A deep spatial/spectral descriptor of hyperspectral texture using scattering transform

Gianni Franchi (1) , Jesus Angulo (1)

1 CMM - Centre de Morphologie Mathématique

A technique to describe the spatial / spectral features of hyperspectral images is introduced. These descriptors aim at representing the content of the image while considering invariances related to the texture and to its geometric transformations, so called spatial invariances. Moreover, we also consider spectral invariances which are related to the composition of the pixels. Our approach is based on the scattering transform, which provides an useful framework for deep learning classification. The goal through these descriptors is to improve pixel-wise classification of hyperspectral images.

Mots clés: computer vision; hyperspectral images; pixel-wise classification; deep learning; wavelet transform

Domaines: Traitement des images [eess.IV]

Gianni Franchi, Jesus Angulo. A deep spatial/spectral descriptor of hyperspectral texture using scattering transform. 2016 IEEE International Conference on Image Processing (ICIP), Sep 2016, Phoenix, United States. ⟨10.1109/ICIP.2016.7533024⟩. ⟨hal-01446966⟩