HUMAN FACE VERIFICATION BASED ON MULTIDIMENSIONAL POLYNOMIAL POWERS OF SIGMOID (PPS)

João Fernando Marar, Helder Coelho

Abstract

In this paper, we described how a multidimensional wavelet neural networks based on Polynomial Powers of Sigmoid (PPS) can be constructed, trained and applied in image processing tasks. In this sense, a novel and uniform framework for face verification is presented. The framework is based on a family of PPS wavelets,generated from linear combination of the sigmoid functions, and can be considered appearance based in that features are extracted from the face image. The feature vectors are then subjected to subspace projection of PPS-wavelet. The design of PPS-wavelet neural networks is also discussed, which is seldom reported in the literature. The Stirling Universitys face database were used to generate the results. Our method has achieved 92 % of correct detection and 5 % of false detection rate on the database.

Download


Paper Citation


in Harvard Style

Fernando Marar J. and Coelho H. (2008). HUMAN FACE VERIFICATION BASED ON MULTIDIMENSIONAL POLYNOMIAL POWERS OF SIGMOID (PPS) . In Proceedings of the First International Conference on Health Informatics - Volume 2: HEALTHINF, (BIOSTEC 2008) ISBN 978-989-8111-16-6, pages 99-106. DOI: 10.5220/0001042800990106


in Bibtex Style

@conference{healthinf08,
author={João Fernando Marar and Helder Coelho},
title={HUMAN FACE VERIFICATION BASED ON MULTIDIMENSIONAL POLYNOMIAL POWERS OF SIGMOID (PPS)},
booktitle={Proceedings of the First International Conference on Health Informatics - Volume 2: HEALTHINF, (BIOSTEC 2008)},
year={2008},
pages={99-106},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001042800990106},
isbn={978-989-8111-16-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Health Informatics - Volume 2: HEALTHINF, (BIOSTEC 2008)
TI - HUMAN FACE VERIFICATION BASED ON MULTIDIMENSIONAL POLYNOMIAL POWERS OF SIGMOID (PPS)
SN - 978-989-8111-16-6
AU - Fernando Marar J.
AU - Coelho H.
PY - 2008
SP - 99
EP - 106
DO - 10.5220/0001042800990106