Dynamic Vision : From Images to Face Recognition,9781860941818

Dynamic Vision : From Images to Face Recognition

by ; ;
ISBN13: 9781860941818
ISBN10: 1860941818
Format: Hardcover
Pub. Date: 2000-09-01
Publisher(s): WORLD SCIENTIFIC PUB CO INC
List Price: $85.00

Rent Textbook

Select for Price
Add to Cart
There was a problem. Please try again later.

Rent Digital

Rent Digital Options
Online:1825 Days access
Downloadable:Lifetime Access
$40.80
*To support the delivery of the digital material to you, a digital delivery fee of $3.99 will be charged on each digital item.
$40.80*
Add to Cart

New Textbook

We're Sorry
Sold Out

Used Textbook

We're Sorry
Sold Out

Buy from our Marketplace starting at $6.64

How Marketplace Works:

  • This item is offered by an independent seller and not shipped from our warehouse
  • Item details like edition and cover design may differ from our description; see seller's comments before ordering.
  • Sellers much confirm and ship within two business days; otherwise, the order will be cancelled and refunded.
  • Marketplace purchases cannot be returned to eCampus.com. Contact the seller directly for inquiries; if no response within two days, contact customer service.
  • Additional shipping costs apply to Marketplace purchases. Review shipping costs at checkout.

Summary

Describes models and algorithms that are capable of performing face recognition in a dynamic setting. Contents include perception and representation, learning under uncertainty, selective attention, understanding pose, perceptual integration, databases, and more.

