《机器视觉理论、算法与实践（英文版·第3版）》是机器视觉课程的理想教材，作者清晰、系统地阐述了机器视觉的基本概念，介绍理论的基本元素的同时强调算法和实用设计的约束。书中阐述各个主题时，既阐述了基本算法，又介绍了数学工具。此外，本书还使用案例演示具体技术的应用，并阐明设计现实机器视觉系统的关键约束。
《机器视觉理论、算法与实践（英文版·第3版）》适合作为高等院校计算机及电子工程相关专业研究生的教材，更是从事机器视觉、计算机视觉和机器人领域研究的人员不可多得的技术参考书。
E.R.Davies，著名机器视觉专家。英国物理学会会士、IEE会士、英国机器视觉协会的执行委员。毕业于牛津大学，现任伦敦大学皇家霍洛威学院机器视觉教授。在机器视觉、图像分析、自动视觉检测、噪声抑制技术等方面有丰富的教学和科研经验。
CHAPTER 1 Vision，theChallenge
n1.1 Introduction-TheSenses
n1.2 TheNatureofVision
n1.2.1 TheProcessofRecognition
n1.2.2 TacklingtheRecognitionProblem
n1.2.3 ObjectLocation
n1.2.4 SceneAnalysis
n1.2.5 VisionasInverseGraphics
n1.3 FromAutomatedVisualInspectiontoSurveillance
n1.4 WhatThisBookIsAbout
n1.5 TheFollowingChapters
n1.6 BibliographicalNotes
n
nPART1LOW-LEVELVISION
nCHAPTER 2 ImagesandImagingOperations
n2.1 Introduction
n2.1.1 Gray-scaleversusColor21*
n2.2 ImageProcessingOperations
n2.2.1 SomeBasicOperationsonGray-scaleImages
n2.2.2 BasicOperationsonBinaryImages
n2.2.3 NoiseSuppressionbyImageAccumulation
n2.3 ConvolutionsandPointSpreadFunctions
n2.4 SequentialversusParallelOperations
n2.5 ConcludingRemarks
n2.6 BibliographicalandHistoricalNotes
n2.7 Problems
n
nCHAPTER 3 BasicImageFilteringOperations
n3.1 Introduction
n3.2 NoiseSuppressionbyGaussianSmoothing
n3.3 MedianFilters
n3.4 ModeFilters
n3.5 RankOrderFilters
n3.6 ReducingComputationalLoad
n3.6.1 ABit-basedMethodforFastMedianFiltering
n3.7 Sharp-UnsharpMasking
n3.8 ShiftsIntroducedbyMedianFilters
n3.8.1 ContinuumModelofMedianShifts
n3.8.2 GeneralizationtoGray-scaleImages
n3.8.3 ShiftsArisingwithHybridMedianFilters
n3.8.4 ProblemswithStatistics
n3.9 DiscreteModelofMedianShifts
n3.9.1 GeneralizationtoGray-scaleImages
n3.10 ShiftsIntroducedbyModeFilters
n3.11 ShiftsIntroducedbyMeanandGaussianFilters
n3.12 ShiftsIntroducedbyRankOrderFilters
n3.12.1 ShiftsinRectangularNeighborhoods
n3.12.2 CaseofHighCurvature
n3.12.3 TestoftheModelinaDiscreteCase
n3.13 TheRoleofFiltersinIndustrialApplicationsofVision
n3.14 ColorinImageFiltering
n3.15 ConcludingRemarks
n3.16 BibliographicalandHistoricalNotes
n3.17 Problems
n
nCHAPTER 4 ThresholdingTechniques
n4.1 Introduction
n4.2 Region-growingMethods
n4.3 Thresholding
n4.3.1 FindingaSuitableThreshold
n4.3.2 TacklingtheProblemofBiasinThresholdSelection
n4.3.3 AConvenientMathematicalModel
n4.3.4 Summary
n4.4 AdaptiveThresholding
n4.4.1 TheChowandKanekoApproach
n4.4.2 LocalThresholdingMethods
n4.5 MoreThoroughgoingApproachestoThresholdSelection
n4.5.1 Variance-basedThresholding
n4.5.2 Entropy-basedThresholding
n4.5.3 MaximumLikelihoodThresholding
n4.6 ConcludingRemarks
n4.7 BibliographicalandHistoricalNotes
n4.8 Problems
n
nCHAPTER 5 EdgeDetection
n5.1 Introduction
n5.2 BasicTheoryofEdgeDetection
n5.3 TheTemplateMatchingApproach
n5.4 Theoryof3×3TemplateOperators
n5.5 Summary-DesignConstraintsandConclusions
n5.6 TheDesignofDifferentialGradientOperators
n5.7 TheConceptofaCircularOperator
