LISF: An Invariant Local Shape Features Descriptor Robust to Occlusion

Leonardo Chang, Miguel Arias-Estrada, L. Enrique Sucar, José Hernández-Palancar

2014

Abstract

In this work an invariant shape features extraction, description and matching method (LISF) for binary images is proposed. In order to balance the discriminative power and the robustness to noise and occlusion in the contour, local features are extracted from contour to describe shape, which are later matched globally. The proposed extraction, description and matching methods are invariant to rotation, translation, and scale and present certain robustness to partial occlusion. Its invariability and robustness are validated by the performed experiments in shape retrieval and classification tasks. Experiments were carried out in the Shape99, Shape216, and MPEG-7 datasets, where different artifacts were artificially added to obtain partial occlusion as high as 60%. For the highest occlusion levels the proposed method outperformed other popular shape description methods, with about 20% higher bull’s eye score and 25% higher accuracy in classification.

Paper Citation

in Harvard Style

Chang L., Arias-Estrada M., Sucar L. and Hernández-Palancar J. (2014). LISF: An Invariant Local Shape Features Descriptor Robust to Occlusion . In Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-018-5, pages 429-437. DOI: 10.5220/0004825504290437

in Bibtex Style

@conference{icpram14,
author={Leonardo Chang and Miguel Arias-Estrada and L. Enrique Sucar and José Hernández-Palancar},
title={LISF: An Invariant Local Shape Features Descriptor Robust to Occlusion},
booktitle={Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2014},
pages={429-437},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004825504290437},
isbn={978-989-758-018-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - LISF: An Invariant Local Shape Features Descriptor Robust to Occlusion
SN - 978-989-758-018-5
AU - Chang L.
AU - Arias-Estrada M.
AU - Sucar L.
AU - Hernández-Palancar J.
PY - 2014
SP - 429
EP - 437
DO - 10.5220/0004825504290437