Improved grating and bar cell models in cortical area V1 and texture coding

Authors:
J. M. H. du Buf
Affiliations:
Vision Laboratory, Department of Electronics and Computer Science, University of the Algarve, Campus de Gambelas - FCT, 8000-810 Faro, Portugal
Venue:
Image and Vision Computing
Year:
2007

Citing 6
Cited 0

N-folded Symmetries by Complex Moments in Gabor Space and their Application to Unsupervised Texture Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A neural network for enhancing boundaries and surfaces in synthetic aperture radar images

Neural Networks
Signal Processing for Computer Vision

Signal Processing for Computer Vision
Array Signal Processing: Concepts and Techniques

Array Signal Processing: Concepts and Techniques
Computational Cortical Cell Models for Continuity and Texture

BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision
Contour detection based on nonclassical receptive field inhibition

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents improved models of cortical neurons in V1 that act like grating and bar detectors. Both models use the same frontend, which consists of a contrast normalisation in combination with isotropic DOG filtering, followed by anisotropic Gabor filtering together with a response sharpening. Different grouping processes of ON and OFF responses lead to a very selective detection of bar width and grating frequency, with a good localisation. Furthermore, outputs of grating cells can be grouped over combinations of orientations for coding nonlinear textures. It is shown that these models, apart from being used in the modelling of the visual cortex, can be employed in pattern-recognition applications.