n5.8 DetailedImplementationofCircularOperators
n5.9 StructuredBandsofPixelsinNeighborhoodsofVariousSizes
n5.10 TheSystematicDesignofDifferentialEdgeOperators
n5.11 ProblemswiththeaboveApproach-SomeAlternativeSchemes
n5.12 ConcludingRemarks
n5.13 BibliographicalandHistoricalNotes
n5.14 Problems
n
nCHAPTER 6 BinaryShapeAnalysis
n6.1 Introduction
n6.2 ConnectednessinBinaryImages
n6.3 ObjectLabelingandCounting
n6.3.1 SolvingtheLabelingProbleminaMoreComplexCase
n6.4 MetricPropertiesinDigitalImages
n6.5 SizeFiltering
n6.6 TheConvexHullandItsComputation
n6.7 DistanceFunctionsandTheirUses
n6.8 SkeletonsandThinning
n6.8.1 CrossingNumber
n6.8.2 ParallelandSequentialImplementationsofThinning
n6.8.3 GuidedThinning
n6.8.4 ACommentontheNatureoftheSkeleton
n6.8.5 SkeletonNodeAnalysis
n6.8.6 ApplicationofSkeletonsforShapeRecognition
n6.9 SomeSimpleMeasuresforShapeRecognition
n6.10 ShapeDescriptionbyMoments
n6.11 BoundaryTrackingProcedures
n6.12 MoreDetailontheSigmaandChiFunctions
n6.13 ConcludingRemarks
n6.14 BibliographicalandHistoricalNotes
n6.15 Problems
n
nCHAPTER 7 BoundaryPatternAnalysis
n7.1 Introduction
n7.1.1 HysteresisThresholding
n7.2 BoundaryTrackingProcedures
n7.3 TemplateMatching-AReminder
n7.4 CentroidalProfiles
n7.5 ProblemswiththeCentroidalProfileApproach
n7.5.1 SomeSolutions
n7.6 The（s，）Plot
n7.7 TacklingtheProblemsofOcclusion
n7.8 ChainCode
n7.9 The（r，s）Plot
n7.1 0AccuracyofBoundaryLengthMeasures
n7.1 1ConcludingRemarks
n7.1 2BibliographicalandHistoricalNotes
n7.1 3Problems
n
nCHAPTER 8 MathematicalMorphology
n8.1 Introduction
n8.2 DilationandErosioninBinaryImages
n8.2.1 DilationandErosion
n8.2.2 CancellationEffects
n8.2.3 ModifiedDilationandErosionOperators
n8.3 MathematicalMorphology
n8.3.1 GeneralizedMorphologicalDilation
n8.3.2 GeneralizedMorphologicalErosion
n8.3.3 DualitybetweenDilationandErosion
n8.3.4 PropertiesofDilationandErosionOperators
n8.3.5 ClosingandOpening
n8.3.6 SummaryofBasicMorphologicalOperations
n8.3.7 Hit-and-MissTransform
n8.3.8 TemplateMatching
n8.4 Connectivity-basedAnalysisofImages
n8.4.1 SkeletonsandThinning
n8.5 Gray-scaleProcessing
n8.5.1 MorphologicalEdgeEnhancement
n8.5.2 FurtherRemarksontheGeneralizationtoGray-scaleProcessing
n8.6 EffectofNoiseonMorphologicalGroupingOperations
n8.6.1 DetailedAnalysis
n8.6.2 Discussion
n8.7 ConcludingRemarks
n8.8 BibliographicalandHistoricalNotes
n8.9 Problem
n
nPART 2 INTERMEDIATE-LEVELVISION
nCHAPTER 9 LineDetection
n9.1 Introduction
n9.2 ApplicationoftheHoughTransformtoLineDetection
n9.3 TheFoot-of-NormalMethod
n9.3.1 ErrorAnalysis
n9.3.2 QualityoftheResultingData
n9.3.3 ApplicationoftheFoot-of-NormalMethod
n9.4 LongitudinalLineLocalization
n9.5 FinalLineFitting
n9.6 ConcludingRemarks
n9.7 BibliographicalandHistoricalNotes
n9.8 Problems
n
nCHAPTER 10 CircleDetection
n10.1 Introduction
n10.2 Hough-basedSchemesforCircularObjectDetection
n10.3 TheProblemofUnknownCircleRadius
n10.3.1 ExperimentalResults
n10.4 TheProblemofAccurateCenterLocation
n10.4.1 ObtainingaMethodforReducingComputationalLoad
n10.4.2 ImprovementsontheBasicScheme
n10.4.3 Discussion
n10.4.4 PracticalDetails
n10.5 OvercomingtheSpeedProblem
n10.5.1 MoreDetailedEstimatesofSpeed
n10.5.2 Robustness
n10.5.3 ExperimentalResults
n10.5.4 Summary
n10.6 ConcludingRemarks
n10.7 BibliographicalandHistoricalNotes
n10.8 Problems
n
nCHAPTER 11 TheHoughTransformandItsNature
n11.1 Introduction
n11.2 TheGeneralizedHoughTransform
n11.3 SettingUptheGeneralizedHoughTransform-SomeRelevantQuestions
n11.4 SpatialMatchedFilteringinImages
n11.5 FromSpatialMatchedFilterstoGeneralizedHoughTransforms
n11.6 GradientWeightingversusUniformWeighting
n11.6.1 CalculationofSensitivityandComputationalLoad
n11.7 Summary
n11.8 ApplyingtheGeneralizedHoughTransformtoLineDetection
n11.9 TheEffectsofOcclusionsforObjectswithStraightEdges
n11.10 FastImplementationsoftheHoughTransform
n11.11 TheApproachofGerigandKlein
n11.12 ConcludingRemarks
n11.13 BibliographicalandHistoricalNotes
n11.14 Problem
n
nCHAPTER 12 EllipseDetection
n12.1 Introduction
n12.2 TheDiameterBisectionMethod
n12.3 TheChord-TangentMethod
n12.4 FindingtheRemainingEllipseParameters
n12.5 ReducingComputationalLoadfortheGeneralizedHoughTransformMethod
n12.5.1 PracticalDetails
n12.6 ComparingtheVariousMethods
n12.7 ConcludingRemarks
n12.8 BibliographicalandHistoricalNotes
n12.9 Problems
n
nCHAPTER 13 HoleDetection
n13.1 Introduction
n13.2 TheTemplateMatchingApproach
n13.3 TheLateralHistogramTechnique
n13.4 TheRemovalofAmbiguitiesintheLateralHistogramTechnique
n13.4.1 ComputationalImplicationsoftheNeedtoCheckforAmbiguities
n13.4.2 FurtherDetailoftheSubimageMethod
n13.5 ApplicationoftheLateralHistogramTechniqueforObjectLocation
n13.5.1 LimitationsoftheApproach
n13.6 AppraisaloftheHoleDetectionProblem
n13.7 ConcludingRemarks
n13.8 BibliographicalandHistoricalNotes
n13.9 Problems
n
nCHAPTER 14 PolygonandCornerDetection
n14.1 Introduction
n14.2 TheGeneralizedHoughTransform
n14.2.1 StraightEdgeDetection
n14.3 ApplicationtoPolygonDetection
n14.3.1 TheCaseofanArbitraryTriangle
n14.3.2 TheCaseofanArbitraryRectangle
n14.3.3 LowerBoundsontheNumbersofParameterPlanes
n14.4 DeterminingPolygonOrientation
n14.5 WhyCornerDetection？
n14.6 TemplateMatching
n14.7 Second-orderDerivativeSchemes
n14.8 AMedian-Filter-BasedCornerDetector
n14.8.1 AnalyzingtheOperationoftheMedianDetector
n14.8.2 PracticalResults
n14.9 TheHoughTransformApproachtoCornerDetection
n14.10 ThePlesseyCornerDetector
n14.11 CornerOrientation
n14.12 ConcludingRemarks
n14.13 BibliographicalandHistoricalNotes
n14.14 Problems
n
nCHAPTER 15 AbstractPatternMatchingTechniques
n15.1 Introduction
n15.2 AGraph-theoreticApproachtoObjectLocation
n15.2.1 APracticalExample-LocatingCreamBiscuits
n15.3 PossibilitiesforSavingComputation
