Representation and recognition in vision /
Shimon Edelman bases a comprehensive approach to visual representation on the notion of correspondence between proximal (internal) and distal similarities in objects.
Clasificación: | Libro Electrónico |
---|---|
Autor principal: | |
Formato: | Electrónico eBook |
Idioma: | Inglés |
Publicado: |
Cambridge, Mass. :
MIT Press,
©1999.
©1999 |
Colección: | Bradford book.
|
Temas: | |
Acceso en línea: | Texto completo |
Tabla de Contenidos:
- The Problem of Representation
- A Vision of Representation
- Reconstruction
- Representation without Reconstruction
- The Feature Detector Redux
- The Challenge
- Theories of Representation and Object Recognition
- Recognition-Related Tasks That Require Representation
- Identification and Generalization
- Categorization
- Analogy
- A Formalization of the Notion of Representation
- The Problem of Representation
- Representation as a Mapping
- First- and Second-Order Isomorphism
- Computational Theories of Recognition
- Reconstructionist Theories: A Brief Historical Perspective
- Structural Decomposition Theories
- Theories Based on Geometric Constraints
- Multidimensional Feature Spaces
- S-isomorphism: The Theory
- Similarity as Proximity in a Metric Space
- Some Common Objections
- A Metric Similarity Space as a Working Hypothesis
- Shape Spaces
- Kendall's Shape Space
- Transformations and Deformations
- Best-Correspondence Distance
- An Objective Shape Space
- Parameterization of Distal Shape Space
- Scope of Parameterization
- Dimensionality of Parameterization
- The Distal to Proximal Mapping
- Levels of Representation of Similarity
- The Components of the Mapping F
- Constraints on F
- Implications
- S-isomorphism: An Implementation
- Task-Dependent Treatment of the Measurement Space
- Identification ("Is this an image of object X?")
- Recognition ("Is this an image of something I know?")
- Categorization ("What is this thing?")
- Categorization as Navigation in Shape Space.