Presentation is loading. Please wait.

Presentation is loading. Please wait.

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

Similar presentations


Presentation on theme: "1 P. Arbelaez, M. Maire, C. Fowlkes, J. Malik. Contour Detection and Hierarchical image Segmentation. IEEE Trans. on PAMI, 2011. Student: Hsin-Min Cheng."— Presentation transcript:

1 1 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 2

3 Introduction Original ImageContour  Contour 3

4 Introduction Original ImageSegmentation  Segmentation 4

5 Introduction  From Contour to Segmentation Original ImageSegmentationContour 5

6 Introduction  Goal  Contour Detection  Hierarchical Segmentation from Contours Original ImageSegmentationContour 6

7 Outline  Introduction  Contour Detection  Hierarchical Segmentation  Results  Conclusion 7

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

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

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

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

12 12  Learn local boundary cues  Local Cues Combination 12 Contour Detection ure

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

14  Global framework to capture closure, continuity Contour Detection 14

15  Local Cues and global cues combination Contour Detection 15 Local CuesGlobal cues

16 Outline  Introduction  Contour Detection  Hierarchical Segmentation  Results  Conclusion 16

17 Hierarchical Segmentation  Multiple Segmentations  Fixed resolution  Hierarchy of Segmentations  Flexible resolution adjustment 17

18 Hierarchical Segmentation 1. From contours to segmentation 2. Hierarchical segmentation by iterative merging 18

19 Hierarchical Segmentation  From contours to segmentation  Watershed Transform  Concept 19

20 Hierarchical Segmentation  From contours to segmentation  Watershed Transform  Example 20

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

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

23 Hierarchical Segmentation  Hierarchical segmentation by iterative merging  Hierarchical segmentation  Example 23

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

25 Outline  Introduction  Contour Detection  Hierarchical Segmentation  Results  Conclusion 25

26 Result 26

27 Result 27

28 Result 28 Evaluation of segmentation algorithmsEvaluation of contour detector  BSDS300 Dataset

29 Outline  Introduction  Contour Detection  Hierarchical Segmentation  Results  Conclusion 29

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 30

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. 31

32 Outline  Introduction  Contour Detection  Hierarchical Segmentation  Evaluation  Results 32

33 Boundary Benchmarks  ODS : optimal dataset scale  OIS : optimal image scale  AP :average precision 33

34 Region benchmarks(1)  Segment Covering  Probabilistic Rand Index [Unnikrishnan et. al. 07] [Yang et. al. 08]  Variation of Information [Meila 05] Distance Between two segmentations in terms of their average conditional entropy given by 34

35 Region benchmarks(2) CoveringRand Index Variation of Information 35

36 Additional Dataset 36


Download ppt "1 P. Arbelaez, M. Maire, C. Fowlkes, J. Malik. Contour Detection and Hierarchical image Segmentation. IEEE Trans. on PAMI, 2011. Student: Hsin-Min Cheng."

Similar presentations


Ads by Google