eCite Digital Repository

Learnt Combination in Object Detector Ensembles

Citation

Neugebauer, C and Cameron-Jones, RM and Horton, MP, Learnt Combination in Object Detector Ensembles, Proceedings of Image and Vision Computing New Zealand (IVCNZ) 2010, 8-9 Nov 2010, Queenstown, New Zealand, pp. 1-8. ISBN 978-1-4244-9629-7 (2010) [Refereed Conference Paper]

Copyright Statement

Copyright 2010 IEEE

DOI: doi:10.1109/IVCNZ.2010.6148791

Abstract

This paper considers the application of meta-classification techniques to the task of object detection. The technique of learnt combination is presented and evaluated in the domain of face detection: in the case of an ensemble of greyscale detectors it is shown to be as effective as pre-existing ensemble detection techniques. It is shown that considering detectors operating on different colour channels can improve performance; to exploit this, a method for selecting appropriate colour channels is also presented. Also presented is a new data set for training and evaluating colour-based face detectors.

Item Details

Item Type:Refereed Conference Paper
Keywords:Object detection, ensemble classification, meta-classification, face detection
Research Division:Information and Computing Sciences
Research Group:Artificial Intelligence and Image Processing
Research Field:Computer Vision
Objective Division:Expanding Knowledge
Objective Group:Expanding Knowledge
Objective Field:Expanding Knowledge in the Information and Computing Sciences
Author:Neugebauer, C (Mr Christopher Neugebauer)
Author:Cameron-Jones, RM (Dr Mike Cameron-Jones)
Author:Horton, MP (Mr Michael Horton)
ID Code:76039
Year Published:2010
Deposited By:Computing and Information Systems
Deposited On:2012-02-23
Last Modified:2012-12-12
Downloads:0

Repository Staff Only: item control page