Analysis of human skin hyper-spectral images by non-negative matrix factorization

Abstract : This article presents the use of Non-negative Matrix Factorization, a blind source separation algorithm, for the decomposition of human skin absorption spectra in its main pigments: melanin and hemoglobin. The evaluated spectra come from a Hyper-Spectral Image, which is the result of the processing of a Multi-Spectral Image by a neural network-based algorithm. The implemented source separation algorithm is based on a multiplicative coeffi cient upload. The goal is to represent a given spectrum as the weighted sum of two spectral components. The resulting weighted coefficients are used to quantify melanin and hemoglobin content in the given spectra. Results present a degree of correlation higher than 90% compared to theoretical hemoglobin and melanin spectra. This methodology is validated on 35 melasma lesions from a population of 10 subjects.
Liste complète des métadonnées

Cited literature [21 references]  Display  Hide  Download
Contributor : Franck Marzani <>
Submitted on : Wednesday, February 20, 2013 - 3:37:28 PM
Last modification on : Wednesday, September 12, 2018 - 1:27:58 AM
Document(s) archivé(s) le : Tuesday, May 21, 2013 - 9:25:09 AM


Files produced by the author(s)


  • HAL Id : hal-00790466, version 1



July A Galeano Z, Romuald Jolivot, Franck Marzani. Analysis of human skin hyper-spectral images by non-negative matrix factorization. 10th Mexican International Conference on Artificial Intelligence, Nov 2011, Puebla, Mexico. pp.431-442. ⟨hal-00790466⟩



Record views


Files downloads