hh.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Exploring Body Texture From mmW Images for Person Recognition
Universidad Autonoma de Madrid, Madrid, Spain.ORCID-id: 0000-0002-2428-3792
Universidad Autonoma de Madrid, Madrid, Spain.ORCID-id: 0000-0002-6338-8511
Universidad Autonoma de Madrid, Madrid, Spain.ORCID-id: 0000-0002-6343-5656
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).ORCID-id: 0000-0002-1400-346X
Visa övriga samt affilieringar
2019 (Engelska)Ingår i: IEEE Transactions on Biometrics, Behavior, and Identity Science, E-ISSN 2637-6407, Vol. 1, nr 2, s. 139-151Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

Imaging using millimeter waves (mmWs) has many advantages including the ability to penetrate obscurants, such as clothes and polymers. After having explored shape information retrieved from mmW images for person recognition, in this paper we aim to gain some insight about the potential of using mmW texture information for the same task, considering not only the mmW face, but also mmW torso and mmW wholebody. We report experimental results using the mmW TNO database consisting of 50 individuals based on both hand-crafted and learned features from Alexnet and VGG-face pretrained convolutional neural networks (CNNs) models. First, we analyze the individual performance of three mmW body parts, concluding that: 1) mmW torso region is more discriminative than mmW face and the whole body; 2) CNN features produce better results compared to hand-crafted features on mmW faces and the entire body; and 3) hand-crafted features slightly outperform CNN features on mmW torso. In the second part of this paper, we analyze different multi-algorithmic and multi-modal techniques, including a novel CNN-based fusion technique, improving verification results to 2% EER and identification rank-1 results up to 99%. Comparative analyses with mmW body shape information and face recognition in the visible and NIR spectral bands are also reported.

Ort, förlag, år, upplaga, sidor
Piscataway, NJ: IEEE, 2019. Vol. 1, nr 2, s. 139-151
Nyckelord [en]
mmW imaging, body texture information, border control security, hand-crafted features, deep learning features, CNN-level multimodal fusion, body parts
Nationell ämneskategori
Signalbehandling
Identifikatorer
URN: urn:nbn:se:hh:diva-40622DOI: 10.1109/TBIOM.2019.2906367OAI: oai:DiVA.org:hh-40622DiVA, id: diva2:1353920
Projekt
KK-CAISRKK-SIDUS AIR
Ingår i projekt
Okulär biometrik i naturliga miljöer, Vetenskapsrådet
Forskningsfinansiär
VetenskapsrådetKK-stiftelsen
Anmärkning

Funding: This work was supported in part by the Project CogniMetrics through MINECO/FEDER under Grant TEC2015-70627-R, and in part by the SPATEK Network under Grant TEC2015-68766-REDC. The work of E. Gonzalez-Sosa was supported by the Ph.D. Scholarship from Universidad Autonoma de Madrid. The work of F. Alonso-Fernandez was supported in part by the Swedish Research Council, in part by the CAISR Program, and in part by the SIDUS-AIR Project of the Swedish Knowledge Foundation. The work of V. M. Patel was supported in part by the U.S. Office of Naval Research under Grant YIP N00014-16-1-3134.

Tillgänglig från: 2019-09-24 Skapad: 2019-09-24 Senast uppdaterad: 2019-09-25Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltext

Personposter BETA

Alonso-Fernandez, Fernando

Sök vidare i DiVA

Av författaren/redaktören
Gonzalez-Sosa, EsterVera-Rodriguez, RubenFierrez, JulianAlonso-Fernandez, FernandoPatel, Vishal M.
Av organisationen
CAISR Centrum för tillämpade intelligenta system (IS-lab)
Signalbehandling

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 6 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf