SEGMENTING COLOR IMAGE OF PLANTS WITH A SPATIO-COLORIMETRIC APPROACH

Cindy Torres, Alain Clément, Bertrand Vigouroux

2010

Abstract

An unsupervised vectorial segmentation method using both spatial and color information is presented. To overcome the problem of memory space, this method is based on a multidimensional compact histogram and an original compact spatial neighborhood probability matrix (SNPM). The multidimensional compact histogram allows a drastic reduction of memory space without any data loss. Leaning upon the compact histogram, a SNPM has been computed. It contains all non-negative probabilities of spatial connectivity between pixel colors. In an unsupervised histogram analysis classification process, two phases are classically distinguished: (i) a learning process during which histogram modes are identified and (ii) a second step called the decision step in which a full partition of the colorimetric space is carried out according the previously defined classes. During the second step of a standard colorimetric approach, a colorimetric distance like Euclidean or Mahalanobis is used. We insert here a spatio-colorimetric distance defined as a weighed mixture between a colorimetric distance and the spatial distance calculated from the SNPM. The vectorial classification method is based on previously presented principles, achieving a hierarchical analysis of the color histogram by means of a 3D-connected components labeling. Results are applied to color images of plants to separate plantlets and loam.

References

  1. Busin L., Vandenbroucke N., Macaire L., Postaire J.G., 2005. Colour space selection for unsupervised colour image segmentation by analysis of connectedness properties. International Journal of Robotics and Automation, 20(2):70-77.
  2. Clément A., Vigouroux B., 2001. Un histogramme compact pour l'analyse d'images multi-composantes. Actes du 18ème colloque sur le traitement du signal et des images GRETSI' 01, Toulouse, France, vol. 1, p. 305-307.
  3. Clément A., Vigouroux B., 2003. Unsupervised segmentation of scenes containing vegetation (Forsythia) and soil by hierarchical analysis of bidimensional histogram. Pattern Recognition Letters, nº24, p. 1951-1957.
  4. Comaniciu D., Meer P., 2002. Mean Shift: A Robust Approach toward Feature Space Analysis. IEEE Trans. Pattern Analysis Machine Intell., 24(5):603- 619.
  5. Foucher P., Revollon P., Vigouroux B., 2001. Segmentation d'images en couleurs par réseau de neurones : application au domaine vegetal. Actes du congrès francophone par vision par ordinateur (ORASIS), Cahors, France, 309-317.
  6. Macaire L., Vandenbroucke N., Postaire J.G., 2006. Color image segmentation by analysis of subset connectedness and color homogeneity properties. Computer Vision and Image Understanding, Elsevier, 102:105-116.
  7. Noordam J., Broek W.V.D., 2000. Geometrically guided fuzzy c-means clustering for multivariate image segmentation. International Conference on Pattern Recognition, 1:462-465.
  8. Ouattara S., Clément A., 2008. Unsupervised Image Segmentation by Multi-Dimensional Compact Histograms Analysis. ClasSpec'08, October 15th 2008, Lens, France.
  9. Trémeau A., Laget B., 1995. Quantification de la couleur et analyse d'image, Traitement du signal.
  10. Trémeau A., 1993. Contribution des modèles de la perception visuelle à l'analyse d'image couleur, PhD thesis, University of Saint-Etienne, France.
  11. Xuan G., Fisher P., 2000. Maximum likelihood clustering method based on color features. Proceedings of the First International Conference on Color in Graphics and Image Processing, Saint-Etienne, France, p. 191- 194.
Download


Paper Citation


in Harvard Style

Torres C., Clément A. and Vigouroux B. (2010). SEGMENTING COLOR IMAGE OF PLANTS WITH A SPATIO-COLORIMETRIC APPROACH . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 191-196. DOI: 10.5220/0002835101910196


in Bibtex Style

@conference{visapp10,
author={Cindy Torres and Alain Clément and Bertrand Vigouroux},
title={SEGMENTING COLOR IMAGE OF PLANTS WITH A SPATIO-COLORIMETRIC APPROACH},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={191-196},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002835101910196},
isbn={978-989-674-029-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)
TI - SEGMENTING COLOR IMAGE OF PLANTS WITH A SPATIO-COLORIMETRIC APPROACH
SN - 978-989-674-029-0
AU - Torres C.
AU - Clément A.
AU - Vigouroux B.
PY - 2010
SP - 191
EP - 196
DO - 10.5220/0002835101910196