Caractérisation de paramètres cosmétologiques à partir d'images multispectrales de peau

Abstract : Thanks to its precision in spatial and spectral domain, multispectral imaging has become an essential tool in dermatology. This thesis focuses on the interest of this technology for cosmetological parameters assessment through three different studies: the detection of a foundation make-up, age assessment and roughness measurement.A database of multispectral skin images is build using a multiple optical filters system. A preprocessing step allows to standardize those texture images before their exploitation.Covariance matrices of mutispectral acquisitions can be displayed in a multidimensional scaling space which is a novel way to represent multivariate data sets. Likewise, a new dimensionality reduction algorithm based on PCA is proposed in this thesis.A complete study of the images texture is performed: texture features from mathematical morphology and more generally from image analysis are expanded to the case of multivariate images. In this process, several spectral distances are tested, among which a new distance associating the LIP model to the Asplund metric.Statistical predictions are generated from texture data. Thoses predictions lead to a conclusion about the data processing efficiency and the relevance of multispectral imaging for the three cosmetologic studies.
Document type :
Theses
Complete list of metadatas

Cited literature [196 references]  Display  Hide  Download

https://pastel.archives-ouvertes.fr/tel-01831159
Contributor : Abes Star <>
Submitted on : Thursday, July 5, 2018 - 4:29:06 PM
Last modification on : Wednesday, May 15, 2019 - 10:22:07 AM
Long-term archiving on : Monday, October 1, 2018 - 6:41:44 PM

File

2016PSLEM100_archivage.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01831159, version 1

Citation

Joris Corvo. Caractérisation de paramètres cosmétologiques à partir d'images multispectrales de peau. Traitement du signal et de l'image [eess.SP]. PSL Research University, 2016. Français. ⟨NNT : 2016PSLEM100⟩. ⟨tel-01831159⟩

Share

Metrics

Record views

162

Files downloads

34