Show simple item record

dc.contributor.authorBlack, Jacob A.en
dc.date.accessioned2019-08-26T14:58:47Zen
dc.date.available2019-08-26T14:58:47Zen
dc.date.issued2019en
dc.identifier.urihttp://hdl.handle.net/10919/93263en
dc.description.abstractNeural Networks (NNs) (or 'deep' neural networks (DNNs)) have found great success in many applications across all fields of engineering, and in particular have found recent success in the field of Photonics. In this work we discuss the application of NNs to optical interferometry for the purpose of quantitative phase imaging (QPI). We show that NNs are capable of quantifying the optical pathlength difference in an interferogram with sensitivities that achieve the fundamental limit given by the Cramér-Rao bound (CRB). As an application, we consider a particular QPI technique known as wavelength shifting interferometry (WSI) which obtains the OPL by acquiring multiple interferograms at different, evenly spaced wavenumbers. Traditional phase demodulation algorithms for WSI fail to reach the theoretical OPL sensitivity limit set by the CRB. We have designed NNs which are capable of achieving this bound across a wide range of OPL differences. The NNs are trained on simulated data, and then applied to experimental data. In both simulation and experiment, the NNs outperform the existing analytical demodulation techniques and provide highly sensitive signal demodulation in cases where the analytical approach fails. Thus, NNs provide better performance and more flexibility in the design and use of a WSI system. We expect that the techniques developed in this work can be extended to other two-beam interference based QPI system.en
dc.format.mediumETDen
dc.language.isoen_USen
dc.publisherVirginia Techen
dc.rightsCreative Commons Attribution-NonCommercial-NoDerivs 3.0 United Statesen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/en
dc.subjectPhase imagingen
dc.subjectNeural Networksen
dc.subjectMachine learningen
dc.subjectBiological Imagingen
dc.titleNeural Networks For Phase Demodulation In Optical Interferometryen
dc.typeThesisen
dc.contributor.departmentElectrical and Computer Engineeringen
dc.description.degreeM.S.en
thesis.degree.nameM.S.en
thesis.degree.levelmastersen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.disciplineElectrical Engineeringen
dc.contributor.committeechairZhu, Yizhengen
dc.contributor.committeememberZhu, Yunhuien
dc.contributor.committeememberHuang, Jia-Binen
dc.contributor.committeememberPoon, Ting-Chungen
dc.contributor.committeememberSafaai-Jazi, Ahmaden
dc.description.abstractgeneralNeural Networks (NNs) (or 'deep' neural networks (DNNs)) have found great success in many applications across all fields of engineering, and in particular have found recent success in the field of Photonics. In this work we discuss the application of NNs to making so-called 'phase' images of biological cells and tissues (e.g. red blood cells, sperm cells). This is necessary for many biological samples which are transparent under traditional bright field microscopy. We show that NNs are capable of quantifying the phase of these samples to produce images with higher contrast than possible in a typical microscope image. As an example, we introduce a particular phase microscopy system and study the application of NNs to this system. We show that the NNs are capable of providing solutions for this phase in situations where existing analytical techniques fail. The NNs are also capable of making more precise calculations of the phase than the traditional algorithms in many situations where either technique could be used. Therefore, NNs can provide simultaneously higher performance and more flexibility when designing phase microscopy systems.en


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Creative Commons Attribution-NonCommercial-NoDerivs 3.0 United States
License: Creative Commons Attribution-NonCommercial-NoDerivs 3.0 United States