COMPARATIVE STUDY OF BLIND SOURCE SEPARATION METHODS FOR RAMAN SPECTRA - Application on Numerical Dewaxing of Cutaneous Biopsies

Valeriu Vrabie, Cyril Gobinet, Michel Herbin, Michel Manfait

Abstract

Raman spectroscopy is a powerful tool for the study of molecular composition of biological samples. Digital processing techniques are needed to separate the wealthy but complex information recorded by Raman spectra. Blind source separation methods can be used to efficiently extract the spectra of chemical constituents. We propose in this study to analyze the performances of four blind source separation methods. Two Independent Component Analysis methods using the JADE and FastICA algorithms are based uniquely on the independence of the spectra. The Non-Negative Matrix Factorization takes into account only the positivity of underlying spectra and mixing coefficients. The Maximum Likelihood Positive Source Separation assumes both the independence and positivity of the spectra. A realistic simulated dataset allows a quantitative study of these methods while a real dataset recorded on a paraffin-embedded skin biopsy provides a qualitative study.

Download


Paper Citation


in Harvard Style

Vrabie V., Gobinet C., Herbin M. and Manfait M. (2008). COMPARATIVE STUDY OF BLIND SOURCE SEPARATION METHODS FOR RAMAN SPECTRA - Application on Numerical Dewaxing of Cutaneous Biopsies . In Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008) ISBN 978-989-8111-18-0, pages 349-354. DOI: 10.5220/0001064903490354


in Bibtex Style

@conference{biosignals08,
author={Valeriu Vrabie and Cyril Gobinet and Michel Herbin and Michel Manfait},
title={COMPARATIVE STUDY OF BLIND SOURCE SEPARATION METHODS FOR RAMAN SPECTRA - Application on Numerical Dewaxing of Cutaneous Biopsies},
booktitle={Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)},
year={2008},
pages={349-354},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001064903490354},
isbn={978-989-8111-18-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)
TI - COMPARATIVE STUDY OF BLIND SOURCE SEPARATION METHODS FOR RAMAN SPECTRA - Application on Numerical Dewaxing of Cutaneous Biopsies
SN - 978-989-8111-18-0
AU - Vrabie V.
AU - Gobinet C.
AU - Herbin M.
AU - Manfait M.
PY - 2008
SP - 349
EP - 354
DO - 10.5220/0001064903490354