Publication Details

Investigation of Bilateral Similarity in Central Retinal Blood Vessels

BISWAS Sangeeta, ROHDIN Johan A., KAVETSKYI Andrii, ALVES Saraiva Gabriel, BISWAS Angkan and DRAHANSKÝ Martin. Investigation of Bilateral Similarity in Central Retinal Blood Vessels. IEEE Access, vol. 2021, no. 9, pp. 63012-63028. ISSN 2169-3536. Available from: https://ieeexplore.ieee.org/document/9409039
Czech title
Vyšetřování oboustranné podobnosti centrálních krevních cév sítnice
Type
journal article
Language
english
Authors
Biswas Sangeeta, Ph.D. (DITS FIT BUT)
Rohdin Johan A., Dr. (DCGM FIT BUT)
Kavetskyi Andrii (DITS FIT BUT)
Alves Saraiva Gabriel (FIT BUT)
Biswas Angkan (CAPM)
Drahanský Martin, prof. Ing., Dipl.-Ing., Ph.D. (DITS FIT BUT)
URL
Keywords

retina, symmetry, central retinal blood vessels, deep neural network, biometric system

Abstract

While our left and right eyes clearly have a high degree of external bilateral similarity, it is less obvious to what degree they have internal bilateral similarity. This is especially true for the central retinal blood vessels (CRBVs), which are responsible for supplying blood to retinas and also can be used as a strong biometric. In this paper, we investigate whether the CRBVs of the left and right retinas possess strong enough bilateral similarity so that we reliably tell whether a pair of the left and right retinas belong to a single subject. We evaluate and analyse the performance of both human- and deep neural network-based bilateral verification by experimenting on two publicly available data sets.

Published
2021
Pages
63012-63028
Journal
IEEE Access, vol. 2021, no. 9, ISSN 2169-3536
Publisher
Institute of Electrical and Electronics Engineers
DOI
UT WoS
000645855900001
EID Scopus
BibTeX
@ARTICLE{FITPUB12203,
   author = "Sangeeta Biswas and A. Johan Rohdin and Andrii Kavetskyi and Gabriel Saraiva Alves and Angkan Biswas and Martin Drahansk\'{y}",
   title = "Investigation of Bilateral Similarity in Central Retinal Blood Vessels",
   pages = "63012--63028",
   journal = "IEEE Access",
   volume = 2021,
   number = 9,
   year = 2021,
   ISSN = "2169-3536",
   doi = "10.1109/ACCESS.2021.3074514",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12203"
}
Back to top