Utilize este identificador para referenciar este registo: http://hdl.handle.net/10400.1/169
Título: Invariant multi-scale object categorisation and recognition
Autor: Rodrigues, J. M. F.
du Buf, J. M. H.
Palavras-chave: Visão computorizada
Córtex visual
Data: 2007
Editora: Girona
Citação: 3rd Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA 07). - Girona, 6 - 8 June 2007. - LNCS 4477. - p. 459-466
Resumo: Object recognition requires that templates with canonical views are stored in memory. Such templates must somehow be normalised. In this paper we present a novel method for obtaining 2D translation, rotation and size invariance. Cortical simple, complex and end-stopped cells provide multi-scale maps of lines, edges and keypoints. These maps are combined such that objects are characterised. Dynamic routing in neighbouring neural layers allows feature maps of input objects and stored templates to converge. We illustrate the construction of group templates and the invariance method for object categorisation and recognition in the context of a cortical architecture, which can be applied in computer vision.
URI: http://hdl.handle.net/10400.1/169
Aparece nas colecções:ISE3-Livros (ou partes, com ou sem arbitragem científica)

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
RODInv.pdf601,62 kBAdobe PDFVer/Abrir

FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.