n15.4 UsingtheGeneralizedHoughTransformforFeatureCollation
n15.4.1 ComputationalLoad
n15.5 GeneralizingtheMaximalCliqueandOtherApproaches
n15.6 RelationalDescriptors
n15.7 Search
n15.8 ConcludingRemarks
n15.9 BibliographicalandHistoricalNotes
n15.10 Problems
n
nPART3 3 -DVISIONANDMOTION
nCHAPTER 16 TheThree-dimensionalWorld
n16.1 Introduction
n16.2 Three-DimensionalVision-TheVarietyofMethods
n16.3 ProjectionSchemesforThree-dimensionalVision
n16.3.1 BinocularImages
n16.3.2 TheCorrespondenceProblem
n16.4 ShapefromShading
n16.5 PhotometricStereo
n16.6 TheAssumptionofSurfaceSmoothness
n16.7 ShapefromTexture
n16.8 UseofStructuredLighting
n16.9 Three-DimensionalObjectRecognitionSchemes
n16.10 TheMethodofBallardandSabbah
n16.11 TheMethodofSilberbergetal.
n16.12 HoraudsJunctionOrientationTechnique
n16.13 AnImportantParadigm-LocationofIndustrialParts
n16.14 ConcludingRemarks
n16.15 BibliographicalandHistoricalNotes
n16.16 Problems
n
nCHAPTER 17 TacklingthePerspectiven-PointProblem
n17.1 Introduction
n17.2 ThePhenomenonofPerspectiveInversion
n17.3 AmbiguityofPoseunderWeakPerspectiveProjection
n17.4 ObtainingUniqueSolutionstothePoseProblem
n17.4.1 Solutionofthe3-PointProblem
n17.4.2 UsingSymmetricalTrapeziaforEstimatingPose
n17.5 ConcludingRemarks
n17.6 BibliographicalandHistoricalNotes
n17.7 Problems
n
nCHAPTER18Motion
n18.1 Introduction
n18.2 OpticalFlow
n18.3 InterpretationofOpticalFlowFields
n18.4 UsingFocusofExpansiontoAvoidCollision
n18.5 Time-to-AdjacencyAnalysis
n18.6 BasicDifficultieswiththeOpticalFlowModel
n18.7 StereofromMotion
n18.8 ApplicationstotheMonitoringofTrafficFlow
n18.8.1 TheSystemofBascleetal.
n18.8.2 TheSystemofKolleretal.
n18.9 PeopleTracking
n18.9.1 SomeBasicTechniques
n18.9.2 Within-vehiclePedestrianTracking
n18.10 HumanGaitAnalysis
n18.11 Model-basedTrackingofAnimals-ACaseStudy
n18.12 Snakes
n18.13 TheKalmanFilter
n18.14 ConcludingRemarks
n18.15 BibliographicalandHistoricalNotes
n18.16 Problem
n
nCHAPTER 19 InvariantsandTheirApplications
n19.1 Introduction
n19.2 CrossRatios：The“RatioofRatios”Concept
n19.3 InvariantsforNoncollinearPoints
n19.3.1 FurtherRemarksaboutthe5-PointConfiguration
n19.4 InvariantsforPointsonConics
n19.5 DifferentialandSemidifferentialInvariants
n19.6 SymmetricalCrossRatioFunctions
n19.7 ConcludingRemarks
n19.8 BibliographicalandHistoricalNotes
n19.9 Problems
n
nCHAPTER 20 EgomotionandRelatedTasks
n20.1 Introduction
n20.2 AutonomousMobileRobots
n20.3 ActiveVision
n20.4 VanishingPointDetection
n20.5 NavigationforAutonomousMobileRobots
n20.6 ConstructingthePlanViewofGroundPlane
n20.7 FurtherFactorsInvolvedinMobileRobotNavigation
n20.8 MoreonVanishingPoints
n20.9 CentersofCirclesandEllipses
n20.10 VehicleGuidanceinAgriculture-ACaseStudy
n20.10.1 3-DAspectsoftheTask
n20.10.2 Real-timeImplementation
n20.11 ConcludingRemarks
n20.12 BibliographicalandHistoricalNotes
