Boosting-based face detection and adaptation
By: Zhang, Cha.
Contributor(s): Zhang, Zhengyou.
Material type:
BookSeries: Synthesis digital library of engineering and computer science: ; Synthesis lectures on computer vision: # 2.Publisher: San Rafael, Calif. (1537 Fourth Street, San Rafael, CA 94901 USA) : Morgan & Claypool, c2010Description: 1 electronic text (x, 128 p. : ill.) : digital file.ISBN: 9781608451340 (electronic bk.).Subject(s): Human face recognition (Computer science) -- Mathematical models | face detection | boosting | multiple instance learning | adaptation | multiple task learning | multimodal fusionDDC classification: 006.42 Online resources: Abstract with links to resource Also available in print.| Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
|---|---|---|---|---|---|---|
E books
|
PK Kelkar Library, IIT Kanpur | Available | EBKE283 |
Mode of access: World Wide Web.
System requirements: Adobe Acrobat Reader.
Part of: Synthesis digital library of engineering and computer science.
Series from website.
Includes bibliographical references (p. 113-126).
1. A brief survey of the face detection literature -- Introduction -- The Viola-Jones face detector -- The integral image -- AdaBoost learning -- The attentional cascade structure -- Recent advances in face detection -- Feature extraction -- Variations of the boosting learning algorithm -- Other learning schemes -- Book overview --
2. Cascade-based real-time face detection -- Soft-cascade training -- Fat stumps -- Multiple instance pruning -- Pruning using the final classification -- Multiple instance pruning -- Experimental results --
3. Multiple instance learning for face detection -- MILboost -- Noisy-or MILboost -- ISR MILboost -- Application of MILboost to low resolution face detection -- Multiple category boosting -- Probabilistic McBoost -- Winner-take-all McBoost -- Experimental results -- A practical multi-view face detector --
4. Detector adaptation -- Problem formulation -- Parametric learning -- Detector adaptation -- Taylor-expansion-based adaptation -- Adaptation of logistic regression classifiers -- Logistic regression -- Adaptation of logistic regression classifier -- Direct labels -- Similarity labels -- Adaptation of boosting classifiers -- Discussions and related work -- Experimental results -- Results on direct labels -- Results on similarity labels --
5. Other applications -- Face verification with boosted multi-task learning -- Introduction -- AdaBoosting LBP -- Boosted multi-task learning -- Experimental results -- Boosting-based multimodal speaker detection -- Introduction -- Related works -- Sound source localization -- Boosting-based multimodal speaker detection -- Merge of detected windows -- Alternative speaker detection algorithms -- Experimental results --
6. Conclusions and future work -- Bibliography -- Authors' biographies.
Abstract freely available; full-text restricted to subscribers or individual document purchasers.
Compendex
INSPEC
Google scholar
Google book search
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.
Also available in print.
Title from PDF t.p. (viewed on October 13, 2010).
There are no comments for this item.