Download presentation
Presentation is loading. Please wait.
1
Segmentation and Boundary Detection Using Multiscale Measurements Ronen Basri Achi Brandt Meirav Galun Eitan Sharon
2
Eitan Sharon - Weizmann Institute Image Segmentation
3
Eitan Sharon - Weizmann Institute Local Uncertainty
4
Eitan Sharon - Weizmann Institute Global Certainty
5
Eitan Sharon - Weizmann Institute Local Uncertainty
6
Eitan Sharon - Weizmann Institute Global Certainty
7
Eitan Sharon - Weizmann Institute Coarse Measurements for Texture
8
Eitan Sharon - Weizmann Institute A Chicken and Egg Problem Problem: Coarse measurements mix neighboring statistics Solution: support of measurements is determined as the segmentation process proceeds
9
Eitan Sharon - Weizmann Institute Normalized-cuts measure in graphs Complete hierarchy in linear time Use multiscale measures of intensity, texture, shape, and boundary integrity Segmentation by Weighted Aggregation
10
Eitan Sharon - Weizmann Institute Normalized-cuts measure in graphs Complete hierarchy in linear time Use multiscale measures of intensity, texture, shape, and boundary integrity Segmentation by Weighted Aggregation
11
Eitan Sharon - Weizmann Institute Segmentation by Weighted Aggregation Normalized-cuts measure in graphs Complete hierarchy in linear time Use multiscale measures of intensity, texture, shape and boundary integrity
12
Eitan Sharon - Weizmann Institute The Pixel Graph Couplings Reflect intensity similarity Low contrast – strong coupling High contrast – weak coupling
13
Eitan Sharon - Weizmann Institute Hierarchical Graph
14
Eitan Sharon - Weizmann Institute Hierarchy in SWA
15
Eitan Sharon - Weizmann Institute Normalized-Cut Measure
16
Eitan Sharon - Weizmann Institute Normalized-Cut Measure High-energy cut Minimize:
17
Eitan Sharon - Weizmann Institute Normalized-Cut Measure Low-energy cut Minimize:
18
Eitan Sharon - Weizmann Institute Segment Detection
19
Eitan Sharon - Weizmann Institute Coarse-Scale Measurements Average intensities of aggregates Multiscale intensity-variances of aggregates Multiscale shape-moments of aggregates Boundary alignment between aggregates
20
Eitan Sharon - Weizmann Institute Adaptive vs. Rigid Measurements Averaging Our algorithm - SWA Geometric Original
21
Eitan Sharon - Weizmann Institute Our algorithm - SWA Adaptive vs. Rigid Measurements Interpolation Geometric Original
22
Eitan Sharon - Weizmann Institute Use Averages to Modify the Graph
23
Eitan Sharon - Weizmann Institute Use Averages to Modify the Graph
24
Eitan Sharon - Weizmann Institute Texture Examples
25
Eitan Sharon - Weizmann Institute Isotropic and Oriented Filters Textons by K-Means Malik et al IJCV2001 A brief tutorial
26
Eitan Sharon - Weizmann Institute Oriented Texture in SWA Shape Moments Oriented Texture of aggregate – orientation, width and length in all scales center of mass width length orientation with Meirav Galun
27
Eitan Sharon - Weizmann Institute Boundary Integrity in SWA
28
Eitan Sharon - Weizmann Institute Hierarchy in SWA
29
Eitan Sharon - Weizmann Institute SWA Linear in # of points (a few dozen operations per point) Detects the salient segments Hierarchical structure
30
Eitan Sharon - Weizmann Institute Experiments Our SWA algorithm (CVPR’00 + CVPR’01) run-time: 5-10 seconds. Normalized cuts (Shi and Malik, PAMI ’ 00; Malik et al., IJCV ’ 01) run-time: about 10-15 minutes. Software courtesy of Doron Tal, UC Berkeley. images on a pentium III 1000MHz PC:
31
Eitan Sharon - Weizmann Institute Isotropic Texture - Horse I Our Algorithm (SWA) Normalized Cuts
32
Eitan Sharon - Weizmann Institute Isotropic Texture - Horse II Our Algorithm (SWA)Normalized Cuts
33
Eitan Sharon - Weizmann Institute Isotropic Texture - Tiger Normalized Cuts Our Algorithm (SWA)
34
Eitan Sharon - Weizmann Institute Isotropic Texture - Butterfly Our Algorithm (SWA) Normalized Cuts
35
Eitan Sharon - Weizmann Institute Isotropic Texture - Leopard Our Algorithm (SWA)
36
Eitan Sharon - Weizmann Institute Isotropic Texture - Dalmatian Dog Our Algorithm (SWA)
37
Eitan Sharon - Weizmann Institute Isotropic Texture - Squirrel Our Algorithm (SWA)Normalized Cuts
38
Eitan Sharon - Weizmann Institute Full Texture - Squirrel Our Algorithm (SWA)Normalized Cuts with Meirav Galun
39
Eitan Sharon - Weizmann Institute Full Texture - Composition Our Algorithm (SWA) with Meirav Galun
40
Eitan Sharon - Weizmann Institute Full Texture – Lion Cub Our Algorithm (SWA) with Meirav Galun
41
Eitan Sharon - Weizmann Institute Full Texture – Polar Bear Our Algorithm (SWA) with Meirav Galun
42
Eitan Sharon - Weizmann Institute Full Texture – Penguin Our Algorithm (SWA) with Meirav Galun
43
Eitan Sharon - Weizmann Institute Full Texture – Leopard Our Algorithm (SWA) with Meirav Galun
44
Eitan Sharon - Weizmann Institute Full Texture – Leopard Our Algorithm (SWA) with Meirav Galun
45
Eitan Sharon - Weizmann Institute Full Texture – Owl Our Algorithm (SWA) with Meirav Galun
46
Eitan Sharon - Weizmann Institute Full Texture – Bird Our Algorithm (SWA) with Meirav Galun
47
Eitan Sharon - Weizmann Institute Separation of Parts Poissonian u: Δu = 1 u = 0 outside the segment
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.