Learning to Detect Objects of Many Classes Using Binary Classifiers
- Ramana Isukapalli
- Ahmed Elgammal, Rutgers University
- Russ Greiner, Dept of Computing Science; PI of AICML
Viola and Jones [VJ] demonstrate that cascade classification methods can successfully detect objects belonging to a single class, such as faces. Detecting and identifying objects that belong to any of a set ofViola and Jones [VJ] demonstrate that cascade classification methods can successfully detect objects belonging to a single class, such as faces. Detecting and identifying objects that belong to any of a set of “classes”, many class detection, is a much more challenging problem. We show that objects from each class can form a “cluster” in a “classifier space” and illustrate examples of such clusters using images of real world objects. Our detection algorithm uses a “decision tree classifier” (whose internal nodes each correspond to a VJ classifier) to propose a class label for every sub-image W of a test image (or reject it as a negative instance). If this W reaches a leaf of this tree, we then passW through a subsequent VJ cascade of classifiers, specific to the identified class, to determine whether W is truly an instance of the proposed class. We perform several empirical studies to compare our system for detecting objects of any of M classes, to the obvious approach of running a set of M learned VJ cascade classifiers, one for each class of objects, on the same image. We found that the detection rates are comparable, and our many-class detection system is about as fast as running a single VJ cascade, and it scales up well as the number of classes increases.
Citation
R. Isukapalli, A. Elgammal, R. Greiner. "Learning to Detect Objects of Many Classes Using Binary Classifiers". European Conference on Computer Vision (ECCV), Graz, Austria, May 2006.| Keywords: | face recognition, MDP, image understanding, machine learning |
| Category: | In Conference |
BibTeX
@incollection{Isukapalli+al:ECCV06,
author = {Ramana Isukapalli and Ahmed Elgammal and Russ Greiner},
title = {Learning to Detect Objects of Many Classes Using Binary Classifiers},
booktitle = {European Conference on Computer Vision (ECCV)},
year = 2006,
}Last Updated: April 23, 2007Submitted by Nelson Loyola
