Home
Related Papers
Researchers
Help

Table of Contents

Partial Shape Similarity

0. Motivation
1. Edge Detection
2. Edge Grouping
3. Extraction of Contour Parts
4. Recognizing Shapes by Parts
5. Results

---

Structural Shape Similarity

0. Introduction
1. Shape Segmentation
2. Skeleton Computation
3. Skeleton Pruning
4. Recognizing Shapes by Structures

---

Contour Grouping Based on Local Symetry

0. Introduction
1. From Edges To Contours
2. Center points
3. Reference Shape Model
4. Particle Filter
5.1. Experimental Result 1
5.2. Experimental Result 2
5.3. Experimental Result 3
5.4. Experimental Result 4
5.5. Experimental Result 5
5.6. Experimental Result 6
5.7. Experimental Result 7
5.8. Experimental Result 8
6. Conclusion
7. Contour Grouping Video

Experimental Results

Some Technical Details

• 100 particles were used for filtering.
• On average about 200 followers were chosen for each particle as prior boosting. If there is lot of clutter more followers were chosen. This is automatically done in our program by our proposal.
• Initialization was done around the beginning of the shape we want to group.
• The parameters used for particle evaluation were pretty stable and one set worked for almost all images.

<- Prev

Next ->