Estimation of the color image gradient with perceptual attributes

  • Philippe Pujas
  • Marie-José Aldon
Poster Session A: Color & Texture, Enhancement, Image Analysis & Pattern Recognition, Segmentation
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1310)


Classical gradient operators are generally defined for grey level images and are very useful for image processing such as edge detection, image segmentation, data compression and object extraction. Some attempts have been made to extend these techniques to multi-component images. However, most of these solutions do not provide an optimal edge enhancement.

In this paper we propose a general formulation of the gradient of a multi-image. We first give the definition of the gradient operator, and then we extend it to multi-spectral images by using a metric and a tensorial formula. This definition is applied to the case of RGB images. Then we propose a perceptual color representation and we show that the gradient estimation may be improved by using this color representation space. Different examples are provided to illustrate the efficiency of the method and its robustness for color image analysis.


Color Image Gradient Magnitude Perceptual Space Gradient Estimator Sobel Operator 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    I. Sobel, “Neighbourhood coding of binary images for fast contour following and general array binary processing”, Computer Graphics and Image Processing, vol. 8,1978, pp. 127–135.Google Scholar
  2. 2.
    J.M.S. Prewitt, “Object enhancement and extraction”, Picture Processing and Psychopictorics, B.S. Lipking and A. Rosenfeld, editors”, Academic Press, New York, 1970, pp. 75–149.Google Scholar
  3. 3.
    J.F. Canny, “A Computational approach to edge detection”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 8, November 1986, pp. 769–798.Google Scholar
  4. 4.
    R. Deriche, “Using Canny criteria to derive an optimal edge detector recursively implemented, The International Journal of Computer Vision, vol. 2, April 1987, pp. 167–187.Google Scholar
  5. 5.
    J. Shen and S. Castan, “An Optimal linear operator for edge detection”, Conference on Computer Vision and Pattern Recognition, Miami Beach, Florida, USA, 1986, pp. 109–114.Google Scholar
  6. 6.
    R. Machuca and K. Philips, “Application of Vector Fields to Image Processing”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 5, n°3, may 1983, pp. 316–329.Google Scholar
  7. 7.
    S. Di Zenzo, “Note on the gradient of a multi-image”, Computer Vision, Graphics, And Image Processing, vol. 33, 1986, pp. 116–125.Google Scholar
  8. 8.
    M. Chapron, “A New Chromatic Edge Detector Used for Color Image Segmentation”, 11th IAPR International Conference on Pattern Recognition, The Hague, vol. 3, 1992, pp. 311–314.Google Scholar
  9. 9.
    P. Pujas: Analyse de scènes exploitant des images couleur et 3D, PhD Thesis, University Montpellier II, France, February 1996.Google Scholar
  10. 10.
    R. Taylor and P. Lewis, “Color Image Segmentation Using Boundary Relaxation”, 11th IAPR International Conference on Pattern Recognition, The Hague, vol. 3, 1992, pp. 721–724.Google Scholar
  11. 11.
    R. Nevatia, “A Color Edge Detector and Its Use in Scene Segmentation”, IEEE Trans. on Systems, Man, and Cybernetics, vol. 7, 1977, pp. 820–826.Google Scholar
  12. 12.
    A.R. Smith, “Color gamut transform pairs”, SIGGRAPH'78, Atlanta, USA, august 1992, pp. 721–724.Google Scholar
  13. 13.
    Y. Ohta and T. Kanade and T. Sakai, “Color Information for Region Segmentation”, Computer Graphics And Image Processing”, vol. 13, 1980, pp. 222–241.Google Scholar
  14. 14.
    D. Tseng and C. Chang, “Color Segmentation Using Perceptual Attributes”, 11th IAPR International Conference on Pattern Recognition, The Hague, vol. 3, August 1992, pp. 228–231.Google Scholar
  15. 15.
    P. Pujas and M.J. Aldon, “Robust Color Image Segmentation”, 7th ICAR, Sant Feliu de Guixols, Catalonia, Spain, September 1995, pp. 145–155.Google Scholar
  16. 16.
    S. Tominaga, “Color Image Segmentation Using Three Perceptual Attributes”, CVPR, 1996, pp. 628–630.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Philippe Pujas
    • 1
  • Marie-José Aldon
    • 2
  1. 1.Institut Universitaire de Technologie de MontpellierUniversité Montpellier IIBéziersFrance
  2. 2.LIRMM - UMR C55060 - CNRS/Université Montpellier IIMontpellier Cedex 05France

Personalised recommendations