Pupil localization using self-organizing migrating algorithm
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F20%3A10247142" target="_blank" >RIV/61989100:27240/20:10247142 - isvavai.cz</a>
Result on the web
<a href="https://link.springer.com/chapter/10.1007/978-3-030-14907-9_21" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-14907-9_21</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-030-14907-9_21" target="_blank" >10.1007/978-3-030-14907-9_21</a>
Alternative languages
Result language
angličtina
Original language name
Pupil localization using self-organizing migrating algorithm
Original language description
In this paper, we propose a new method for pupil localization in images. The main contribution of the proposed method is twofold. Firstly, the method is based on the proposed eye model that takes into account physiological properties of eyes (i.e. reflects the properties of pupil, iris, and sclera). Secondly, the correct shape and the position of the model are determined using an evolutionary algorithm called Self-Organizing Migrating Algorithm (SOMA). Thanks to these ideas, the proposed method is faster than the state-of-the-art methods without reduction of accuracy. We evaluated the algorithms on two publicly available data sets in remote tracking scenarios (namely BioID [7] and GI4EÂ [11]). (C) Springer Nature Switzerland AG 2020.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Lecture Notes in Electrical Engineering
ISBN
978-3-030-14906-2
ISSN
1876-1100
e-ISSN
1876-1119
Number of pages
10
Pages from-to
207-216
Publisher name
Springer Verlag
Place of publication
Cham
Event location
Ostrava
Event date
Sep 11, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—