HIERARCHICAL OBJECT CLASSIFICATION USING IMAGENET DOMAIN ONTOLOGIES

Haider Ali

2010

Abstract

We present a binary tree based object classification method in this paper. The binary tree builds a group of classes using ImageNet domain ontologies. A binary decision function is introduced in the root node of the decision tree using the positive samples of the first group for training. The decision function continues dividing the groups in sub-sequent groups when approaching the leaf nodes and provides positive and negative samples for multi-class problems. We have tested our method on the PASCAL Visual Object Classes Challenge 2006 (VOC2006) dataset and have achieved comparable accuracy for group classification. The results show that the proposed method is a powerful class binarization technique for hierarchical objects group classification.

Paper Citation

in Harvard Style

Ali H. (2010). HIERARCHICAL OBJECT CLASSIFICATION USING IMAGENET DOMAIN ONTOLOGIES . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 534-536. DOI: 10.5220/0002851905340536

in Bibtex Style

@conference{visapp10,
author={Haider Ali},
title={HIERARCHICAL OBJECT CLASSIFICATION USING IMAGENET DOMAIN ONTOLOGIES},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={534-536},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002851905340536},
isbn={978-989-674-029-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)
TI - HIERARCHICAL OBJECT CLASSIFICATION USING IMAGENET DOMAIN ONTOLOGIES
SN - 978-989-674-029-0
AU - Ali H.
PY - 2010
SP - 534
EP - 536
DO - 10.5220/0002851905340536