Morphological Texture Description from Multispectral Skin Images in Cosmetology

Joris Corvo (1, 2) , Jesus Angulo (1) , Josselin Breugnot (2) , Sylvie Bordes (2) , Brigitte Closs (2)

1 CMM - Centre de Morphologie Mathématique
2 SILAB

In this paper, we propose methods to extract texture features from multispectral skin images. We first describe the acquisition protocol and corrections we applied on multispectral skin images. In the framework of a cosmetology application, a skin morphological texture evaluation is then proposed using either multivariate approach on multispectral dataset or marginal on a dataset whose dimensionality has been reduced by a multivariate analysis based on PCA.

Mots clés: Multispectral imaging; mathematical morphology; texture analysis; cosmetology

Domaines: Informatique [cs]; Traitement des images [eess.IV]

Joris Corvo, Jesus Angulo, Josselin Breugnot, Sylvie Bordes, Brigitte Closs. Morphological Texture Description from Multispectral Skin Images in Cosmetology. 13th International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing, May 2017, Fontainebleau, France. pp.443 - 477, ⟨10.1007/978-3-319-57240-6_38⟩. ⟨hal-01536371⟩