A New Rotation Invariant Weber Local Descriptor for Recognition of Skin Diseases

  • Anabik Pal
  • Nibaran Das
  • Somenath Sarkar
  • Dwijendranath Gangopadhyay
  • Mita Nasipuri
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8251)


A new rotation invariant Weber Local texture Descriptor(WLD) is proposed here. Performance of the developed features is evaluated on the basis of the recognition accuracies of SVM classifiers, trained and tested with the extracted features from the images of skins affected with three popular skin diseases such as Leprosy, Tineaversicolor, Vitiligo, and also normal skin, collected from School of Tropical Medicine, Kolkata. The WLD features are extracted with variations of the radius from 1 to 3 considering perimeters of having 8, 16 and 24 pixels respectively. The modified WLD provides an average improvement of 4.79% in recognition accuracy over the normal WLD in the present four class problem. Dividing each sample image into 4 sub-regions through its centre of gravity and extracting WLD features from each of them. Thus we have extracted two different feature sets having normal WLD and rotation invariant WLD. They provide the maximum recognition accuracies of 85.06% and 87.36% respectively using SVM classiifiers on test set.


Texture WLD SVM Leprosy Tineaversicolor Vitiligo 


  1. 1.
    Haralick, R.M., et al.: Textural Features for Image Classification. IEEE Transactions on Systems, Man and Cybernetics SMC-3, 610–621 (1973)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Haralick, R.M.: Statistical and structural approaches to texture. Proceedings of the IEEE 67, 786–804 (1979)CrossRefGoogle Scholar
  3. 3.
    Galloway, M.M.: Texture analysis using gray level run lengths. Computer Graphics and Image Processing 4, 172–179 (1975)CrossRefGoogle Scholar
  4. 4.
    Ojala, T., et al.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 971–987 (2002)CrossRefGoogle Scholar
  5. 5.
    Jabid, T., et al.: Gender Classification using Local Directional Pattern (LDP). Presented at the International Conference on Pattern Recognition (2010)Google Scholar
  6. 6.
    Jie, C., et al.: WLD: A Robust Local Image Descriptor. IEEE Transactions on Pattern Analysis and Machine Intelligence 32, 1705–1720 (2010)CrossRefGoogle Scholar
  7. 7.
    Jain, A.K.: Fundamentals of Digital Signal Processing: Prentice-Hall (1989)Google Scholar
  8. 8.
    Hall, M., et al.: The WEKA data mining software: an update. ACM SIGKDD Explorations Newsletter 11, 10–18 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Anabik Pal
    • 1
  • Nibaran Das
    • 2
  • Somenath Sarkar
    • 3
  • Dwijendranath Gangopadhyay
    • 4
  • Mita Nasipuri
    • 2
  1. 1.Department of Information TechnologyJadavpur UniversityKolkataIndia
  2. 2.Department of Computer Science and EngineeringJadavpur UniversityKolkataIndia
  3. 3.Department of DermatologySchool of Tropical MedicineKolkataIndia
  4. 4.Department of DermatologyBurdwan Medical CollegeBurdwanIndia

Personalised recommendations