Decision Forests for Computer Vision and Medical Image Analysis

✍ Scribed by A. Criminisi, J. Shotton (auth.), A. Criminisi, J. Shotton (eds.)

• Publisher: Springer-Verlag London
• Year: 2013
• Tongue: English
• Leaves: 366
• Series: Advances in Computer Vision and Pattern Recognition
• Edition: 1
• Category: Library

✦ Synopsis

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. Topics and features: with a foreword by Prof. Y. Amit and Prof. D. Geman, recounting their participation in the development of decision forests; introduces a flexible decision forest model, capable of addressing a large and diverse set of image and video analysis tasks; investigates both the theoretical foundations and the practical implementation of decision forests; discusses the use of decision forests for such tasks as classification, regression, density estimation, manifold learning, active learning and semi-supervised classification; includes exercises and experiments throughout the text, with solutions, slides, demo videos and other supplementary material provided at an associated website; provides a free, user-friendly software library, enabling the reader to experiment with forests in a hands-on manner.

✦ Table of Contents

Front Matter....Pages I-XIX
Overview and Scope....Pages 1-2
Notation and Terminology....Pages 3-4
Front Matter....Pages 5-5
Introduction: The Abstract Forest Model....Pages 7-23
Classification Forests....Pages 25-45
Regression Forests....Pages 47-58
Density Forests....Pages 59-77
Manifold Forests....Pages 79-93
Semi-supervised Classification Forests....Pages 95-107
Front Matter....Pages 109-109
Keypoint Recognition Using Random Forests and Random Ferns....Pages 111-124
Extremely Randomized Trees and Random Subwindows for Image Classification, Annotation, and Retrieval....Pages 125-141
Class-Specific Hough Forests for Object Detection....Pages 143-157
Hough-Based Tracking of Deformable Objects....Pages 159-173
Efficient Human Pose Estimation from Single Depth Images....Pages 175-192
Anatomy Detection and Localization in 3D Medical Images....Pages 193-209
Semantic Texton Forests for Image Categorization and Segmentation....Pages 211-227
Semi-supervised Video Segmentation Using Decision Forests....Pages 229-244
Classification Forests for Semantic Segmentation of Brain Lesions in Multi-channel MRI....Pages 245-260
Manifold Forests for Multi-modality Classification of Alzheimer’s Disease....Pages 261-272
Entanglement and Differentiable Information Gain Maximization....Pages 273-293
Decision Tree Fields: An Efficient Non-parametric Random Field Model for Image Labeling....Pages 295-309
Front Matter....Pages 311-311
Efficient Implementation of Decision Forests....Pages 313-332
The Sherwood Software Library....Pages 333-342
Conclusions....Pages 343-345
Back Matter....Pages 347-368

✦ Subjects

Pattern Recognition; Artificial Intelligence (incl. Robotics)