n20.13 Problems
n
nCHAPTER 21 ImageTransformationsandCameraCalibration
n21.1 Introduction
n21.2 ImageTransformations
n21.3 CameraCalibration
n21.4 IntrinsicandExtrinsicParameters
n21.5 CorrectingforRadialDistortions
n21.6 Multiple-viewVision
n21.7 GeneralizedEpipolarGeometry
n21.8 TheEssentialMatrix
n21.9 TheFundamentalMatrix
n21.10 PropertiesoftheEssentialandFundamentalMatrices
n21.11 EstimatingtheFundamentalMatrix
n21.12 ImageRectification
n21.13 3-DReconstruction
n21.14 AnUpdateonthe8-PointAlgorithm
n21.15 ConcludingRemarks
n21.16 BibliographicalandHistoricalNotes
n21.17 Problems
n
nPART 4 TOWARDREAL-TIMEPATTERNRECOGNITIONSYSTEMS
nCHAPTER 22 AutomatedVisualInspection
n22.1 Introduction
n22.2 TheProcessofInspection
n22.3 ReviewoftheTypesofObjectstoBeInspected
n22.3.1 FoodProducts
n22.3.2 PrecisionComponents
n22.3.3 DifferingRequirementsforSizeMeasurement
n22.3.4 Three-dimensionalObjects
n22.3.5 OtherProductsandMaterialsforInspection
n22.4 Summary-TheMainCategoriesofInspection
n22.5 ShapeDeviationsRelativetoaStandardTemplate
n22.6 InspectionofCircularProducts
n22.6.1 ComputationoftheRadialHistogram：StatisticalProblems
n22.6.2 ApplicationofRadialHistograms
n22.7 InspectionofPrintedCircuits
n22.8 SteelStripandWoodInspection
n22.9 InspectionofProductswithHighLevelsofVariability
n22.10 X-rayInspection
n22.11 TheImportanceofColorinInspection
n22.12 BringingInspectiontotheFactory
n22.13 ConcludingRemarks
n22.14 BibliographicalandHistoricalNotes
n
nCHAPTER 23 InspectionofCerealGrains
n23.1 Introduction
n23.2 CaseStudy1：LocationofDarkContaminantsinCereals
n23.2.1 ApplicationofMorphologicalandNonlinearFilterstoLocateRodentDroppings
n23.2.2 AppraisaloftheVariousSchemas
n23.2.3 ProblemswithClosing
n23.3 CaseStudy2：LocationofInsects
n23.3.1 TheVectorialStrategyforLinearFeatureDetection
n23.3.2 DesigningLinearFeatureDetectionMasksforLargerWindows
n23.3.3 ApplicationtoCerealInspection
n23.3.4 ExperimentalResults
n23.4 CaseStudy3：High-speedGrainLocation
n23.4.1 ExtendinganEarlierSamplingApproach
n23.4.2 ApplicationtoGrainInspection
n23.4.3 Summary
n23.5 OptimizingtheOutputforSetsofDirectionalTemplateMasks
n23.5.1 ApplicationoftheFormulas
n23.5.2 Discussion
n23.6 ConcludingRemarks
n23.7 BibliographicalandHistoricalNotes
n
nCHAPTER 24 StatisticalPatternRecognition
n24.1 Introduction
n24.2 TheNearestNeighborAlgorithm
n24.3 BayesDecisionTheory
n24.4 RelationoftheNearestNeighborandBayesApproaches
n24.4.1 MathematicalStatementoftheProblem
n24.4.2 TheImportanceoftheNearestNeighborClassifier
n24.5 TheOptimumNumberofFeatures
n24.6 CostFunctionsandError-RejectTradeoff
n24.7 TheReceiver-OperatorCharacteristic
n24.8 MultipleClassifiers
n24.9 ClusterAnalysis
n24.9.1 SupervisedandUnsupervisedLearning
n24.9.2 ClusteringProcedures
n24.10 PrincipalComponentsAnalysis
n24.11 TheRelevanceofProbabilityinImageAnalysis
n24.12 TheRoutetoFaceRecognition
