Loading...
Publication
Multi-scale keypoints in V1 and face detection
| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 340.82 KB | Adobe PDF |
Advisor(s)
Abstract(s)
End-stopped cells in cortical area V1, which combine out-
puts of complex cells tuned to different orientations, serve to detect line
and edge crossings (junctions) and points with a large curvature. In this
paper we study the importance of the multi-scale keypoint representa-
tion, i.e. retinotopic keypoint maps which are tuned to different spatial
frequencies (scale or Level-of-Detail). We show that this representation
provides important information for Focus-of-Attention (FoA) and object
detection. In particular, we show that hierarchically-structured saliency
maps for FoA can be obtained, and that combinations over scales in
conjunction with spatial symmetries can lead to face detection through
grouping operators that deal with keypoints at the eyes, nose and mouth,
especially when non-classical receptive field inhibition is employed. Al-
though a face detector can be based on feedforward and feedback loops
within area V1, such an operator must be embedded into dorsal and
ventral data streams to and from higher areas for obtaining translation-,
rotation- and scale-invariant face (object) detection.
Description
Keywords
Visão computorizada Córtex visual
Citation
1st International Symposium Brain, Vision and Artificial Intell. (BV&AI 2005) . - Naples, 19-21 October 2005. - LNCS 3704. - p. 205-214
Publisher
Naples