EXTRACTION OF WHEAT EARS WITH STATISTICAL METHODS BASED ON TEXTURE ANALYSIS

M. Bakhouche, F. Cointault, P. Gouton

2007

Abstract

In the agronomic domain, the simplification of crop counting is a very important and fastidious step for technical institutes such as Arvalis1, which has then proposed us to use image processing to detect the number of wheat ears in images acquired directly in a field. Texture image segmentation techniques based on feature extraction by first and higher order statistical methods have been developped for unsupervised pixel classification. The K-Means algorithm is implemented before the choice of a threshold to highlight the ears. Three methods have been tested with very heterogeneous results, except the run length technique for which the results are closed to the visual counting with an average error of 6%. Although the evaluation of the quality of the detection is visually done, automatic evaluation algorithms are currently implementing. Moreover, other statistical methods of higher order must be implemented in the future jointly with methods based on spatio-frequential transforms and specific filtering.

References

  1. Al-Janobi A. 2001. Performance evaluation of crossdiagonal texture matrix method. Pattern Recognition, vol. 34, pp-171-180.
  2. Borsotti M., Campadelli P. and Schettini R. 1998. Quantitative evaluation of color image segmentation results. Pattern Recognition Letters, 19:741-747.
  3. Brodatz P. Textures. 1966. A photograph Album For Artists and designer. Dover, New York.
  4. Burges C.J. 1998. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2:121-167.
  5. Conners R.W. and Harlow C.A. 1980. A Thoerical Comparison of Texture algorithms, IEEE Trans. On PAMI, Vol.2, N°3, pp. 204-222.
  6. Foucherot I., Gouton P., Devaux J.C. and Truchetet F. 2004. New method for analysing colour texture based on the Karhunen-Loeve transform and quantification. Pattern Recognition, 37 (8), pp. 1661- 1674.
  7. Galloway M.M. 1975. Texture analysis using gray level run lengths. Computer Graphics and Image Processing, vol.4, pp-172-179.
  8. Germain C., Rousseau R. and Grenier G. 1995. Non destructive counting of wheatears with picture analysis. Image Processing and its application, pp. 453-439.
  9. Guérin D., Cointault F., Gée C. and Guillemin J.P. 2005. Étude de faisabilité d'un système de comptage d'épis de blé par vision (Feasibility study of a wheatears counting system per vision) - Traitement du Signal, Special Session Colour Imaging, Vol. 21, n°5, pp. 549-560.
  10. Haralick R.M., Shanmugam K. and Dinstein I.H. 1973. Textural features for image classification. IEEE Trans. On sys. Han and cybernetics, Vol. SMC-3, n°6.
  11. Kavdir I. and Guyer D.E. 2004. Comparison of artificial neural networks and statistical classifiers in apple sorting using textural features. Biosystem Engineering 89 (3), pp 331-334.
  12. Laurent H., Chabrier S., Rosenberger C., Emile B. and Marché P. Etude comparative de critères d'évaluation de la segmentation, In Gretsi 2003.
  13. Mäenpää T. and Pietikäinen M. 2004. Classification with colour and texture: jointly or separately. Pattern Recognition, vol 37, pp 1629-1640.
  14. Pratt W.K. 1991. Digital image processing. Willey Interscience, New York.
  15. Rosenberger C. 1999. Mise en Oeuvre d'un Système Adaptatif de segmentation d'images. PhD thesis, Université de Rennes 1.
  16. Unser M. 1986. Sum and difference histograms for texture classification. IEEE Trans, Patterrn Anal, Mach. Intel. 8, pp. 118-125.
  17. Weska J. S., Dyer C. R. and Rosenfeld A. 1976. A comparative Study of texture measures for terrain classification. IEEE Trans. On sys, Man. And cybernetic, vol. 6, n°4, pp. 269- 285.
  18. Zeboudj R. 1988. Filtrage, Seuillage Automatique, Contraste et Contours: du Pré-Traitement à l'analyse d'image. PhD thesis, Université de Saint Etienne.
Download


Paper Citation


in Harvard Style

Bakhouche M., Cointault F. and Gouton P. (2007). EXTRACTION OF WHEAT EARS WITH STATISTICAL METHODS BASED ON TEXTURE ANALYSIS . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 978-972-8865-74-0, pages 276-280. DOI: 10.5220/0002056702760280


in Bibtex Style

@conference{visapp07,
author={M. Bakhouche and F. Cointault and P. Gouton},
title={EXTRACTION OF WHEAT EARS WITH STATISTICAL METHODS BASED ON TEXTURE ANALYSIS},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2007},
pages={276-280},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002056702760280},
isbn={978-972-8865-74-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - EXTRACTION OF WHEAT EARS WITH STATISTICAL METHODS BASED ON TEXTURE ANALYSIS
SN - 978-972-8865-74-0
AU - Bakhouche M.
AU - Cointault F.
AU - Gouton P.
PY - 2007
SP - 276
EP - 280
DO - 10.5220/0002056702760280