachestoTextureAnalysis 777
26.11 ConcludingRemarks 777
26.12 BibliographicalandHistoricalNotes 778
CHAPTER27 ImageAcquisition
27.1 Introduction 781
27.2 IlluminationSchemes 782
27.2.1 EliminatingShadows 784
27.2.2 PrinciplesforProducingRegionsofUniformIllumination 787
27.2.3 CaseofTwoInfiniteParallelStripLights 790
27.2.4 OverviewoftheUniformIlluminationScenario 793
27.2.5 UseofLine-scanCameras 794
27.3 CamerasandDigitization 796
27.3.1 Digitization 798
27.4 TheSamplingTheorem 798
27.5 ConcludingRemarks 802
27.6 BibliographicalandHistoricalNotes 803
CHAPTER28 Real-timeHardwareandSystemsDesignConsiderations
28.1 Introduction 805
28.2 ParallelProcessing 806
28.3 SIMDSystems 807
28.4 TheGaininSpeedAttainablewithNProcessors 809
28.5 Flynn’sClassification 810
28.6 OptimalImplementationofanImageAnalysisAlgorithm 813
28.6.1 HardwareSpecificationandDesign 813
28.6.2 BasicIdeasonOptimalHardwareImplementation 814
28.7 SomeUsefulReal-timeHardwareOptions 816
28.8 SystemsDesignConsiderations 818
28.9 DesignofInspectionSystems-TheStatusQuo 818
28.10 SystemOptimization 822
28.11 TheValueofCaseStudies 824
28.12 ConcludingRemarks 825
28.13 BibliographicalandHistoricalNotes 827
28.13.1 GeneralBackground 827
28.13.2 RecentHighlyRelevantWork 829
PART5 PERSPECTIVESONVISION 831
CHAPTER29 MachineVision:ArtorScience?
29.1 Introduction 833
29.2 ParametersofImportanceinMachineVision 834
29.3 Tradeoffs 836
29.3.1 SomeImportantTradeoffs 837
29.3.2 TradeoffsforTwo-stageTemplateMatching 838
29.4 FutureDirections 839
29.5 Hardware,Algorithms,andProcesses 840
29.6 ARetrospectiveView 841
29.7 JustaGlimpseofVision? 842
29.8 BibliographicalandHistoricalNotes 843
APPENDIX RobustStatistics
A.1 Introduction 845
A.2 PreliminaryDefinitionsandAnalysis 848
A.3 TheM-estimator(InfluenceFunction)Approach 850
A.4 TheLeastMedianofSquaresApproachtoRegression 856
A.5 OverviewoftheRobustnessProblem 860
A.6 TheRANSACApproach 861
A.7 ConcludingRemarks 863
A.8 BibliographicalandHistoricalNotes 864
A.9 Problem 865
ListofAcronymsandAbbreviations 867
References 869
AuthorIndex 917
SubjectIndex 925
……
