Comparison of Shape Descriptors for Mice Behavior Recognition

  • Jonathan de Andrade Silva
  • Wesley Nunes Gonçalves
  • Bruno Brandoli Machado
  • Hemerson Pistori
  • Albert Schiaveto de Souza
  • Kleber Padovani de Souza
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6419)

Abstract

Shape representation provides fundamental features for many applications in computer vision and it is known to be important cues for human vision. This paper presents an experimental study on recognition of mice behavior. We investigate the performance of the four shape recognition methods, namely Chain-Code, Curvature, Fourier descriptors and Zernike moments. These methods are applied to a real database that consists of four mice behaviors. Our experiments show that Zernike moments and Fourier descriptors provide the best results. To evaluate the noise tolerance, we corrupt each contour with different levels of noise. In this scenario, Fourier descriptor shows invariance to high levels of noise.

Keywords

Computer Vision Shape Descriptors Mice Behavior 

References

  1. 1.
    Luciano, Cesar, R.M.: Shape Analysis and Classification: Theory and Practice. Image Processing Series. CRC, Boca Raton (2000)MATHGoogle Scholar
  2. 2.
    Salem, A.B.M., Sewisy, A.A., Elyan, U.A.: A vertex chain code approach for image recognition. Graphics, Vision and Image Processing ICGST 05 (2005)Google Scholar
  3. 3.
    Zhang, D., Lu, G.: A comparative study of curvature scale space and fourier descriptors for shape-based image retrieval. J. Visual Commun. Image Represent 14, 39–57 (2003)CrossRefGoogle Scholar
  4. 4.
    Zhang, D., Lu, G.: Study and evaluation of different fourier methods for image retrieval. Image Vision Comput. 23, 33–49 (2005)CrossRefGoogle Scholar
  5. 5.
    Hwang, S.K., Kim, W.Y.: A novel approach to the fast computation of zernike moments. Pattern Recognition 39, 2065–2076 (2006)CrossRefMATHGoogle Scholar
  6. 6.
    Chong, C.W., Raveendran, P., Mukundan, R.: Translation invariants of zernike moments. Pattern Recognition, 1765–1773 (2003)Google Scholar
  7. 7.
    Yang, G.Y., Shu, H.Z., Toumoulin, C., Han, G.N., Luo, L.M.: Efficient legendre moment computation for grey level images. Pattern Recognition 39, 74–80 (2006)CrossRefGoogle Scholar
  8. 8.
    Morrow-Tesch, J., Dailey, J.W., JIang, H.: A video data base system for studying animal behavior. Journal of Animal Science 76, 2605–2608 (1998)CrossRefGoogle Scholar
  9. 9.
    Gonçalves, W.N., Saueia, V.A., Machado, B.B., de Silva, J.A., de Souza, K.P., Pistori, H.: Técnicas de segmentação baseadas em subtração de fundo e modelos de cores: Um estudo comparativo. XXVIII CILAMCE (2007)Google Scholar
  10. 10.
    Pistori, H., Odakura, V.V.V.A., Monteiro, J.B.O., Gonçalves, W.N., Roel, A.R., de Silva, J.A., Machado, B.B.: Mice and larvae tracking using a particle filter with an auto-adjustable observation model. Pattern Recog. Lett. 31, 337–346 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Jonathan de Andrade Silva
    • 1
  • Wesley Nunes Gonçalves
    • 1
  • Bruno Brandoli Machado
    • 1
  • Hemerson Pistori
    • 2
  • Albert Schiaveto de Souza
    • 3
  • Kleber Padovani de Souza
    • 2
  1. 1.Computer Science DepartmentUniversity of São Paulo (USP)São CarlosBrazil
  2. 2.Research Group in Engineering and ComputingDom Bosco Catholic UniversityBrazil
  3. 3.Department of MorphophysiologyFederal University of Mato Grosso do SulBrazil

Personalised recommendations