A Bio-inspired Neural Model for Colour Image Segmentation

Authors:
Francisco Javier Díaz-Pernas;Míriam Antón-Rodríguez;José Fernando Díez-Higuera;Mario Martínez-Zarzuela
Affiliations:
Department of Signal Theory, Communications and Telematics Engineering Telecommunications Engineering School, University of Valladolid, Valladolid, Spain;Department of Signal Theory, Communications and Telematics Engineering Telecommunications Engineering School, University of Valladolid, Valladolid, Spain;Department of Signal Theory, Communications and Telematics Engineering Telecommunications Engineering School, University of Valladolid, Valladolid, Spain;Department of Signal Theory, Communications and Telematics Engineering Telecommunications Engineering School, University of Valladolid, Valladolid, Spain
Venue:
ANNPR '08 Proceedings of the 3rd IAPR workshop on Artificial Neural Networks in Pattern Recognition
Year:
2008

Citing 6
Cited 0

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system

Neural Networks
Synthetic aperture radar processing by a multiple scale neural system for boundary and surface representation

Neural Networks - Special issue: automatic target recognition
A neural network for enhancing boundaries and surfaces in synthetic aperture radar images

Neural Networks
Segmentation of Color Textures

IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Processing (3rd Edition)

Digital Image Processing (3rd Edition)

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper describes a multi-scale neural model to enhance regions and extract contours of colour-texture image taking into consideration the theory for visual information processing in the early stages of human visual system. It is composed of two main components: the Colour Opponent System (COS) and the Chromatic Segmentation System (CSS). The structure of the CSS architecture is based on BCS/FCS systems, so the proposed architecture maintains the essential qualities of the base model such as illusory contours extraction, perceptual grouping and discounting the illuminant. Experiments performed show the good visual results obtained and the robustness of the model when processing images presenting different levels of noise.