Machine Vision and Applications

, Volume 16, Issue 6, pp 364–373

Colour tonality inspection using eigenspace features

Original Paper


In industrial quality inspection of colour texture surfaces, such as ceramic tiles or fabrics, it is important to maintain a consistent colour shade or tonality during production. We present a multidimensional histogram method using a novelty detection scheme to inspect the surfaces. The image noise, introduced by the imaging system, is found mainly to affect the chromatic channels. For colour tonality inspection, the difference between images is very subtle and comparison in the noise dominated chromatic channels is error prone. We perform vector-ordered colour smoothing and extract a localised feature vector at each pixel. The resulting histogram represents an encapsulation of local and global information. Principal component analysis (PCA) is performed on this multidimensional feature space of an automatically selected reference image to obtain reliable colour shade features, which results in a reference eigenspace. Then unseen product images are projected onto this eigenspace and compared for tonality defect detection using histogram comparison. The proposed method is compared and evaluated on a data set with groundtruth.


Colour tonality Surface inspection Image noise analysis Vector directional processing Multidimensional histogramming 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kittler, J., Marik, R., Mirmehdi, M., Petrou, M., Song, J.: Detection of defects in colour texture surfaces. In: IAPR Machine Vision Applications, pp. 558–567 (1994)Google Scholar
  2. 2.
    Wiltschi, K., Pinz, A., Lindeberg, T.: An automatic assessment scheme for steel quality inspection. Mach. Vision Appl. 12, 113–128 (2000)CrossRefGoogle Scholar
  3. 3.
    Chetverikov, D., Hanbury, A.: Finding defects in texture using regularity and local orientation. Pattern Recognit. 35(10), 2165–2180 (2002)CrossRefMATHGoogle Scholar
  4. 4.
    Kumar, A., Pang, G.: Defect detection in textured materials using optimized filters. IEEE Trans. Syst. Man Cybernet. 32(5), 553–570 (2002)CrossRefGoogle Scholar
  5. 5.
    Baldrich, R., Vanrell, M., Villanueva, J.: Texture and color features for tile classification. In: SPIE Polarization and Color Techniques in Industrial Inspection, vol. 3826, pp. 124–135 (1999)Google Scholar
  6. 6.
    Lumbreras, F., Serrat, J., Baldrich, R., Vanrell, M., Villanueva, J.: Color texture recognition through multiresolution features. In: International Conference on Quality Control by Artificial Vision, vol. 1, pp. 114–121 (2001)Google Scholar
  7. 7.
    Ai, J., Liu, D., Zhu, X.: Combination of wavelet analysis and color applied to automatic color grading of ceramic tiles. In: International Conference on Pattern Recognition, vol. 3, pp. 23–26 (2004)Google Scholar
  8. 8.
    Penaranda, J., Briones, L., Florez, J.: Color machine vision system for process control in the ceramics industry. In: SPIE New Image Processing Techniques and Applications: Algorithms, Methods, and Components, vol. 3101, pp. 182–192 (1997)Google Scholar
  9. 9.
    Boukouvalas, C., Kittler, J., Marik, R., Petrou, M.: Automatic color grading of ceramic tiles using machine vision. IEEE Trans. Ind. Electron. 44(1), 132–135 (1997)CrossRefGoogle Scholar
  10. 10.
    Boukouvalas, C., Kittler, J., Marik, R., Petrou, M.: Color grading of randomly textured ceramic tiles using color histograms. IEEE Trans. Ind. Electron. 46(1), 219–226 (1999)CrossRefGoogle Scholar
  11. 11.
    Swain M and Ballard, D.: Indexing via color histograms. Int. J. Comput. Vision 7(1), 11–32 (1990)CrossRefGoogle Scholar
  12. 12.
    Pietikainen, M., Maenpaa, T., Viertola, J.: Color texture classification with color histograms and local binary patterns. In: International Workshop on Texture Analysis and Synthesis, pp. 109–112 (2002)Google Scholar
  13. 13.
    Jolliffe, I.: Principal Component Analysis. Springer-Verlag, New York (1986)Google Scholar
  14. 14.
    Nishino, K., Sato, Y., IKeuchi, K.: Eigen-texture method: appearance compression and synthesis based on a 3d model. IEEE Trans. Pattern Anal. Mach. Intell. 23(11), 1257–1255 (2001)CrossRefGoogle Scholar
  15. 15.
    Haenselmann, T., Effelsberg, W.: Texture resynthesis using principal component analysis. In: SPIE Human Vision and Electronic Imaging, vol. 4662, pp. 440–447 (2002)Google Scholar
  16. 16.
    Ade, F.: Characterization of texture by ‘eigenfilter’. Signal Process. 5(5), 451–457 (1983)CrossRefGoogle Scholar
  17. 17.
    Randen T and, J.: Husφy. Filtering for texture classification: a comparative study. IEEE Trans. Pattern Anal. Mach. Intell. 21(4), 291–310 (1999)CrossRefGoogle Scholar
  18. 18.
    Ade, F., Lins, N., Unser, M.: Comparison of various filter sets for defect detection in textiles. In: International Conference on Pattern Recognition, vol. 1, pp. 428–431 (1984)Google Scholar
  19. 19.
    Bharati, M., MacGregor, J.: Texture analysis of images using principal component analysis. In: SPIE Process Imaging for Automatic Control, vol. 4188, pp. 27–37 (2001)Google Scholar
  20. 20.
    Trahanias, P. and Venetsanopoulos, A.: Vector directional filters –a new class of multichannel image processing filters. IEEE Trans. Image Process. 2(4), 528–534 (1993)CrossRefGoogle Scholar
  21. 21.
    Pratt, W.: Digital Image Processing. Wiley, New York (1991)MATHGoogle Scholar
  22. 22.
    Trahanias, P., Karakos, D., Venetsanopoulos, A.: Directional processing of color images: theory and experimental results. IEEE Trans. Image Process. 5(6), 868–880 (1996)CrossRefGoogle Scholar
  23. 23.
    Krzanowski, W.: Principles of Multivariate Analysis: A User's Perspective. Oxford University Press, Oxford (1988)MATHGoogle Scholar

Copyright information

© Springer-Verlag 2005

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of BristolBristolEngland

Personalised recommendations