Learning to classify materials using Mueller imaging polarimetry

Yvain Quéau (1) , Florian Leporcq (2) , Alexis Lechervy (1) , Ayman Alfalou (3)

1 Equipe Image - Laboratoire GREYC - UMR6072
2 ENSEEIHT - Ecole Nationale Supérieure d'Electrotechnique, d'Electronique, d'Informatique, d'Hydraulique et de Télécommunications
3 L@BISEN - Laboratoire ISEN

This study investigates the combination of Mueller imaging polarimetry with machine learning for the automated optical classication of raw materials. It shows that standard image classication techniques based on support vector machines or deep neural networks can readily be applied to polarimetric data extracted from Mueller matrix measurements. The feasability of such an approach is empirically demonstrated through the classication of multispectral depolarization images of real-world materials (banana, wood and foam samples).

Mots clés: Material classication; polarimetry; Mueller imaging; machine learning; deep neural networks

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Yvain Quéau, Florian Leporcq, Alexis Lechervy, Ayman Alfalou. Learning to classify materials using Mueller imaging polarimetry. Fourteenth International Conference on Quality Control by Artificial Vision (QCAV), May 2019, Mulhouse, France. ⟨hal-02088951v1⟩