Improving gender classification accuracy in the wild
| Data(s) |
24/11/2015
24/11/2015
2013
|
|---|---|
| Resumo |
<p>[EN]In this paper, we focus on gender recognition in challenging large scale scenarios. Firstly, we review the literature results achieved for the problem in large datasets, and select the currently hardest dataset: The Images of Groups. Secondly, we study the extraction of features from the face and its local context to improve the recognition accuracy. Diff erent descriptors, resolutions and classfii ers are studied, overcoming previous literature results, reaching an accuracy of 89.8%.</p> |
| Identificador |
http://hdl.handle.net/10553/15087 716518 <p>10.1007/978-3-642-41827-3_34</p> |
| Idioma(s) |
eng |
| Direitos |
info:eu-repo/semantics/openAccess |
| Fonte |
<p>Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. 18th Iberoamerican Congress, CIARP. Berlin: Springer, 2013 (Lecture Notes in Computer Science, ISSN 0302-9743. vol.8259, pp. 270-277). ISBN 978-3-642-41826-6. Online ISBN 978-3-642-41827-3</p> |
| Palavras-Chave | #120304 Inteligencia artificial |
| Tipo |
info:eu-repo/semantics/conferenceObject |
