shape representation and description
play

Shape Representation and Description Alexandre Falc ao Institute - PowerPoint PPT Presentation

Shape Representation and Description Alexandre Falc ao Institute of Computing - University of Campinas afalcao@ic.unicamp.br Alexandre Falc ao MC920/MO443 - Indrodu c ao ao Proc. de Imagens Introduction A segmented object may


  1. Shape Representation and Description Alexandre Falc˜ ao Institute of Computing - University of Campinas afalcao@ic.unicamp.br Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  2. Introduction A segmented object may contain multiple boundaries. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  3. Introduction A segmented object may contain multiple boundaries. We will focus on 2D boundaries represented by closed, connected and oriented curves (contours). Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  4. Introduction A segmented object may contain multiple boundaries. We will focus on 2D boundaries represented by closed, connected and oriented curves (contours). Each contour defines a shape whose properties are very important for image analysis. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  5. Introduction Other shape representations can be derived from a contour and their properties are usually encoded in a more compact representation (i.e., feature vector). Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  6. Introduction Other shape representations can be derived from a contour and their properties are usually encoded in a more compact representation (i.e., feature vector). Some feature vectors require specific distance functions to compute shape similarities independently of their orientation and size. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  7. Introduction Other shape representations can be derived from a contour and their properties are usually encoded in a more compact representation (i.e., feature vector). Some feature vectors require specific distance functions to compute shape similarities independently of their orientation and size. The pair, feature extraction function and distance function, is called here a descriptor. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  8. Introduction The Euclidean IFT from a contour S (lecture 2) creates in V multiscale contours (iso-contours) by subsequent exact dilations and erosions of S [1]. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  9. Introduction Each contour is related to its internal and external skeletons (point sets with at least two equidistant pixels in the contour). Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  10. Introduction Each contour is related to its internal and external skeletons (point sets with at least two equidistant pixels in the contour). The Euclidean IFT can output a labeled map L , which is used to create internal and external multiscale skeletons. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  11. Introduction Each contour is related to its internal and external skeletons (point sets with at least two equidistant pixels in the contour). The Euclidean IFT can output a labeled map L , which is used to create internal and external multiscale skeletons. These skeletons present a highly desirable characteristic of being one-pixel-wide and connected in all scales. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  12. Introduction Each contour is related to its internal and external skeletons (point sets with at least two equidistant pixels in the contour). The Euclidean IFT can output a labeled map L , which is used to create internal and external multiscale skeletons. These skeletons present a highly desirable characteristic of being one-pixel-wide and connected in all scales. In the presence of multiple contours, a simple variant computes the skeleton by influence zones (SKIZ — a point set with equidistant pixels in at least two contours). Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  13. Introduction A given contour S . Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  14. Introduction A given contour S . Pixels along S receive a subsequent label from 1 to |S| . Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  15. Introduction A given contour S . Pixels along S receive a subsequent label from 1 to |S| . The labels are propagated to form a label map L (discrete Voronoi regions). Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  16. Introduction A given contour S . Pixels along S receive a subsequent label from 1 to |S| . The labels are propagated to form a label map L (discrete Voronoi regions). A multiscale skeleton is created from local differences in L . Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  17. Introduction A given contour S . Pixels along S receive a subsequent label from 1 to |S| . The labels are propagated to form a label map L (discrete Voronoi regions). A multiscale skeleton is created from local differences in L . Skeletons are obtained by thresholding the multiscale skeleton at increasing scales. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  18. Introduction A given contour S . Pixels along S receive a subsequent label from 1 to |S| . The labels are propagated to form a label map L (discrete Voronoi regions). A multiscale skeleton is created from local differences in L . Skeletons are obtained by thresholding the multiscale skeleton at increasing scales. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  19. Introduction A given contour S . Pixels along S receive a subsequent label from 1 to |S| . The labels are propagated to form a label map L (discrete Voronoi regions). A multiscale skeleton is created from local differences in L . Skeletons are obtained by thresholding the multiscale skeleton at increasing scales. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  20. Introduction The Euclidean IFT with a small dilation radius from an internal skeleton S creates a root map R , Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  21. Introduction The Euclidean IFT with a small dilation radius from an internal skeleton S creates a root map R , the aperture angles of the discrete Voronoi regions in R are used to detect salience points of the skeleton, Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  22. Introduction The Euclidean IFT with a small dilation radius from an internal skeleton S creates a root map R , the aperture angles of the discrete Voronoi regions in R are used to detect salience points of the skeleton, from salience points of the internal and external skeletons, we detect convex and concave salience points of the contour. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  23. Introduction The Euclidean IFT can also speed up the computation of the largest ellipse (tensor scale) centered at each pixel, creating a region-based shape representation. Orientation ( s ) = angle between t 1 ( s ) and the horizontal axis. � 1 − | t 2 ( s ) | 2 Anisotropy ( s ) = | t 1 ( s ) | 2 . Thickness ( s ) = | t 2 ( s ) | . Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  24. Introduction By using the HSI color space, the tensor orientation at each pixel is represented by a distinct color. The region-based representation stores orientation and anisotropy at each pixel. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  25. Organization of the lecture Muliscale skeletonization and SKIZ [1]. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  26. Organization of the lecture Muliscale skeletonization and SKIZ [1]. Contour and skeleton saliences [2]. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  27. Organization of the lecture Muliscale skeletonization and SKIZ [1]. Contour and skeleton saliences [2]. Tensor scale computation [3]. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  28. Organization of the lecture Muliscale skeletonization and SKIZ [1]. Contour and skeleton saliences [2]. Tensor scale computation [3]. Shape description from these representations [4]. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  29. Organization of the lecture Muliscale skeletonization and SKIZ [1]. Contour and skeleton saliences [2]. Tensor scale computation [3]. Shape description from these representations [4]. Combining multiple descriptors [5]. Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  30. Multiscale skeletonization and SKIZ Consider a binary image ˆ I = ( D I , I ) with m disjoint contours S i ⊂ D I , i = 1 , 2 , . . . , m . Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

  31. Multiscale skeletonization and SKIZ Consider a binary image ˆ I = ( D I , I ) with m disjoint contours S i ⊂ D I , i = 1 , 2 , . . . , m . By circumscribing each contour in a given orientation (clockwise), a function λ p ( t ) assigns to each pixel t ∈ S i a subsequent integer number from 1 to |S i | . Alexandre Falc˜ ao MC920/MO443 - Indrodu¸ c˜ ao ao Proc. de Imagens

Recommend


More recommend