Cargando…

Decision Forests for Computer Vision and Medical Image Analysis

Decision forests (also known as random forests) are an indispensable tool for automatic image analysis. This practical and easy-to-follow text explores the theoretical underpinnings of decision forests, organizing the vast existing literature on the field within a new, general-purpose forest model....

Descripción completa

Detalles Bibliográficos
Clasificación:Libro Electrónico
Autor Corporativo: SpringerLink (Online service)
Otros Autores: Criminisi, Antonio (Editor ), Shotton, J. (Editor )
Formato: Electrónico eBook
Idioma:Inglés
Publicado: London : Springer London : Imprint: Springer, 2013.
Edición:1st ed. 2013.
Colección:Advances in Computer Vision and Pattern Recognition,
Temas:
Acceso en línea:Texto Completo
Tabla de Contenidos:
  • Overview and Scope
  • Notation and Terminology
  • Part I: The Decision Forest Model
  • Introduction
  • Classification Forests
  • Regression Forests
  • Density Forests
  • Manifold Forests
  • Semi-Supervised Classification Forests
  • Part II: Applications in Computer Vision and Medical Image Analysis
  • Keypoint Recognition Using Random Forests and Random Ferns
  • Extremely Randomized Trees and Random Subwindows for Image Classification, Annotation, and Retrieval
  • Class-Specific Hough Forests for Object Detection
  • Hough-Based Tracking of Deformable Objects
  • Efficient Human Pose Estimation from Single Depth Images
  • Anatomy Detection and Localization in 3D Medical Images
  • Semantic Texton Forests for Image Categorization and Segmentation
  • Semi-Supervised Video Segmentation Using Decision Forests
  • Classification Forests for Semantic Segmentation of Brain Lesions in Multi-Channel MRI
  • Manifold Forests for Multi-Modality Classification of Alzheimer's Disease
  • Entangled Forests and Differentiable Information Gain Maximization
  • Decision Tree Fields
  • Part III: Implementation and Conclusion
  • Efficient Implementation of Decision Forests
  • The Sherwood Software Library
  • Conclusions.