(20) * << * >> * Russian * English * Content * All Issues

Classification of crystallogram images using the methods of statistical analysis of texture images

N.Y. Ilyasova, A.V. Kupriyanov, A.G. Khramov1

Image Processing Systems Institute of RAS

1Samara State Aerospace University

 PDF, 398 kB

Pages: 122-127.

Full text of article: Russian language.

Abstract:
The paper is devoted to the analysis of the applicability of statistical features of texture images for the classification of crystallograms. The second-order moment characteristics calculated on the basis of multivariate distribution of the brightness function were used as the features of texture images. The k-nearest neighbour method was used for the classification of crystallograms. Experimental studies were performed on lacrimal fluid crystallograms. The authors identified seven different classes of crystallograms and two groups: the norm group and the pathology group. The dependence of the classification quality on the set of features and the image type was interpreted.

Citation:
Ilyasova NY, Kupriyanov AV, Khramov AG. Classification of crystallogram images using the methods of statistical analysis of texture images. Computer Optics 2000; 20: 122 - 127.

References:

  1. Saratovkin DD. Dendritic crystallization. Moscow: Metallurgizdat. 1953: 95.
  2. M.Shirvaikar, M.Trivedi, Developing texture-based image clutter measures for object detection // Optical Engineering, vol.31(12), p.2628-2639, 1992.
  3. Chukhman TP. Crystallographic study of lacrimal fluid in inflammatory diseases of the eye. Dissertation for the degree of candidate of medical sciences; Volgograd; 1999.
  4. V.A.Soifer, V.V.Kotlyar, S.N.Khonina, and A.G.Khramov, The Method of The Directional Field in the Interpretation and Recognition of Images with Structure Redundancy // Pattern Recognition and Image Analysis, v.6, No.4, p.710-724, 1996
  5. Ilyasova NY, Ustinov AV, Khramov AG. Numerical methods and algorithms of building of directional fields in quasiperiodic structures. Computer Optics 1998; 18: 150-165.
  6. Dvoryanova TP, Ilyasova NY, Ustinov AV, Khramov AG. Computer system for analysis of the diagnostic crystallograms. Computer Optics 1996; 16: 90-96.
  7. R.M.Haralick, K.Shanmugam, I.Dinstein, Textural features for image classification // IEEE Trans.Syst.Man Cybern. v.3, p.610- 621, 1973.
  8. O.Basset, F.Dupont, A.Herandez, C.Odet, Texture image analysis: application to the classification of bovine muscles from meat slice images // Optical. Engineering, v.38(11), p.1950-1959, 1999.
  9. J.Hozman, M.Bernas, R.Kubinek, Biomedical Image Processing Applications // Biomedical Engineering & Biotechnology, Publishing House of the Czech Technical University, 1994.
  10. Duda RO, Hart PE. Pattern classification and scene analysis. Moscow: Mir Publisher; 1976: 512.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20