CATEGORIZATION OF SIMILAR OBJECTS USING BAG OF VISUAL WORDS AND SUPPORT VECTOR MACHINES

Przemysław Górecki, Piotr Artiemjew, Paweł Drozda, Krzysztof Sopyła

2012

Abstract

This paper studies the problem of visual subcategorization of objects within a larger category. Such categorization seems more challenging than categorization of objects from visually distinctive categories, previously presented in the literature. The proposed methodology is based on ”Bag of Visual Words” using Scale-Invariant Feature Transform (SIFT) descriptors and Support Vector Machines (SVM). We present the results of the experimental session, both for categorization of visually similar and visually distinctive objects. In addition, we attempt to empirically identify the most effective visual dictionary size and the feature vector normalization scheme.

Download


Paper Citation


in Harvard Style

Górecki P., Artiemjew P., Drozda P. and Sopyła K. (2012). CATEGORIZATION OF SIMILAR OBJECTS USING BAG OF VISUAL WORDS AND SUPPORT VECTOR MACHINES . In Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-8425-95-9, pages 231-236. DOI: 10.5220/0003714702310236

in Bibtex Style

@conference{icaart12,
author={Przemysław Górecki and Piotr Artiemjew and Paweł Drozda and Krzysztof Sopyła},
title={CATEGORIZATION OF SIMILAR OBJECTS USING BAG OF VISUAL WORDS AND SUPPORT VECTOR MACHINES},
booktitle={Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2012},
pages={231-236},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003714702310236},
isbn={978-989-8425-95-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - CATEGORIZATION OF SIMILAR OBJECTS USING BAG OF VISUAL WORDS AND SUPPORT VECTOR MACHINES
SN - 978-989-8425-95-9
AU - Górecki P.
AU - Artiemjew P.
AU - Drozda P.
AU - Sopyła K.
PY - 2012
SP - 231
EP - 236
DO - 10.5220/0003714702310236