Repository logo
 
Loading...
Thumbnail Image
Publication

Multi-scale cortical keypoint representation for attention and object detection

Use this identifier to reference this record.

Advisor(s)

Abstract(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.

Description

Keywords

Visão computorizada Córtex visual

Citation

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

Research Projects

Organizational Units

Journal Issue