Table of Contents

Preface xv
Part I Background 1(56)
About Face
3(12)
The Visual Face
3(1)
The Changing Face
4(2)
Computing Faces
6(5)
Biological Perspectives
11(1)
The Approach
12(3)
Perception and Representation
15(16)
A Distal Object
16(2)
Representation by 3D Reconstruction
18(1)
Two-dimensional View-based Representation
19(2)
Image Template-based Representation
21(1)
The Correspondence Problem and Alignment
22(4)
Biological Perspectives
26(3)
Discussion
29(2)
Learning under Uncertainty
31(26)
Statistical Learning
32(1)
Learning as Function Approximation
33(3)
Bayesian Inference and MAP Classification
36(1)
Learning as Density Estimation
37(4)
Parametric Models
37(2)
Non-parametric Models
39(1)
Semi-parametric Models
40(1)
Unsupervised Learning without Density Estimation
41(3)
Dimensionality Reduction
43(1)
Clustering
43(1)
Linear Classification and Regression
44(4)
Least-squares
45(1)
Linear Support Vector Machines
45(3)
Non-linear Classification and Regression
48(3)
Multi-layer Networks
48(2)
Support Vector Machines
50(1)
Adaptation
51(2)
Biological Perspectives
53(1)
Discussion
54(3)
Part II From Sensory to Meaningful Perception 57(104)
Selective Attention: Where to Look
59(22)
Pre-attentive Visual Cues from Motion
60(5)
Measuring Temporal Change
61(1)
Motion Estimation
62(3)
Learning Object-based Colour Cues
65(6)
Colour Spaces
66(2)
Colour Density Models
68(3)
Perceptual Grouping for Selective Attention
71(2)
Data Fusion for Perceptual Grouping
73(3)
Temporal Matching and Tracking
76(1)
Biological Perspectives
77(1)
Discussion
78(3)
A Face Model: What to Look For
81(22)
Person-independent Face Models for Detection
82(4)
Feature-based Models
82(1)
Holistic Models
83(2)
The Face Class
85(1)
Modelling the Face Class
86(3)
Principal Components Analysis for a Face Model
87(1)
Density Estimation in Local PCA Spaces
88(1)
Modelling a Near-face Class
89(1)
Learning a Decision Boundary
90(9)
Face Detection in Dynamic Scenes
91(2)
Normalisation
93(2)
Face Detection using Multi-layer Perceptrons
95(2)
Face Detection using Support Vector Machines
97(2)
Perceptual Search
99(2)
Biological Perspectives
101(1)
Discussion
102(1)
Understanding Pose
103(22)
Feature and Template-based Correspondence
105(1)
The Face Space across Views: Pose Manifolds
105(6)
The Effect of Gabor Wavelet Filters on Pose Manifolds
111(2)
Template Matching as Affine Transformation
113(5)
Similarities to Prototypes across Views
118(3)
Learning View-based Support Vector Machines
121(2)
Biological Perspectives
123(1)
Discussion
123(2)
Prediction and Adaptation
125(36)
Temporal Observations
128(1)
Propagating First-order Markov Processes
129(2)
Kalman Filters
131(1)
Propagating Non-Gaussian Conditional Densities
132(2)
Learning Priors using HMMs and EM
132(1)
Observation Augmented Density Propagation
133(1)
Tracking Attended Regions
134(2)
Adaptive Colour Models
136(4)
Selective Adaptation
140(5)
Tracking Faces
145(2)
Pose Tracking
147(9)
Person-specific Pose Tracking
149(1)
Person-independent Pose Tracking
150(6)
Biological Perspectives
156(1)
Discussion
157(4)
Part III Models of Identity 161(66)
Single-View Identification
163(24)
Identification Tasks
163(2)
Nearest-neighbour Template Matching
165(1)
Representing Knowledge of Facial Appearance
166(2)
Statistical Knowledge of Facial Appearance
168(8)
Low Dimensionality: Principal Components Analysis
168(5)
Separability: Linear Discriminant Analysis
173(3)
Sparseness and Topography: Local Feature Analysis
176(1)
Statistical Knowledge of Identity
176(4)
Identification Tasks Revisited
177(2)
Class-conditional Densities for Modelling Identity
179(1)
Structural Knowledge: The Role of Correspondence
180(3)
Beyond Alignment: Correspondence at a Single View
181(1)
Combining Statistical and Structural Models
182(1)
Biological Perspectives
183(2)
Discussion
185(2)
Multi-View Identification
187(22)
View-based Models
189(2)
The Role of Prior Knowledge
191(1)
View Correspondence in Identification
191(8)
Learning Linear Shape Models
192(3)
Nonlinear Shape Models
195(4)
Generalisation from a Single View
199(4)
Identity by Linear Combination
199(2)
Identity by Similarity to Prototype Views
201(2)
Generalisation from Multiple Views
203(2)
Biological Perspectives
205(2)
Discussion
207(2)
Identifying Moving Faces
209(18)
Biological Perspectives
210(3)
Learning and Identity Constancy
210(1)
The Effect of Temporal Order of Pose on Learning
210(1)
The Effect of Motion on Familiar Face Identification
211(2)
Computational Theories of Temporal Identification
213(2)
Atemporal Representation
213(1)
Spatio-temporal Signatures
214(1)
Identification using Holistic Temporal Trajectories
215(3)
Identification by Continuous View Transformation
218(1)
An Experimental System
219(6)
Discussion
225(2)
Part IV Perception in Context 227(38)
Perceptual Integration
229(24)
Sensory and Model-based Vision
230(1)
Perceptual Fusion
231(5)
Perceptual Inference
236(6)
Inference using Hidden Markov Models
240(1)
Closed-loop Perceptual Control
241(1)
Vision as Cooperating Processes
242(5)
Visual Attention and Grouping
242(3)
Face Detection, Tracking and Identification
245(2)
Biological Perspectives
247(3)
Discussion
250(3)
Beyond Faces
253(12)
Multi-model Identification
254(1)
Visually Mediated Interaction
255(3)
Visual Surveillance and Monitoring
258(2)
Immersive Virtual Reality
260(1)
Visual Database Screening
261(4)
Part V Appendices 265(50)
A Databases
267(14)
A.1 Database Acquisition and Design
267(1)
A.1.1 Intrinsic Experimental Variables
268(1)
A.1.2 Extrinsic Experimental Variables
268(1)
A.2 Acquisition of a Pose-labelled Database
269(1)
A.2.1 Using Artificial Markers
269(2)
A.2.2 Using Sensors and a Calibrated Camera
271(2)
A.3 Benchmarking
273(2)
A.4 Commercial Databases
275(2)
A.5 Public Domain Face Databases
277(2)
A.6 Discussion
279(2)
B Commercial Systems
281(16)
B.1 System Characterisation
282(1)
B.2 A View on the Industry
283(1)
B.2.1 Visionics Corporation
284(2)
B.2.2 Miros Inc.
286(1)
B.2.3 VisionSpheres Technologies
287(2)
B.2.4 Eigenface-based Systems: Viisage Technologies, Intelligent Verification Systems and Facia Reco
289(2)
B.2.5 Systems based on Facial Feature Matching: Plettac Electronic Security GmbH, ZN Bochum GmbH and Eyematic Interfaces Inc.
291(4)
B.3 Discussion
295(2)
C Mathematical Details
297(18)
C.1 Principal Components Analysis
297(1)
C.2 Linear Discriminant Analysis
298(2)
C.3 Gaussian Mixture Estimation
300(1)
C.3.1 Expectation-maximisation
300(1)
C.3.2 Automatic Model Order Selection
301(1)
C.3.3 Adaptive EM for Non-stationary Distributions
302(2)
C.4 Kalman Filters
304(1)
C.4.1 Zero-order Prediction
304(1)
C.4.2 First-order Prediction
305(1)
C.5 Bayesian Belief Networks
306(3)
C.6 Hidden Markov Models
309(3)
C.7 Gabor Wavelets
312(3)
Bibliography 315(24)
Index 339

An electronic version of this book is available through VitalSource.

This book is viewable on PC, Mac, iPhone, iPad, iPod Touch, and most smartphones.

By purchasing, you will be able to view this book online, as well as download it, for the chosen number of days.

Digital License

You are licensing a digital product for a set duration. Durations are set forth in the product description, with "Lifetime" typically meaning five (5) years of online access and permanent download to a supported device. All licenses are non-transferable.

More details can be found here.

A downloadable version of this book is available through the eCampus Reader or compatible Adobe readers.

Applications are available on iOS, Android, PC, Mac, and Windows Mobile platforms.

Please view the compatibility matrix prior to purchase.