MULTIPLE SCALE NEURAL ARCHITECTURE FOR RECOGNISING COLOURED AND TEXTURED SCENES

Francisco Javier Díaz-Pernas, Míriam Antón-Rodríguez, Víctor Iván Serna-González, José Fernando Díez-Higuera, Mario Martínez-Zarzuela

Abstract

A dynamic multiple scale neural model for recognising colour images of textured scenes is proposed. This model combines colour and textural information to recognise coloured textures through the operation of two main components: segmentation component formed by the Colour Opponent System (COS) and the Chromatic Segmentation System (CSS); and recognition component formed by pattern generation stages and Fuzzy ARTMAP neural network. Firstly, the COS module transforms the RGB chromatic input signals into a bio-inspired codification system (L, M, S and luminance signals), and then it generates the opponent channels (black-white, L-M and S-(L+M)). The CSS module incorporates contour extraction, double opponency mechanisms and diffusion processes in order to generate coherent enhancing regions in colour image segmentation. These colour region enhancements along with the local textural features of the scene constitute the recognition pattern to be sent into the Fuzzy ARTMAP network. The structure of the CSS architecture is based on BCS/FCS systems, thus, maintaining their essential qualities such as illusory contours extraction, perceptual grouping and discounting the illuminant. But base models have been extended to allow colour stimuli processing in order to obtain general purpose architecture for image segmentation with later applications on computer vision and object recognition. Some comparative testing with other models is included here in order to prove the recognition capabilities of this neural architecture.

Download


Paper Citation


in Harvard Style

Javier Díaz-Pernas F., Antón-Rodríguez M., Iván Serna-González V., Fernando Díez-Higuera J. and Martínez-Zarzuela M. (2008). MULTIPLE SCALE NEURAL ARCHITECTURE FOR RECOGNISING COLOURED AND TEXTURED SCENES . In Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008) ISBN 978-989-8111-18-0, pages 177-184. DOI: 10.5220/0001063101770184


in Bibtex Style

@conference{biosignals08,
author={Francisco Javier Díaz-Pernas and Míriam Antón-Rodríguez and Víctor Iván Serna-González and José Fernando Díez-Higuera and Mario Martínez-Zarzuela},
title={MULTIPLE SCALE NEURAL ARCHITECTURE FOR RECOGNISING COLOURED AND TEXTURED SCENES},
booktitle={Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)},
year={2008},
pages={177-184},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001063101770184},
isbn={978-989-8111-18-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 2: BIOSIGNALS, (BIOSTEC 2008)
TI - MULTIPLE SCALE NEURAL ARCHITECTURE FOR RECOGNISING COLOURED AND TEXTURED SCENES
SN - 978-989-8111-18-0
AU - Javier Díaz-Pernas F.
AU - Antón-Rodríguez M.
AU - Iván Serna-González V.
AU - Fernando Díez-Higuera J.
AU - Martínez-Zarzuela M.
PY - 2008
SP - 177
EP - 184
DO - 10.5220/0001063101770184