Primal sketch feature extraction from a log-polar image

Authors:
Herman M. Gomes;Robert B. Fisher
Affiliations:
Departamento de Sistemas e Computaçãão, Universidade Federal da Paraíba, Av. Aprígio Veloso s/n, 58109-970 Campina Grande, PB, Brazil;Institute of Perception, Action and Behaviour, Division of Informatics, Edinburgh University, 5 Forrest Hill, Edinburgh EH1 2QL, UK
Venue:
Pattern Recognition Letters - Special issue: Sibgrapi 2001
Year:
2003

Citing 2
Cited 4

An active vision architecture based on iconic representations

Artificial Intelligence - Special volume on computer vision
Learning and Extracting Primal-Sketch Features in a Log-Polar Image Representation

SIBGRAPI '01 Proceedings of the 14th Brazilian Symposium on Computer Graphics and Image Processing

Gradient detection in discrete log-polar images

Pattern Recognition Letters
Face recognition based on polar frequency features

ACM Transactions on Applied Perception (TAP)
A review of log-polar imaging for visual perception in robotics

Robotics and Autonomous Systems
Design strategies for direct multi-scale and multi-orientation feature extraction in the log-polar domain

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel approach for extracting primal sketch features (edges, bars, blobs and ends) from a log-polar image. Symmetry operators and a PCA module precede a set of neural networks that learn the feature's class and contrast. Experiments show the process accurately extracts the desired feature-based image description.