n24.12.1 TheFaceasPartofa3-DObject
n24.13 AnotherLookatStatisticalPatternRecognition：TheSupportVectorMachine
n24.14 ConcludingRemarks
n24.15 BibliographicalandHistoricalNotes
n24.16 Problems
n
nCHAPTER 25 BiologicallyInspiredRecognitionSchemes
n25.1 Introduction
n25.2 ArtificialNeuralNetworks
n25.3 TheBackpropagationAlgorithm
n25.4 MLPArchitectures
n25.5 OverfittingtotheTrainingData
n25.6 OptimizingtheNetworkArchitecture
n25.7 HebbianLearning
n25.8 CaseStudy：NoiseSuppressionUsingANNs
n25.9 GeneticAlgorithms
n25.10 ConcludingRemarks
n25.11 BibliographicalandHistoricalNotes
n
nCHAPTER 26 Texture
n26.1 Introduction
n26.2 SomeBasicApproachestoTextureAnalysis
n26.3 Gray-levelCo-occurrenceMatrices
n26.4 LawsTextureEnergyApproach
n26.5 AdesEigenfilterApproach
n26.6 AppraisaloftheLawsandAdeApproaches
n26.7 Fractal-basedMeasuresofTexture
n26.8 ShapefromTexture
n26.9 MarkovRandomFieldModelsofTexture
n26.10 StructuralApproachestoTextureAnalysis
n26.11 ConcludingRemarks
n26.12 BibliographicalandHistoricalNotes
n
nCHAPTER 27 ImageAcquisition
n27.1 Introduction
n27.2 IlluminationSchemes
n27.2.1 EliminatingShadows
n27.2.2 PrinciplesforProducingRegionsofUniformIllumination
n27.2.3 CaseofTwoInfiniteParallelStripLights
n27.2.4 OverviewoftheUniformIlluminationScenario
n27.2.5 UseofLine-scanCameras
n27.3 CamerasandDigitization
n27.3.1 Digitization
n27.4 TheSamplingTheorem
n27.5 ConcludingRemarks
n27.6 BibliographicalandHistoricalNotes
n
nCHAPTER 28 Real-timeHardwareandSystemsDesignConsiderations
n28.1 Introduction
n28.2 ParallelProcessing
n28.3 SIMDSystems
n28.4 TheGaininSpeedAttainablewithNProcessors
n28.5 FlynnsClassification
n28.6 OptimalImplementationofanImageAnalysisAlgorithm
n28.6.1 HardwareSpecificationandDesign
n28.6.2 BasicIdeasonOptimalHardwareImplementation
n28.7 SomeUsefulReal-timeHardwareOptions
n28.8 SystemsDesignConsiderations
n28.9 DesignofInspectionSystems-TheStatusQuo
n28.10 SystemOptimization
n28.11 TheValueofCaseStudies
n28.12 ConcludingRemarks
n28.13 BibliographicalandHistoricalNotes
n28.13.1 GeneralBackground
n28.13.2 RecentHighlyRelevantWork
n
nPART5PERSPECTIVESONVISION
nCHAPTER 29 MachineVision：ArtorScience？
n29.1 Introduction
n29.2 ParametersofImportanceinMachineVision
n29.3 Tradeoffs
n29.3.1 SomeImportantTradeoffs
n29.3.2 TradeoffsforTwo-stageTemplateMatching
n29.4 FutureDirections
n29.5 Hardware，Algorithms，andProcesses
n29.6 ARetrospectiveView
n29.7 JustaGlimpseofVision？
n29.8 BibliographicalandHistoricalNotes
n
nAPPENDIXRobustStatistics
nA.1 Introduction
nA.2 PreliminaryDefinitionsandAnalysis
nA.3 TheM-estimator（InfluenceFunction）Approach
nA.4 TheLeastMedianofSquaresApproachtoRegression
nA.5 OverviewoftheRobustnessProblem
nA.6 TheRANSACApproach
nA.7 ConcludingRemarks
nA.8 BibliographicalandHistoricalNotes
nA.9 Problem
n
nListofAcronymsandAbbreviations
nReferences
nAuthorIndex
nSubjectIndex
新书资讯