13 Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants

Keyword list at end

• 13.1 Matching, Volumes, 3-D
  • 13.1.1 Aspect Graph Matching, Characteristic Views
    • 13.1.1.1 Aspect Graphs, Matching Systems, Object Recognition
    • 13.1.1.2 Aspect Graph Matching -- Bowyer
    • 13.1.1.3 Aspect Graph Matching -- Ikeuchi
  • 13.1.2 3-D Object Recognition Using Invariants
    • 13.1.2.1 Invariants, General Issues and Techniques
    • 13.1.2.2 Invariants, Points
    • 13.1.2.3 Invariants, Lines, Curves
    • 13.1.2.4 Invariants, Areas
    • 13.1.2.5 Invariants, Projective, Perspective
    • 13.1.2.6 Affine Invariants
    • 13.1.2.7 Invariance Papers -- Mundy
  • 13.1.3 Matching Using Accumulation and Alignment Schemes
    • 13.1.3.1 Pose Estimation, 3D Models
    • 13.1.3.2 Grimson Object Recognition Papers
• 13.2 Combined Feature Matching
• 13.3 Graph Matching and Relaxation
  • 13.3.1 Graph Matching Theoretical Issues
  • 13.3.2 General Structure and Graph Representation, Relations, Neighbors
  • 13.3.3 Social Networks, Creation, Visualization, Use
  • 13.3.4 Subgraph Isomorphism, Common Subgraphs, Subgraph Matching
  • 13.3.5 Matching Graphs and 3-D Network Descriptions
    • 13.3.5.1 Spatial Information and Features, Visual Relationships
  • 13.3.6 Graph Matching, Neural Networks, Hopfield Networks
  • 13.3.7 Graph Matching, Continuous Relaxation, Constraint Satisfaction
    • 13.3.7.1 Continuous Relaxation Theory, Constraint Satisfaction
    • 13.3.7.2 Boltzmann Machine, Simulated Annealing, and Related Topics
    • 13.3.7.3 Hummel and Zucker Relaxation Papers
    • 13.3.7.4 Shmuel Peleg Theoretical Relaxation Papers
    • 13.3.7.5 Faugeras and Berthod Gradient Optimization Methods
  • 13.3.8 Discrete Relaxation Methods
    • 13.3.8.1 Discrete Relaxation Theoretical Issues
  • 13.3.9 Matching Using "Tree" Searching Techniques, Heuristic Search
    • 13.3.9.1 Tabu Search
  • 13.3.10 Basic Comparison of Relational Network Descriptions
    • 13.3.10.1 Evidence Theory, Combination Techniques, Optimization Techniques
      • 13.3.10.1.1 Fuzzy Sets, Fuzzy Logic
    • 13.3.10.2 Maximum Likelihood Estimation, Classification
    • 13.3.10.3 Energy Minimization, Energy Maximization Computation, Function Solving
    • 13.3.10.4 Optimizations
    • 13.3.10.5 Regression
    • 13.3.10.6 MRF Optimization, Energy Minimization
    • 13.3.10.7 Computational Complexity Issues
    • 13.3.10.8 Ant Colony Optimization, Bee Colony Optimization
    • 13.3.10.9 Bayesian Networks, Bayes Nets
    • 13.3.10.10 Graph Edit Distance, Tree-Edit Distance
    • 13.3.10.11 Graph Clustering, Cilque Generation
    • 13.3.10.12 Graph Embedding Clustering
    • 13.3.10.13 Linear Prediction Techniques
    • 13.3.10.14 Random Field Models for Structure Matching
  • 13.3.11 Structural Matching for Computer Vision
• 13.4 Object Recognition, General Techniques
  • 13.4.1 Invariants -- Eigen Representations, General Appearance Based Methods
    • 13.4.1.1 Other Sparse Coding, Low Dimensional Representation, Invariants
      • 13.4.1.1.1 Sparse Descriptions, Dictionary Descriptions
    • 13.4.1.2 Other, Kernel Methods, Invariants
    • 13.4.1.3 Active Appearance Models: AAM
    • 13.4.1.4 Invariants -- Principal Component Analysis
    • 13.4.1.5 Invariants -- ICA, Independent Component Analysis
    • 13.4.1.6 Invariants -- Linear Discriminant Analysis, Fisher Linear Discriminant
    • 13.4.1.7 Surveys, Comparisons, Evaluations, Principal Components
    • 13.4.1.8 Learning for Principal Components, Eigen Representations
    • 13.4.1.9 Computation and Analysis of Principal Components, Eigen Values, SVD
    • 13.4.1.10 Faces using Invariants, Appearence models -- Eigenfaces
      • 13.4.1.10.1 ICA, PCA in Face Recognition
      • 13.4.1.10.2 LDA in Face Recognition
      • 13.4.1.10.3 Singular Value Decompostion, SVD in Face Recognition
      • 13.4.1.10.4 Other Invariants in Face Recognition, General Invariants, Sparse Representations
  • 13.4.2 Three-Dimensional Matching Using Hashing/Indexing
  • 13.4.3 Model Based Recognition Systems
    • 13.4.3.1 Parameterized Models, Fit Model to Objects
    • 13.4.3.2 Associative Memory for Matching and Recognition
  • 13.4.4 3-D Object Recognition from Pose Estimation or Alignment
  • 13.4.5 Object Recognition Evaluation
  • 13.4.6 Object Recognition, Retrieval Datasets
• 13.5 General Spatial Reasoning and Geometric Reasoning Issues, Visual Relations
• 13.6 Knowledge-Based Vision
  • 13.6.1 General Issues -- Knowledge-Based Vision
    • 13.6.1.1 Knowledge-Based Vision, Surveys, Overviews
    • 13.6.1.2 Crowdsourcing, Recognition, Analysis, Descriptions
  • 13.6.2 ACRONYM and SUCCESSOR Papers - Stanford University and Others
  • 13.6.3 University of Massachusetts VISIONS System
    • 13.6.3.1 Knowledge Distillation
    • 13.6.3.2 Explainable Aritficial Intelligence
  • 13.6.4 Constraint Based Matching
  • 13.6.5 Rule-Based or Expert Systems for Recognition
  • 13.6.6 Recognition by Function
  • 13.6.7 Integration of Vision Modules, Select Operations, Sequence Operations
  • 13.6.8 Context in Computer Vision
    • 13.6.8.1 Context, Fine-Grained Classification
    • 13.6.8.2 Context Supplied by Text or Language
    • 13.6.8.3 Context from the environment
  • 13.6.9 Annotation, Captioning, Image Captioning
• 13.7 General References for Matching
  • 13.7.1 RANSAC Matching Issues, Design, Evaluation
  • 13.7.2 String Matching, Text Matching
• 13.8 Other Feature Matching Techniques