A carregar...
Publicação
Multi-scale cortical keypoint representation for attention and object detection
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 388.16 KB | Adobe PDF |
Orientador(es)
Resumo(s)
Keypoints (junctions) provide important information for
focus-of-attention (FoA) and object categorization/recognition. In this
paper we analyze the multi-scale keypoint representation, obtained by
applying a linear and quasi-continuous scaling to an optimized model of
cortical end-stopped cells, in order to study its importance and possibilities
for developing a visual, cortical architecture.We show that keypoints,
especially those which are stable over larger scale intervals, can provide
a hierarchically structured saliency map for FoA and object recognition.
In addition, the application of non-classical receptive field inhibition to
keypoint detection allows to distinguish contour keypoints from texture
(surface) keypoints.
Descrição
Palavras-chave
Visão computorizada Córtex visual
Contexto Educativo
Citação
2nd Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA 2005). - Estoril, Lisboa : Springer LNCS 3523, 7-9 June 2005. - LNCS 3523. - p. 255-262
Editora
Estoril, Lisboa