动态视觉：从图像到面部识别DYNAMIC VISION: FROM IMAGES TO FACE RECOGNITION
点此进入淘宝搜索页搜索分類: 图书,进口原版书,科学与技术 Science & Techology ,
作者： Shaogang Gong等著
出 版 社：
出版时间： 2000-12-1字数：版次： 1页数： 344印刷时间： 2000/09/01开本：印次： 1纸张： 胶版纸I S B N ： 9781860941818包装： 精装内容简介
Face recognition is a task that the human vision system seems to perform almost effortlessly, yet the goal of building computer-based systems with comparable capabilities has proven to be difficult. The task implicitly requires the ability to locate and track faces through often complex and dynamic scenes. Recognition is difficult because of variations in factors such as lighting conditions, viewpoint, body movement and facial expression. Although evidence from psychophysical and neurobiological experiments provides intriguing insights into how we might code and recognise faces, its bearings on computational and engineering solutions are far from clear. The study of face recognition has had an almost unique impact on computer vision and machine learning research at large. It raises many challenging issues and provides a good vehicle for examining some difficult problems in vision and learning. Many of the issues raised are relevant to object recognition in general.
This book describes the latest models and algorithms that are capable of performing face recognition in a dynamic setting. The key question is how to design computer vision and machine learning algorithms that can operate robustly and quickly under poorly controlled and changing conditions. Consideration of face recognition as a problem in dynamic vision is perhaps both novel and important. The algorithms described have numerous potential applications in areas such as visual surveillance, verification, access control, video-conferencing, multimedia and visually mediated interaction.
The book will be of special interest to researchers and academics involved in machine vision, visual recognition and machine learning. It should also be of interest to industrial research scientists and managers keen to exploit this emerging technology and develop automated face and human recognition systems. It is also useful to postgraduate students studying computer science, electronic engineering, information or systems engineering, and cognitive psychology.
目录
Preface
PART I BACKGROUND
1 About Face
1.1 The Visual Face
1.2 The Changing Face
1.3 Computing Faces
1.4 Biological Perspectives .
1.5 The Approach
2 Perception and Representation
2.1 A Distal Object
2.2 Representation by 3D Reconstruction
2.3 Two-dimensional View-based Representation
2.4 Image Template-based Representation
2.5 The Correspondence Problem and Alignment
2.6 Biological Perspectives
2.7 Discussion
3 Learning under Uncertainty
3.1 Statistical Learning
3.2 Learning as Function Approximation
3.3 Bayesian Inference and MAP Classification
3.4 Learning as Density Estimation
3.4.1 Parametric Models
3.4.2 Non-parametric Models
3.4.3 Semi-parametric Models
3.5 Unsupervised Learning without Density Estimation
3.5.1 Dimensionality Reduction
3.5.2 Clustering
3.6 Linear Classification and Regression
3.6.1 Least-squares
3.6.2 Linear Support Vector Machines
3.7 Non-linear Classification and Regression
3.7.1 Multi-layer Networks
3.7.2 Support Vector Machines
3.8 Adaptation
3.9 Biological Perspectives
3.10 Discussion
PART II FROM SENSORY TO MEANINGFUL PERCEPTION
4 Selective Attention: Where to Look
4.1 Pre-attentive Visual Cues from Motion .
4.1.1 Measuring Temporal Change
4.1.2 Motion Estimation
4.2 Learning Object-based Colour Cues
4.2.1 Colour Spaces
4.2.2 Colour Density Models
4.3 Perceptual Grouping for Selective Attention
4.4 Data Fusion for Perceptual Grouping
4.5 Temporal Matching and Tracking
4.6 Biological Perspectives
4.7 Discussion
5 A Face Model: What to Look For
5.1 Person-independent Face Models for Detection
5.1.1 Feature-based Models
5.1.2 Holistic Models
5.1.3 The Face Class
5.2 Modelling the Face Class
5.2.1 Principal Components Analysis for a Face Model
5.2.2 Density Estimation in Local PCA Spaces
5.3 Modelling a Near-face Class
5.4 Learning a Decision Boundary
……
6 Undersanding Pose
7 Prediction and Adaptation
PART III MODELS OF IKDENTITY
8 Single-View Identification
9 Multi-View Identification
10 Identifying Moving Faces
PART IV PERCEPTION IN CONTEXT
11 Perceptual Integration
12 Beyond Faces
PART V APPENDICES
A Databases
B Commercial Systems
C Mathematical Details
Bibliography
Index
