Multi-scale cortical keypoint representation for attention and object detection

Authors:
João Rodrigues;Hans du Buf
Affiliations:
Escola Superior Tecnologia, University of Algarve, Faro, Portugal;Vision Laboratory, FCT, University of Algarve, Faro, Portugal
Venue:
IbPRIA'05 Proceedings of the Second Iberian conference on Pattern Recognition and Image Analysis - Volume Part II
Year:
2005

Citing 3
Cited 2

Phase-based disparity measurement

CVGIP: Image Understanding
Image Representation Using 2D Gabor Wavelets

IEEE Transactions on Pattern Analysis and Machine Intelligence
Contour detection based on nonclassical receptive field inhibition

IEEE Transactions on Image Processing

A multi-scale visual salient feature points extraction method based on Gabor wavelets

ROBIO'09 Proceedings of the 2009 international conference on Robotics and biomimetics
Multi-scale keypoints in v1 and face detection

BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.