Boosting-Based Face Detection and Adaptation (Paperback)

Author: Zhang, Cha

Customer Reviews   Write a Review

Be the first to review this item and earn 25 Rakuten Super Points™

Product Overview

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 thresh-olds 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.

We then present two multiple instance learning schemes for face detection, multiple instance learning boosting (MILBoost) and winner-take-all multiple category boosting (WTA-McBoost). MIL Boost addresses the uncertainty in accurately pinpointing the location of the object being detected, while WTA-McBoost addresses the uncertainty in determining the most appropriate subcategory label for multiview object detection. Both schemes can resolve the ambiguity of the labeling process and reduce outliers during training, which leads to improved detector performances.

In many applications, a detector trained with generic data sets may not perform optimally in a new environment. We propose detection adaption, which is a promising solution for this problem. We present an adaptation scheme based on the Taylor expansion of the boosting learning objective function, and we propose to store the second order statistics of the generic training data for future adaptation. We show that with a small amount of labeled data in the new environment, the detector's performance can be greatly improved.

We also present two interesting applications where boosting learning was applied successfully. The first application is face verification for filtering and ranking image/video search results on celebrities. We present boosted multi-task learning (MTL), yet another boosting learning algorithm that extends MILBoost with a graphical model. Since the available number of training images for each celebrity may be limited, learning individual classifiers for each person may cause overfitting. MTL jointly learns classifiers for multiple people by sharing a few boosting classifiers in order to avoid overfitting. The second application addresses the need of speaker detection in conference rooms. The goal is to find who is speaking, given a microphone array and a panoramic video of the room. We show that by combining audio and visual features in a boosting framework, we can determine the speaker's position very accurately.

Finally, we offer our thoughts on future directions for face detection.

Specifications

Publisher Morgan & Claypool
Mfg Part# 9781608451333
SKU 211436113
Format Paperback
ISBN10 160845133X
Release Date 8/13/2012
loading
$48.89 + free shipping
Rakuten Super Points Earn 49 ($0.49) Rakuten Super Points™
What are Rakuten Super Points™?
Get rewarded when you shop! Earn 1 point per dollar spent. That's like getting cash back on every purchase. Easy to see matured points in checkout. Use points just like cash.
Learn More
Get this item for
(price with shipping)
(redeem points)
Format: Paperback
Condition: Brand New
In Stock. Usually Ships in 1 to 2 business days
Please select an option to buy
Add to Cart

Sold By:  VNHM SHOP
What is a Marketplace and Shop Owner?
  • Our marketplace is a platform where approved third-party retailers (Shop Owners) can sell their products
  • Items are sold and shipped by Shop Owners
  • Your credit card and personal information remain secure; Rakuten.com meets all PCI Security Standards.
  • Purchases can only be returned to the Shop Owner
  • All purchases receive Rakuten Super Points™
ADVERTISEMENT
Promotions & Offers (1)
  •  custom promo
    5% Back* Sitewide with Promo Code Rewardme *See page for details
ADVERTISEMENT
ADVERTISEMENT