Title:
Fast Asymmetric Learning for Cascade Face Detection
Fast Asymmetric Learning for Cascade Face Detection
Files
Author(s)
Wu, Jianxin
Brubaker, S. Charles
Mullin, Matthew D.
Rehg, James M.
Brubaker, S. Charles
Mullin, Matthew D.
Rehg, James M.
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
A cascade face detector uses a sequence of node classifiers to distinguish faces from non-faces. This paper presents a new approach to design node classifiers in the cascade detector. Previous methods used machine learning algorithms that simultaneously select features and form ensemble classifiers. We argue that if these two parts are decoupled, we have the freedom to design a classifier that explicitly addresses the difficulties caused by the asymmetric learning goal. There are three contributions in this paper. The first is a categorization of asymmetries in the learning goal, and why they make face detection hard. The second is the Forward Feature Selection (FFS) algorithm and a fast caching strategy for AdaBoost. FFS and the fast AdaBoost can reduce the training time by approximately 100 and 50 times, in comparison to a naive implementation of the AdaBoost feature selection method. The last contribution is Linear Asymmetric Classifier (LAC), a classifier that explicitly handles the asymmetric learning goal as a well-defined constrained optimization problem. We demonstrated experimentally that LAC results in improved ensemble classifier performance.
Sponsor
Date Issued
2005
Extent
840931 bytes
Resource Type
Text
Resource Subtype
Technical Report