Intelligent Visual Perception Tutorial智能視感學（英文版）

Foreword
Preface
    Base article
Chapter 1  Introduction
  1.1  Overview
    1.1.1  Concept about the VisualPerception
    1.1.2  The Development of Visual PerceptionTechnology
    1.1.3  Classification of Visual PerceptionSystem
  1.2  A Visual Perception Hardware-base
    1.2.1 iImage Seing
    1.2.2  Image Acquisition
    1.2.3  PC Hardware Requirements forVPS
  Exercises
Chapter 2  Foundatio of Image Processing
  2.1  Basic Processing Methods for Gray Image
    2.1.1  Spatial Domain EnhancementAlgorithm
    2.1.2  Frequency Domain EnhancementAlgorithm
  2.2  Edge Detection of Gray Image
    2.2.1  Threshold Edge Detection
    2.2.2  Gradient-based Edge Detection
    2.Z.3  Laplacian Operator
    2.2.4  Canny Edge Operator
    2.2.5  Mathematical MorphologicalMethod
    2.2.6  Brief Description of OtherAlgorithms
  2.3  Binarization Processing and Segmentation ofImage
    2.3.1  General Description
    2.3.2  Histogram-based Valley-pointThreshold Image Binarization
    2.3.3  OTSU Algorithm
    2.3.4  Minimum Error Method of ImageSegmentation
  2.4  Color Image Enhancement
    2.4.1  Color Space and ItsTraformation
    2.4.2  Histogram Equalization of ColorLevels in Color Image
  2.5  Color Image Edge Detection
    2.5.1   Color Image Edge DetectionBased on Gradient Extreme Value
    2.5.2  Practical Method for Color ImageEdge Detection
  Exercises
Chapter 3  Mathematical Model of the Camera
  3.1  Geometric Traformatio of Image Space
    3.1.1   Homogeneous Coordinates
    3.1.2  Orthogonal Traformation and RigidBody Traformation
    3.1.3  Similarity Traformation and AffineTraformation
    3.1.4  Pepective Traformation
  3.2  Image Coordinate System and Its Traformation
    3.2.1  Image Coordinate System
    3.2.2  Image Coordinate Traformation
  3.3  Common Method of Calibration Camera Paramete
    3.3.1  Step Calibration Method
    3.3.2  Calibration Algorithm Based on Morethan One Free Plane
    3.3.3  Non-linear Distortion ParameterCalibration Method
  Exercises
Chapter 4  Visual Perception Identification Algorithms
  4.1  Image Feature Extraction and IdentificationAlgorithm
    4.1.1  Decision Theory Approach
    4.1.2  Statistical ClassificationMethod
    4.1.3  Feature Classification DiscretionSimilarity about the Image Recognition Process
  4.2  Principal Component Analysis
    4.2.1  Principal Component AnalysisPrinciple
    4.2.2  Kernel Principal ComponentAnalysis
    4.2.3  PCA-based Image Recognition
  4.3  Support Vector Machines
    4.3.1   Main Contents of StatisticalLearning Theory
    4.3.2  Classification-Support VectorMachine  ~
    4.3.3  Solution to the Nonlinear RegressionProblem
    4.3.4  Algorithm of Support VectorMachine
    4.3.5  Image Characteristics IdentificationBased on SVM
  4.4  Moment Invariants and Normalized Moments ofInertia
    4.4.1  Moment Theory
    4.4.2  Normalized Moment of Inertia
  4.5  Template Matching and Similarity
    4.5.1  Spatial Domain Description ofTemplate Matching
    4.5.2  Frequency Domain Description ofTemplate Matching
  4.6  Object Recognition Based on Color Feature
    4.6.1  Image Colorimetric Processing
    4.6.2  Cotruction of Color-Pool
    4.6.3  Object Recognition Based onColor
  4.7  Image Fuzzy Recognition Method
    4.7.1  Fuzzy Content Feature and FuzzySimilarity Degree
    4.7.2  Extraction of Fuzzy Structure
    4.7.3  Fuzzy Synthesis Decision-making ofImage Matching
  Exercises
Chapter 5  Detection Principle of Visual Perception
  5.1  Single View Geometry and Detection Principle ofMonocular Visual Perception
    5.1.1  Single Vision CoordinateSystem
    5.1.2  Basic Algorithm for Single VisionDetection
    5.1.3  Engineering Technology Based onSingle View Geometry
  5.2  Detection Principle of Binocular VisualPerception
    5.2.1  Two-view Geometry and Detection ofBinocular Perception
    5.2.2  Epipolar Geometry Principle
    5.2.3  Determination Method of SpatialCoordinates
    5.2.4  Camera Calibration in BinocularVisual Perception System
  5.3  Theoretical Basis for Multiple Visual PerceptionDetection
    5.3.1  Teor Geometry Principle
    5.3.2  Geometric Properties of Three VisualTeor
    5.3.3  Operation of Three-visual Teor
    5.3.4  Cotraint Matching Feature Points ofThree-visual Teor
    5.3.5  Three-visual Teor Restrict the ThreeVisual Restraint Feature Line' s Matching
  Exercises
  Application article
Chapter 6  Practical Technology of Intelligent VisualPerception
  6.1  Automatic Monitoring System and Method of LoadLimitation of The Bridge
    6.1.1  The Basic Composition of TheSystem
    6.1.2  System Algorithm
  6.2  Intelligent Identification System for BilletNumber
    6.2.1  System Control Program
    6.2.2  Recognition Algorithm
  6.3  Verification of Banknotes-Sorting Based on ImageInformation
    6.3.1  Preprocessing of the BanknotesImage
    6.3.2  Distinction Between Old and NewBanknotes
    6.3.3  Distinction of the Denomination andDirection of the Banknotes
    6.3.4  Banknotes Fineness Detection
  6.4  Intelligent Collision Avoidance Technology ofVehicle
    6.4.1  Basic Hardware Configuration
    6.4.2  Road Obstacle RecognitionAlgorithm
    6.4.3  Smart Algorithm of Anti-collision toPedestria
  6.5  Intelligent Visual Perception Control of TrafficLights
    6.5.1  Overview
    6.5.2  The Core Algorithm of IntelligentVisual Perception Control of Traffic Lights
  Exercises
Appendix
  Least Square and Common Algorithms in Visual PerceptionDetection
  I.1  Basic Idea of the Algorithm
  I.2  Common Least Square Algorithms in VisualPerception Detection
    I.2.1   Least Square of Linear Systemof Equatio
    I.2.2  Least Square Solution of NonlinearHomogeneous System of Equatio Theory and Method of BAYESDecision
   II.1  Introduction
   II.2  BAYES Classification Decision Mode
     II.2.1  BAYES Classification ofMinimum Error Rate
     II.2.2  BAYES Classification Decisionof Minimum Risk
III  Statistical Learning and VC-dimeion Theorem
  III.1  Bounding Theory and VC-dimeion Principle
  III.2  Generalized Capability Bounding
  III.3  Structural Risk Minimization Principle ofInduction
IV  Optimality Conditio on Cotrained Nonlinear ProgrammingProblem
  IV.1  Kuhn-Tucker Condition
    IV.1.1  Gordon Lemma
    IV.1.2  Fritz John Theorem
    IV.1.3  Proof of the Kuhn-TuckerCondition
  IV.2  Karush-Kuhn-Tucker Condition
Subject Index
References