Show simple item record

dc.contributor.authorLi, Shuai
dc.contributor.authorBarbastathis, George
dc.date.accessioned2019-03-19T13:39:12Z
dc.date.available2019-03-19T13:39:12Z
dc.date.issued2018-10
dc.date.submitted2018-09
dc.identifier.issn1094-4087
dc.identifier.urihttp://hdl.handle.net/1721.1/121038
dc.description.abstractThe phase extraction neural network (PhENN) [Optica 4, 1117 (2017)] is a computational architecture, based on deep machine learning, for lens-less quantitative phase retrieval from raw intensity data. PhENN is a deep convolutional neural network trained through examples consisting of pairs of true phase objects and their corresponding intensity diffraction patterns; thereafter, given a test raw intensity pattern, PhENN is capable of reconstructing the original phase object robustly, in many cases even for objects outside the database where the training examples were drawn from. Here, we show that the spatial frequency content of the training examples is an important factor limiting PhENN's spatial frequency response. For example, if the training database is relatively sparse in high spatial frequencies, as most natural scenes are, PhENN's ability to resolve fine spatial features in test patterns will be correspondingly limited. To combat this issue, we propose "flattening" the power spectral density of the training examples before presenting them to PhENN. For phase objects following the statistics of natural scenes, we demonstrate experimentally that the spectral pre-modulation method enhances the spatial resolution of PhENN by a factor of 2.en_US
dc.description.sponsorshipSingapore-MIT Alliance (015824)en_US
dc.description.sponsorshipUnited States. Office of the Director of National Intelligence. Rapid Analysis of Various Emerging Nanoelectronics (FA8650-17-C-9113)en_US
dc.publisherOptical Society of Americaen_US
dc.relation.isversionofhttp://dx.doi.org/10.1364/OE.26.029340en_US
dc.rightsArticle is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.en_US
dc.sourceOSA Publishingen_US
dc.titleSpectral pre-modulation of training examples enhances the spatial resolution of the phase extraction neural network (PhENN)en_US
dc.typeArticleen_US
dc.identifier.citationLi, Shuai, and George Barbastathis. “Spectral Pre-Modulation of Training Examples Enhances the Spatial Resolution of the Phase Extraction Neural Network (PhENN).” Optics Express 26, no. 22 (October 25, 2018): 29340.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mechanical Engineeringen_US
dc.contributor.mitauthorLi, Shuai
dc.contributor.mitauthorBarbastathis, George
dc.relation.journalOptics Expressen_US
dc.eprint.versionFinal published versionen_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dc.date.updated2019-03-01T12:46:35Z
dspace.orderedauthorsLi, Shuai; Barbastathis, Georgeen_US
dspace.embargo.termsNen_US
dc.identifier.orcidhttps://orcid.org/0000-0002-7836-0431
dc.identifier.orcidhttps://orcid.org/0000-0002-4140-1404
mit.licensePUBLISHER_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record