Limitations et comparaisons d’ordonnancement utilisant des distances couleur

Limitations et comparaisons d’ordonnancement utilisant des distances couleur

Audrey Ledoux Noël Richard Anne-Sophie Capelle-Laizé 

Université de Poitiers, XLIM-SIC UMR CNRS 7252 Boulevard Marie et Pierre Curie Téléport 2, BP 30179, 86962 Futuroscope Chasseneuil cedex

Corresponding Author Email: 
{aledoux,richard,capelle}@sic.univ-poitiers.fr
Page: 
65-82
|
DOI: 
https://doi.org/10.3166/ts.29.65-82
Received: 
N/A
| |
Accepted: 
N/A
| | Citation

OPEN ACCESS

Abstract: 

Mathematical morphology is based on the concept of ordering. With color image process, write a valid order relation requires to using distances from standard color spaces CIELAB or CIELUV . Since the first recommendations of the CIE (International commission on illumination), several colors distances have been proposed. The aim of this paper is studying the impact of each color distances in the context of color mathematical morphology. The results are developed for a new construction of morphological operators based on color

distances in CIELAB space. A criterion to evaluate methods of color ordering is then proposed to compare the main approaches in mathematical morphology with those based on a distance function.

RÉSUMÉ

La morphologie mathématique repose sur la notion d’ordonnancement. Pour le traitement d’images couleur, l’écriture d’une relation d’ordre valide nécessite l’utilisation de distances couleur normalisées issues des espaces CIELAB ou CIELUV . Depuis les premières recommandations de la CIE (Commission internationale de l’éclairage), plusieurs distances couleur ont été proposées. Le but de cet article est d’étudier l’impact de ces formules de distance couleur dans le contexte de la morphologie mathématique couleur. Les résultats sont développés pour une nouvelle construction des opérateurs morphologiques couleur basée sur la distance dans l’espace CIELAB. Un critère de comparaison des méthodes d’ordonnancement couleur est ensuite proposé pour comparer les principales approches en morphologie mathématique avec celles basées sur une fonction de distance.

Keywords: 

color images, mathematical morphology, perceptual distance

MOTS-CLÉS

images couleur, morphologie mathématique, distance perceptuelle

Extended abstract
1. Introduction
2. Définition d’un ordonnancement couleur
3. Pourquoi le choix d’une métrique?
4. Premiers tests
5. Nouveaux tests et résultats
6. Conclusion
  References

Angulo-Lopez J. (2007). Morphological colour operators in totally ordered lattices based on distances: Application to image filtering, enhancement and analysis. Computer Vision and Image Understanding, vol. 107, no 1-2, p. 56–73.

Angulo-Lopez J., Serra J. (2003). Morphological coding of color images by vector connected filters. Signal processing and its applications. Seventh international symposium on, vol. 1, p. 69–72.

Aptoula E., Lefèvre S. (2007). A comparative study on multivariate mathematical morphology. Pattern Recognition, vol. 40, no 11, p. 2914–2929.

Aptoula E., Lefèvre S. (2008). On lexicographical ordering in multivariate mathematical morphology. Pattern Recognition Letters, vol. 29, no 2, p. 109–118.

Barnett V. (1976). The ordering of multivariate data. Journal of the Royal Statistical Society. Series A (General), p. 318–355.

Bonton P., Fernandez-Maloigne C., Tremeau A. (2004). Image numérique couleur: de l’acquisition au traitement. Dunod.

CIE. (1995). Industrial colour-difference evaluation. CIE Publication, vol. 116.

CIE. (2001). Technical Report: Improvement to Industrial Colordifference Evaluation. CIE Publication, vol. 142.

Clarke F., McDonald R., Rigg D. (1984). Modification to the jpc 79 colour difference formula. Journal of Society of Dyers Colour, vol. 100, no 4, p. 128-132.

Comer M., Delp E. (1999). Morphological operations for color image processing. Journal of Electronic Imaging, vol. 8, no 3, p. 279–289.

DIN. (2000). Din 6176. farbmetrische bestimmung von farbabständen bei körperfarben nach der din99-formel (colorimetric evaluation of colour differences of surface colours according to din99 formula–available in english).

Evans A. (2003). Vector area morphology for motion field smoothing and interpretation. Vision, Image and Signal Processing, IEE Proceedings, vol. 150, no 4, p. 219-226.

Flórez-Revuelta F. (2005). Ordering of the rgb space with a growing self-organizing network. application to color mathematical morphology. Artificial Neural Networks: Biological Inspirations–ICANN 2005, p. 385–390.

Gonzalez P., Cabezas V., Mora M., Cordova F., Vidal J. (2010). Morphological color images processing using distance-based and lexicographic order operators. In Xxix international conference of the chilean computer science society, p. 258–264.

Hanbury A., Serra J. (2001). Mathematical morphology in the hls colour space. In Proceedings of the british machine vision conference, p. 451–460.

Hanbury A., Serra J. (2002). Mathematical morphology in the cielab space. Journal of Image Analysis and Stereology, vol. 21, p. 201-206.

Ivanovici M., Richard N. (2011). Fractal dimension of color fractal images. IEEE Transactions on Image Processing, vol. 20, no 1, p. 227–235.

Lambert P., Gaspard S. (2000). Enhancement and registration of multichannel images based on vector order filter. Signal processing: theories and applications: EUSIPCO.

Lezoray O., Meurie C., Elmoataz A. (2005). A graph approach to color mathematical morphology. In Proceedings of the fifth ieee international symposium on signal processing and information technology, p. 856-861.

Louverdis G., Vardavoulia M., Andreadis I., Tsalides P. (2002). A new approach to morphological color image processing. Pattern recognition, vol. 35, n° 8, p. 1733-1741.

Ortiz F., Torres F., Juan E. D., Cuenca N. (2002). Colour mathematical morphology for neural image analysis. Real Time Imaging, vol. 8, n° 6, p. 455-465.

Picard R., Graczyk C., Mann S., Wachman J., Picard L., Campbell L. (1995). Vistex benchmark database of color textured images. http://vismod.media.mit.edu/vismod/imagery/VisionTexture/vistex.html. (Vision and Modeling Group of the MIT Media Laboratory, Cambridge, Massachusetts)

Plaza A., Martinez P., Perez R., Plaza J. (2004). A new approach to mixed pixel classification of hyperspectral imagery based on extended morphological profiles. Pattern Recognition, vol. 37, n° 6, p. 1097-1116.

Ronse C. (1990). Why mathematical morphology needs complete lattices. Signal Processing, vol. 21, n° 2, p. 129-154.

Serra J. (1988). Image analysis and mathematical morphology: Theoretical advances (vol. II). Academic Press.

Tobar M., Platero C., González P., Asensio G. (2007). Mathematical morphology in the his colour space. Pattern Recognition and Image Analysis, p. 467-474.