Publication detail

Face Recognition by Bunch Graph Method

ŠŤASTNÝ, J. ŠKORPIL, V.

Czech title

Rozpoznávání obličejů metodou shlukových grafů

English title

Face Recognition by Bunch Graph Method

Type

journal article - other

Language

en

Original abstract

Face Bunch Graph method method uses a simple comparison function both for the localization and the recognition of faces. The input data for the two processes are so-called Jets, which represent image properties in the neighbourhood of a face bunch graph (FBG) node. The algorithm described below was chosen for implementation because of its very good results and because of the application of the same representation for both searching for and comparing images.

Czech abstract

Metoda shlukových grafů používá jednoduché srovnávací funkce pro lokalizaci i pro rozpoznání obličejů. Jako vstupní data pro oba procesy slouží tzv. Jety , které reprezentují vlastnosti obrazu v okolí uzlu shlukového grafu. Tento dále popsaný algoritmus byl zvolen pro implementaci vzhledem k velmi dobrým výsledkům a dále pak z důvodu použití stejné reprezentace jak pro vyhledávání tak porovnávání snímků.

English abstract

Face Bunch Graph method method uses a simple comparison function both for the localization and the recognition of faces. The input data for the two processes are so-called Jets, which represent image properties in the neighbourhood of a face bunch graph (FBG) node. The algorithm described below was chosen for implementation because of its very good results and because of the application of the same representation for both searching for and comparing images.

Keywords in Czech

Shlukový graf, shodová funkce, rozpoznávání

Keywords in English

Recognition, face, bunch graph

RIV year

2004

Released

01.01.2004

ISSN

1109-2742

Volume

3

Number

1

Pages from–to

134–138

Pages count

5

BIBTEX


@article{BUT46469,
  author="Jiří {Šťastný} and Vladislav {Škorpil},
  title="Face Recognition by Bunch Graph Method",
  year="2004",
  volume="3",
  number="1",
  month="January",
  pages="134--138",
  issn="1109-2742"
}