Maximum likelihood estimates for object detection using multiple detectors

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

Abstract

Object detection in real images has attracted much attention during the last decade. Using machine learning and large databases it is possible to develop detectors for visual categories that have a very high hit-rate, with low false positive rates. In this paper we investigate a general probabilistic framework for context based scene interpretation using multiple detectors. Methods for finding maximum likelihood estimates of scenes given detection results are presented. Although we have investigated how the method works for a specific case, namely for face detection, it is a general method. We show how to combine the results of a number of detectors i.e. face, eye, nose and mouth detectors. The methods have been tested using detectors trained on real images, with promising results.
Original languageEnglish
Title of host publicationStructural, Syntactic, and Statistical Pattern Recognition, Proceedings (
PublisherSpringer
Pages658-666
Volume4109
ISBN (Print)978-3-540-37236-3
DOIs
Publication statusPublished - 2006
EventJoint IAPR International Workshops, SSPR 2006 and SPR 2006 - Hong Kong, China
Duration: 2006 Aug 172006 Aug 19

Publication series

Name
Volume4109
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceJoint IAPR International Workshops, SSPR 2006 and SPR 2006
Country/TerritoryChina
CityHong Kong
Period2006/08/172006/08/19

Subject classification (UKÄ)

  • Mathematics

Fingerprint

Dive into the research topics of 'Maximum likelihood estimates for object detection using multiple detectors'. Together they form a unique fingerprint.

Cite this