A hybrid gradient for n-dimensional images through hyperspherical coordinates

Authors:
Ramón Moreno;Manuel Graña
Affiliations:
Computational Intelligence Group, University of the Basque Country, Spain;Computational Intelligence Group, University of the Basque Country, Spain
Venue:
HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part II
Year:
2012

Citing 7
Cited 0

Using color to separate reflection components

Color
Active-GNG: model acquisition and tracking in cluttered backgrounds

VNBA '08 Proceedings of the 1st ACM workshop on Vision networks for behavior analysis
Two lattice computing approaches for the unsupervised segmentation of hyperspectral images

Neurocomputing
Segmentation and classification of hyperspectral images using watershed transformation

Pattern Recognition
Surveillance and human-computer interaction applications of self-growing models

Applied Soft Computing
A hybrid color distance for image segmentation

HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part II
A New Scheme for Robust Gradient Vector Estimation in Color Images

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a hybrid gradient which provides a good behavior on regions with different illumination. It avoids the shadow effects focusing on the detection of regions of the scene with different chromatic properties. It works with image intensity and chromaticity according with its intensity level emulating the Human Vision System (HVS). This gradient is grounded in the Hyperspherical coordinates, therefore it has a general propose and can be applied on RGB images, multi-spectral images or hyperspectral images.