1 / 30

Otolith Shape Analysis using Wavelet Transfoms and Curvature Scale Space

Otolith Shape Analysis using Wavelet Transfoms and Curvature Scale Space. Vicenç Parisi Baradad, Joan Cabestany, Jaume Piera Emili Garcia-Ladona, Toni Lombarte. INTRODUCTION – Contour – Wavelet – CSS – Fourier – Matching. Introduction. Contour coding Wavelet Transform

Download Presentation

Otolith Shape Analysis using Wavelet Transfoms and Curvature Scale Space

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Otolith Shape Analysisusing Wavelet TransfomsandCurvature Scale Space Vicenç Parisi Baradad, Joan Cabestany, Jaume Piera Emili Garcia-Ladona, Toni Lombarte

  2. INTRODUCTION – Contour – Wavelet – CSS – Fourier – Matching Introduction • Contour coding • Wavelet Transform • Curvature Scale Space representation • Fourier Transform • Data base retrieval

  3. Introduction – CONTOUR – Wavelet – CSS – Fourier– Matching • Coordinates (x,y)

  4. Introduction – CONTOUR – Wavelet – CSS – Fourier – Matching • Equiangle coordinates

  5. Introduction – CONTOUR – Wavelet – CSS – Fourier – Matching • Chain code

  6. Introduction – Contour – WAVELET – CSS – Fourier – Matching Wavelet Transform

  7. Introduction – Contour – WAVELET – CSS – Fourier – Matching

  8. Introduction – Contour – WAVELET – CSS – Fourier – Matching • Mother wavelet: smoothing function second derivative

  9. Introduction – Contour – Wavelet– CSS – Fourier– Matching Curvature Scale Space • Invariance to image translation, scale and rotation changes • Robust to shear • Good performance against high frequency noise

  10. Introduction – Contour – Wavelet– CSS – Fourier– Matching Contour Smoothing

  11. Introduction – Contour – Wavelet– CSS – Fourier– Matching Curvature Inflection Points

  12. Introduction – Contour – Wavelet– CSS – Fourier– Matching Sampling Invariance 150 samples 512 samples CSS normalized

  13. Introduction – Contour – Wavelet– CSS – Fourier– Matching Noise inmunity Low scales elimination increases noise inmunity

  14. Introduction – Contour – Wavelet– CSS – Fourier– Matching Scaling invariance

  15. Introduction – Contour – Wavelet– CSS – Fourier– Matching Rotation invariance Rotation = Maxima translation

  16. Introduction – Contour – Wavelet– CSS – Fourier– Matching Shear "invariance" Shear produces slight changes

  17. Introduction – Contour – Wavelet– CSS– FOURIER – Matching Fourier Transform • Integral covers whole contour • Singularities not located Cosinus Sinus

  18. Data Base 107 otoliths Wavelet Fourier CSS

  19. Introduction – Contour – Wavelet– CSS– Fourier – MATCHING Wavelet Matching • Energy conservation • Wavelet distance • Zero Crossing distance

  20. Introduction – Contour – Wavelet– CSS– Fourier – MATCHING

  21. Introduction – Contour – Wavelet– CSS– Fourier – MATCHING

  22. Introduction – Contour – Wavelet– CSS– Fourier – MATCHING

  23. Introduction – Contour – Wavelet– CSS– Fourier – MATCHING

  24. Introduction – Contour – Wavelet– CSS– Fourier – MATCHING CSS Matching Image Model

  25. Introduction – Contour – Wavelet– CSS– Fourier – MATCHING Noise, Rotation and Shear

  26. Introduction – Contour – Wavelet– CSS– Fourier– MATCHING Fourier Matching

  27. Introduction – Contour – Wavelet– CSS– Fourier – MATCHING Fourier Matching under Rotation

  28. Introduction – Contour – Wavelet– CSS– Fourier – MATCHING Fourier Matching under Shear

  29. Introduction – Contour – Wavelet– CSS– Fourier– MATCHING Fourier Matching under Noise

  30. Introduction – Contour – Wavelet– CSS– Fourier – Matching Conclusions • (Wavelet + chain code) and CSS robust under affine transformations and Shear • Wavelet and CSS locate Singularities • Wavelet + CSS allow database compression • Wavelet allows perfect contour reconstruction

More Related