本书以全新的角度论述智能化的全自动人脸识别方法，着重阐述如何把诸如模式识别、机器学习、图形图像处理、视频的时空关联、甚至逻辑判断等单一的方法有机地结合在一起，非监督式地从视频中检测和识别人脸，并自动建立和更新相映的数据库。

本书综合了世界范围内生物识别，特别是人脸识别研究的最新成果，并提出了广义的人脸检测与识别的归类方法。本书内容新颖、广泛，学术性与实用性强，适用于人脸识别领域的科研人员、教学人员、研究生，对其它生物识别领域的研究也具有重要的借鉴作用。

Machine, based Intelligent Face Recognition discusses the general engineering method of imitating intelligent human brains for video-based face recognition in a fundamental way, which is completely unsupervised,automatic, self-learning,self-updated and robust. It also overviews stateof-the-art researchon cognitive-based biometrics and machine-based biometrics, and especially the advances in face recognition.

This book is intended for scientists, researchers, engineers, and students in the field of computer vision, machine intelligence, and particularly of face recognition.

1 Introduction

 1.1 Face Recognition--Machine Versus Human

 1.2 Proposed Approach

 1.3 Prospective Applications

1.3.1 Recognition in the Future Intelligent Home

1.3.2 Automotive

1.3.3 Mobile Phone for Children

 1.4 Outline

 References

2 Fundamentals and Advances in Biometrics and Face Recognition

 2.1 Generalized Biometric Recognition

 2.2 Cognitive-based Biometric Recognition

2.2.1 Introduction

2.2.2 History of Cognitive Science

2.2.3 Human Brain Structure

2.2.4 Generic Methods in Cognitive Science

2.2.5 Visual Function in Human Brain

2.2.6 General Cognitive-based Object Recognition

2.2.7 Cognitive-based Face Recognition

2.2.8 Inspirations from Cognitive-based Face Recognition

 2.3 Machine-based Biometric Recognition

2.3.1 Introduction

2.3.2 Biometric Recognition Tasks

2.3.3 Enrollment--a Special Biometric Procedure

2.3.4 Biometric Methods Overview

2.3.5 Fingerprint Recognition

 2.4 Generalized Face Recognition Procedure

 2.5 Machine-based Face Detection

2.5.1 Face Detection Categories

 2.6 Machine-based Face Tracking

 2.7 Machine-based Face Recognition

2.7.1 Overview

2.7.2 Benchmark Studies of Face Recognition

2.7.3 Some General Terms Used in Face Recognition

2.7.4 Recognition Procedures and Methods

2.7.5 Video-based Recognition

2.7.6 Unsupervised and Fully Automatic Approaches

 2.8 Summary and Discussions

 References

3 Combined Face Detection and Tracking Methods

 3.1 Introduction

 3.2 Image-based Face Detection

3.2.1 Choice of the Detection Algorithm

3.2.2 Overview of the Detection Algorithm

3.2.3 Face Region Estimation

3.2.4 Face Detection Quality

 3.3 Temporal-based Face Detection

3.3.1 Overview

3.3.2 Search Region Estimation

3.3.3 Analysis of Temporal Changes

 3.4 Summary

 3.5 Further Discussions

 References

4 Automatic Face Recognition

 4.1 Overview

 4.2 Feature Extraction and Encoding

 4.3 Matching/Classification

4.3.1 Image-based Classifier

4.3.2 Adaptive Similarity Threshold

4.3.3 Temporal Filtering

 4.4 Combined Same Face Decision Algorithms

 4.5 Summary

 References

5 Unsupervised Face Database Construction

 5.1 Introduction

 5.2 Backgrounds for Constructing Face Databases

5.2.1 Supervised Learning

5.2.2 Unsupervised Learning

5.2.3 Clustering Analysis

 5.3 Database Structure

5.3.1 A Fused Clustering Method

5.3.2 Parameters in the Proposed Structure

 5.4 Features of an Optimum Database

 References

6 State Machine Based Automatic Procedure

 6.1 Introduction

 6.2 States Explorations

7 System Implementation

 7.1 Introduction

 7.2 Typical Hardware Configuration

 7.3 Software Implementation

7.3.1 Overview

7.3.2 Implementation Efforts

 7.4 Technology Dependent Parameters

 7.5 Summary

 References

8 Performance Analysis

 8.1 Introduction

 8.2 Performance of Face Detection

 8.3 Performance of Face Recognition

 8.4 Performance of Database Construction Algorithms

 8.5 Overall Performance of the Whole System

8.5.1 Online Version

8.5.2 Offline Version

8.5.3 Critical Assumptions

 8.6 Summary

 References

9 Conclusions and Future Directions

 9.1 Conclusions

 9.2 Future Directions

Index