Multi-scale keypoints in V1 and beyond: Object segregation, scale selection, saliency maps and face detection

End-stopped cells in cortical area V1, which combine outputs of complex cells tuned to different orientations, serve to detect line and edge crossings, singularities and points with large curvature. These cells can be used to construct retinotopic keypoint maps at different spatial scales (level-of-...

Full description

Saved in:
Bibliographic Details
Published in:BioSystems 2006-10, Vol.86 (1), p.75-90
Main Authors: Rodrigues, João, du Buf, J.M.H.
Format: Article
Language:English
Subjects:
Automatic scale selection
Face
Face detection
Female
Focus-of-attention
Form Perception - physiology
Humans
Keypoints
Male
Models, Neurological
Object segregation
Saliency
Visual cortex
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:End-stopped cells in cortical area V1, which combine outputs of complex cells tuned to different orientations, serve to detect line and edge crossings, singularities and points with large curvature. These cells can be used to construct retinotopic keypoint maps at different spatial scales (level-of-detail). The importance of the multi-scale keypoint representation is studied in this paper. It is shown that this representation provides very important information for object recognition and face detection. Different grouping operators can be used for object segregation and automatic scale selection. Saliency maps for focus-of-attention can be constructed. Such maps can be employed for face detection by grouping facial landmarks at eyes, nose and mouth. Although a face detector can be based on processing within area V1, it is argued that such an operator must be embedded into dorsal and ventral data streams, to and from higher cortical areas, for obtaining translation-, rotation- and scale-invariant detection.
ISSN:0303-2647
1872-8324
DOI:10.1016/j.biosystems.2006.02.019