1 / 31

Contour Detection and Hierarchical Image Segmentation

Contour Detection and Hierarchical Image Segmentation. P. Arbelaez , M. Maire , C. Fowlkes , J. Malik . Contour Detection and Hierarchical image Segmentation. IEEE Trans. on PAMI , 2011. . Student: Hsin -Min Cheng Advisor: Sheng-Jyh Wang. Outline. Introduction Contour Detection

camden
Télécharger la présentation

Contour Detection and Hierarchical Image Segmentation

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. Contour Detection and Hierarchical Image Segmentation P. Arbelaez, M. Maire, C. Fowlkes, J. Malik. Contour Detection and Hierarchical image Segmentation. IEEE Trans. on PAMI , 2011. Student: Hsin-Min Cheng Advisor: Sheng-Jyh Wang

  2. Outline • Introduction • Contour Detection • Hierarchical Segmentation • Results • Conclusion

  3. Introduction • Contour Original Image Contour

  4. Introduction • Segmentation Original Image Segmentation

  5. Introduction • From Contour to Segmentation Original Image Contour Segmentation

  6. Introduction • Goal • Contour Detection • Hierarchical Segmentation from Contours Original Image Contour Segmentation

  7. Outline • Introduction • Contour Detection • Hierarchical Segmentation • Results • Conclusion

  8. Contour Detection 1. Learn local boundary cues 2. Global framework to capture closure, continuity 3. Local Cues and global cues combination

  9. Contour Detection • Learn local boundary cues Local Boundary Cues Image Cue Combination Brightness Model Color Texture

  10. Contour Detection • Learn local boundary cues • Brightness • L*a*b* colorspace • Color • L*a*b* colorspace • Texture • Convolve with 17 filters Filters for creating textons

  11. Contour Detection • Learn local boundary cues • Oriented gradient of histograms • Example • Gradient magnitude G at location(x, y) • Three scales of r ure 11

  12. Contour Detection • Learn local boundary cues • Local Cues Combination ure 12 12

  13. Contour Detection • Global framework to capture closure, continuity V: image pixels E: connections between pairs of nearby pixels =>Build a weighted graph G=(V,E) from image

  14. Contour Detection • Global framework to capture closure, continuity

  15. Contour Detection • Local Cues and global cues combination Local Cues Global cues

  16. Outline • Introduction • Contour Detection • Hierarchical Segmentation • Results • Conclusion

  17. Hierarchical Segmentation • Multiple Segmentations • Fixed resolution • Hierarchy of Segmentations • Flexible resolution adjustment

  18. Hierarchical Segmentation • From contours to segmentation • Hierarchical segmentation by iterative merging

  19. Hierarchical Segmentation • From contours to segmentation • Watershed Transform • Concept

  20. Hierarchical Segmentation • From contours to segmentation • Watershed Transform • Example

  21. Hierarchical Segmentation • From contours to segmentation • Watershed Transform Artifacts Boundary strength Weight each arc

  22. Hierarchical Segmentation • From contours to segmentation • Oriented Watershed Transform WT OWT

  23. Hierarchical Segmentation • Hierarchical segmentation by iterative merging • Hierarchical segmentation • Example

  24. Brief Summary Original Image - Local cues - Global cues Oriented Gradient of histograms Contour Oriented Watershed Transform Hierarchical Segmentation Iterative Merging

  25. Outline • Introduction • Contour Detection • Hierarchical Segmentation • Results • Conclusion

  26. Result

  27. Result

  28. Result • BSDS300 Dataset Evaluation of contour detector Evaluation of segmentation algorithms

  29. Outline • Introduction • Contour Detection • Hierarchical Segmentation • Results • Conclusion

  30. Conclusion • A high performance contour detector, combining local and global image information • A method to transform any contour detector signal into a hierarchy of regions while preserving contour quality

  31. Reference • P. Arbelaez, M. Maire, C. Fowlkes and J. Malik. Contour Detection and Hierarchical Image Segmentation. IEEE TPAMI, Vol. 33, No. 5, pp. 898-916, May 2011 • P. Arbelaez, M. Maire, C. Fowlkes and J. Malik. From Contours to Regions: An Empirical Evaluation. In CVPR 2009. • P. Arbelaez and L. Cohen. Constrained Image Segmentation from Hierarchical Boundaries. In CVPR 2008.

More Related