Fourier Phase Retrieval With Extended Support Estimation via Deep Neural Network

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 19
  • Download : 0
We consider the problem of sparse phase retrieval from Fourier transform magnitudes to recover the k-sparse signal vector and its support T. We exploit extended support estimate epsilon with size larger than k satisfying epsilon superset of T and obtained by a trained deep neural network (DNN). To make the DNN learnable, it provides epsilon as the union of equivalent solutions of T by utilizing modulo Fourier invariances. Set epsilon can be estimated with short running time via the DNN, and support T can he determined from the DNN output rather than from the full index set by applying hard thresholding to epsilon. Thus, the DNN-based extended support estimation improves the reconstruction performance of the signal with a low complexity burden dependent on k. Numerical results verify that the proposed scheme has a superior performance with lower complexity compared to local search-based greedy sparse phase retrieval and a state-of-the-art variant of the Fienup method.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2019-10
Language
English
Article Type
Article
Citation

IEEE SIGNAL PROCESSING LETTERS, v.26, no.10, pp.1506 - 1510

ISSN
1070-9908
DOI
10.1109/LSP.2019.2935814
URI
http://hdl.handle.net/10203/267732
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0