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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [26 references]  Display  Hide  Download

https://hal.inria.fr/hal-01387416
Contributor : Julien Mairal <>
Submitted on : Tuesday, October 25, 2016 - 3:18:56 PM
Last modification on : Wednesday, April 11, 2018 - 1:58:00 AM

File

tillmann.pdf
Files produced by the author(s)

Identifiers

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. pp.4702-4706, ⟨10.1109/ICASSP.2016.7472569⟩. ⟨hal-01387416⟩

Share

Metrics

Record views

491

Files downloads

500