Who are you?
Data(s) |
04/07/2016
04/07/2016
2004
|
---|---|
Resumo |
<p>[EN]Most automatic recognition systems are focused on recognizing, given a single mug-shot of an individual, any new image of that individual. Most verification systems are designed to authenticate an identity provided by the user. However, the previous work rarely focus on the problem of detecting when a new individual, i.e., an unknown one, is present. The goal of the work presented in this paper deals with the possibility of providing the system with basic tools to detect when a new individual starts an interactive session, in order to allow the system to add or improve an identity model in the database. Experiments carried out with a set of 36 different individuals show promising results.</p> |
Identificador |
http://hdl.handle.net/10553/17653 725972 <p><a href="http://dx.doi.org/10.1109/ICPR.2004.1334683" target="_blank">10.1109/ICPR.2004.1334683</a></p> |
Idioma(s) |
eng |
Direitos |
info:eu-repo/semantics/openAccess |
Fonte |
<p>Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004 (vol. 3; pp. 938-941). ISSN 1051-4651</p> |
Palavras-Chave | #120304 Inteligencia artificial |
Tipo |
info:eu-repo/semantics/conferenceObject |