Method for texture classification using image structural features
D.G. Asatryan, V.V. Kurkchiyan, L.R. Kharatyan

Institute for Informatics and Automation Problems of the National Academy of Sciences,
Russian-Armenian (Slavonic) University

Full text of article: Russian language.

Abstract:
In this paper, novel method for texture analysis and classification based on using image structural properties is proposed. It is known that the Human Visual System successfully perceives an image content by visualized collection of existing edges. In this paper, we propose to use the collection of gradient magnitudes as the characteristics of the structure of an image. Gradient magnitude is assumed to be a random variable with two-parameter Weibull distribution, and as a characteristic of the proximity of the two images we use a special measure of proximity of the parameter estimates of the corresponding distributions. Classification is made by method of comparison with the etalon using the database of the University of Heidelberg (Germany) which contains 10 texture classes. As an etalon is used the set of average values of the parameters estimates of the Weibull distribution, calculated by the magnitude gradients of training set of texture, and comparison is performed using the proposed proximity measure. The analysis revealed two virtually indistinguishable classes, and for the remaining eight classes it is shown that the classification error on the average is about 18%.

Key words:
classification, texture, gradient magnitude, Weibull distribution, similarity measure.

References:

  1. Tuceryan, M. Texture Analysis / M. Tuceryan, A.K. Jain // Handbook of Pattern Recognition and Computer Vision. – 2nd ed. – 1998. – P. 207-248.
  2. Mellor, M. Locally Rotation, Contrast, and Scale Invariant Descriptors for Texture Analysis / Mellor Matthew, Byung-Woo Hong and Michael Brady // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2008. – Vol. 30(1) – P. 52-61.
  3. Kupriyanov, A.V. Texture Analysis and Identification of the Crystal Lattice Type upon the Nanoscale Images / A.V. Kupriyanov // Computer Optics. – 2011. – Vol. 35(2). – P. 151-157. – (In Russian).
  4. Bongkyu, L. A New Method for Classification of Structural Textures / Lee Bongkyu // International Journal of Control, Automation, and Systems. – 2004. – Vol. 2(1) – P. 125-133.
  5. Jianguo, Zh. Brief review of invariant texture analysis methods / Zhang Jianguo, Tan Tieniu // Pattern Recognition. – 2002. – Vol. 35. – P. 735-747.
  6. Lu, D. A survey of image classification methods and techniques for improving classification performance / D. Lu, and Q. Weng // International Journal of Remote Sensing. – 2007. – Vol. 28(5). – P. 823-870.
  7. ThakareV.S. Survey On Image Texture Classification Techniques / Vishal S. Thakare, Nitin N. Patil and Jayshri S. Sonawane // International Journal of Advancements in Technology. – 2013. – Vol. 4(1). – P. 97-104.
  8. Jing, Y.T. Recent Trends in Texture Classification. A Review / Y.T. Jing, H.T. Yong, Ye.L. Phooi // Symposium on Progress in Information & Communication Technology. – 2009 – P. 63-68.
  9. Rosenfeld, A. Edge and curve detection for visual scene analysis / A. Rosenfeld and M. Thurston // IEEE Transaction on Computers. – 1971. – Vol. C-20 – P. 562-569.
  10. Geusebroek, J. A six-stimulus theory for stochastic texture / J. Geusebroek and A. Smeulders // International Journal of Computer Vision. – 2005. – Vol. 62(1). – P. 7-16.
  11. Yanulevskaya, V. Significance of the weibull distribution and its sub-models in natural image statistics / V. Yanu­levskaya, J. Geusebroek // Proceedings of the Fourth International Conference on Computer Vision Theory and Applications (VISAPP). – 2009. – Vol. 1. – P. 355-362.
  12. Desyatnikov, I.E. The Search Algorithm for Image in Databases / I.E. Desyatnikov, V.A. Utrobin // Computer Optics. – 2011. – Vol. 35(3) – P. 416-422. – (In Russian).
  13. Asatryan, D. Quality Assessment Measure Based on Image Structural Properties / D. Asatryan, K. Egiazarian // Proceedings of the International Workshop on Local and Non-Local Approximation in Image Processing, Finland, Helsinki. – 2009. – P. 70-73.
  14. Timma, F. Non-parametric texture defect detection using Weibull features / F. Timma and E. Barth // Image Processing. Machine Vision Applications IV. Proceedings of SPIE. SPIE-IS&T. – 2011. – V. 7877.
  15. Soottitantawat, S. Texture Classification Using an Invariant Texture Representation and a Tree Matching Kernel / Somkid Soottitantawat and Surapong Auwatanamongkol // IJCSI International Journal of Computer Science Issues. – 2011. – Vol. 8(1). – P. 98-106.
  16. http://hci.iwr.uni-heidelberg.de// Benchmarks/document/weakly-supervised-learning-industrial-optical-insp/ .
    © 2009, IPSI RAS
    Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; e-mail: ko@smr.ru; Phones: +7 (846 2) 332-56-22, Fax: +7 (846 2) 332-56-20