Face detection, because of its vast array of applications, is one of the most active research areas in computer vision. In this book, we review various approaches to face detection developed in the past decade, with more emphasis on boosting-based learning algorithms. We then present a series of algorithms that are empowered by the statistical view of boosting and the concept of multiple instance learning. We start by describing a boosting learning framework that is capable to handle billions of training examples. It differs from traditional bootstrapping schemes in that no intermediate thresholds need to be set during training, yet the total number of negative examples used for feature selection remains constant and focused (on the poor performing ones). A multiple instance pruning scheme is then adopted to set the intermediate thresholds after boosting learning. This algorithm generates detectors that are both fast and accurate. Table of Contents: A Brief Survey of the Face Detection Literature / Cascade-based Real-Time Face Detection / Multiple Instance Learning for Face Detection / Detector Adaptation / Other Applications / Conclusions and Future Work
Author(s): Cha Zhang, Zhengyou Zhang
Series: Synthesis Lectures on Computer Vision #2
Publisher: Morgan and Claypool Publishers
Year: 2010
Language: English
Pages: 140
Tags: Информатика и вычислительная техника;Обработка медиа-данных;Обработка изображений;
Preface......Page 11
Introduction......Page 13
The Integral Image......Page 14
AdaBoost Learning......Page 15
The Attentional Cascade Structure......Page 18
Feature Extraction......Page 19
Variations of the Boosting Learning Algorithm......Page 26
Other Learning Schemes......Page 34
Book Overview......Page 37
Cascade-based Real-Time Face Detection......Page 41
Soft-Cascade Training......Page 42
Fat Stumps......Page 46
Pruning Using the Final Classification......Page 48
Multiple Instance Pruning......Page 51
Experimental Results......Page 52
Multiple Instance Learning for Face Detection......Page 57
Noisy-OR MILBoost......Page 58
ISR MILBoost......Page 60
Application of MILBoost to Low Resolution Face Detection......Page 62
Multiple Category Boosting......Page 66
Probabilistic McBoost......Page 67
Winner-Take-All McBoost......Page 69
Experimental Results......Page 72
A Practical Multi-view Face Detector......Page 75
Detector Adaptation......Page 81
Detector Adaptation......Page 82
Taylor-Expansion-Based Adaptation......Page 83
Adaptation of Logistic Regression Classifier......Page 84
Direct Labels......Page 85
Similarity Labels......Page 86
Adaptation of Boosting Classifiers......Page 87
Discussions and Related Work......Page 88
Experimental Results......Page 89
Results on Direct Labels......Page 90
Results on Similarity Labels......Page 92
Introduction......Page 95
AdaBoosting LBP......Page 97
Boosted Multi-Task Learning......Page 99
Experimental Results......Page 102
Introduction......Page 106
Related Works......Page 107
Sound Source Localization......Page 108
Boosting-Based Multimodal Speaker Detection......Page 110
Merge of Detected Windows......Page 112
Alternative Speaker Detection Algorithms......Page 113
Experimental Results......Page 114
Conclusions and Future Work......Page 123
Bibliography......Page 125
Authors' Biographies......Page 139
