Dictionary learning from phaseless measurements

Abstract : We propose a new algorithm to learn a dictionary along with sparse representations from signal measurements without phase. Specifically, we consider the task of reconstructing a two-dimensional image from squared-magnitude measurements of a complex-valued linear transformation of the original image. Several recent phase retrieval algorithms exploit underlying sparsity of the unknown signal in order to improve recovery performance. In this work, we consider sparse phase retrieval when the sparsifying dictionary is not known in advance, and we learn a dictionary such that each patch of the reconstructed image can be sparsely represented. Our numerical experiments demonstrate that our proposed scheme can obtain significantly better reconstructions for noisy phase retrieval problems than methods that cannot exploit such " hidden " sparsity.
Type de document :
Communication dans un congrès
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Mar 2016, Shanghai, China. IEEE, pp.4702-4706, 2016, <10.1109/ICASSP.2016.7472569>
Liste complète des métadonnées


https://hal.inria.fr/hal-01387416
Contributeur : Julien Mairal <>
Soumis le : mardi 25 octobre 2016 - 15:18:56
Dernière modification le : lundi 7 novembre 2016 - 09:43:24

Fichier

tillmann.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Andreas Tillmann, Yonina Eldar, Julien Mairal. Dictionary learning from phaseless measurements. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Mar 2016, Shanghai, China. IEEE, pp.4702-4706, 2016, <10.1109/ICASSP.2016.7472569>. <hal-01387416>

Partager

Métriques

Consultations de
la notice

299

Téléchargements du document

273