File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: RedCap: residual encoder-decoder capsule network for holographic image reconstruction

TitleRedCap: residual encoder-decoder capsule network for holographic image reconstruction
Authors
KeywordsComputational resources
Data representations
Digit recognition
Digital holographic reconstruction
Encoder-decoder
Issue Date2020
PublisherOptical Society of America: Open Access Journals. The Journal's web site is located at http://www.opticsexpress.org
Citation
Optics Express, 2020, v. 28 n. 4, p. 4876-4887 How to Cite?
AbstractA capsule network, as an advanced technique in deep learning, is designed to overcome information loss in the pooling operation and internal data representation of a convolutional neural network (CNN). It has shown promising results in several applications, such as digit recognition and image segmentation. In this work, we investigate for the first time the use of capsule network in digital holographic reconstruction. The proposed residual encoder-decoder capsule network, which we call RedCap, uses a novel windowed spatial dynamic routing algorithm and residual capsule block, which extends the idea of a residual block. Compared with the CNN-based neural network, RedCap exhibits much better experimental results in digital holographic reconstruction, while having a dramatic 75% reduction in the number of parameters. It indicates that RedCap is more efficient in the way it processes data and requires a much less memory storage for the learned model, which therefore makes it possible to be applied to some challenging situations with limited computational resources, such as portable devices.
Persistent Identifierhttp://hdl.handle.net/10722/287883
ISSN
2019 Impact Factor: 3.669
2015 SCImago Journal Rankings: 2.186

 

DC FieldValueLanguage
dc.contributor.authorZENG, T-
dc.contributor.authorSo, HKH-
dc.contributor.authorLam, EYM-
dc.date.accessioned2020-10-05T12:04:38Z-
dc.date.available2020-10-05T12:04:38Z-
dc.date.issued2020-
dc.identifier.citationOptics Express, 2020, v. 28 n. 4, p. 4876-4887-
dc.identifier.issn1094-4087-
dc.identifier.urihttp://hdl.handle.net/10722/287883-
dc.description.abstractA capsule network, as an advanced technique in deep learning, is designed to overcome information loss in the pooling operation and internal data representation of a convolutional neural network (CNN). It has shown promising results in several applications, such as digit recognition and image segmentation. In this work, we investigate for the first time the use of capsule network in digital holographic reconstruction. The proposed residual encoder-decoder capsule network, which we call RedCap, uses a novel windowed spatial dynamic routing algorithm and residual capsule block, which extends the idea of a residual block. Compared with the CNN-based neural network, RedCap exhibits much better experimental results in digital holographic reconstruction, while having a dramatic 75% reduction in the number of parameters. It indicates that RedCap is more efficient in the way it processes data and requires a much less memory storage for the learned model, which therefore makes it possible to be applied to some challenging situations with limited computational resources, such as portable devices.-
dc.languageeng-
dc.publisherOptical Society of America: Open Access Journals. The Journal's web site is located at http://www.opticsexpress.org-
dc.relation.ispartofOptics Express-
dc.rightsOptics Express. Copyright © Optical Society of America: Open Access Journals.-
dc.rights© 2020 [Optical Society of America]. Users may use, reuse, and build upon the article, or use the article for text or data mining, so long as such uses are for non-commercial purposes and appropriate attribution is maintained. All other rights are reserved.-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectComputational resources-
dc.subjectData representations-
dc.subjectDigit recognition-
dc.subjectDigital holographic reconstruction-
dc.subjectEncoder-decoder-
dc.titleRedCap: residual encoder-decoder capsule network for holographic image reconstruction-
dc.typeArticle-
dc.identifier.emailSo, HKH: hso@eee.hku.hk-
dc.identifier.emailLam, EYM: elam@eee.hku.hk-
dc.identifier.authoritySo, HKH=rp00169-
dc.identifier.authorityLam, EYM=rp00131-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1364/OE.383350-
dc.identifier.pmid32121718-
dc.identifier.scopuseid_2-s2.0-85079342100-
dc.identifier.hkuros314913-
dc.identifier.volume28-
dc.identifier.issue4-
dc.identifier.spage4876-
dc.identifier.epage4887-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats