Multi-dimensional Scale Saliency Feature Extraction Based on Entropic Graphs

Authors:
P. Suau;F. Escolano
Affiliations:
Robot Vision Group, Departamento de Ciencia de la Computación e IA, Universidad de Alicante, Spain;Robot Vision Group, Departamento de Ciencia de la Computación e IA, Universidad de Alicante, Spain
Venue:
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
Year:
2008

Citing 7
Cited 1

K-d trees for semidynamic point sets

SCG '90 Proceedings of the sixth annual symposium on Computational geometry
Saliency, Scale and Image Description

International Journal of Computer Vision
Biologically Inspired Saliency Map Model for Bottom-up Visual Attention

BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision
Boosting Saliency in Color Image Features

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Comparison of Affine Region Detectors

International Journal of Computer Vision
EBEM: An Entropy-based EM Algorithm for Gaussian Mixture Models

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02

Analysis of the multi-dimensional scale saliency algorithm and its application to texture categorization

SSPR&SPR'10 Proceedings of the 2010 joint IAPR international conference on Structural, syntactic, and statistical pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a multi-dimensional version of the Kadir and Brady scale saliency feature extractor, based on Entropic Graphs and Rényi alpha-entropy estimation. The original Kadir and Brady algorithm is conditioned by the curse of dimensionality when estimating entropy from multi-dimensional data like RGB intensity values. Our approach naturally allows to increase dimensionality, being its computation time slightly affected by the number of dimensions. Our computation time experiments, based on hyperspectral images composed of 31 bands, demonstrate that our approach can be applied to computer vision fields, i.e. hyperspectral or satellite imaging, that can not be solved by means of the original algorithm.