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

From Edges To Contours


What does contour grouping have to do with robotics?
  • Very similar to map-acquisition problem in robotics.
  • Hence we formulate contour grouping as map-acquisition of a virtual robot.
  • The virtual robot walks around 'acquiring the contour'.

Contour acquisition using virtual robot
  • The virtual robot walks along 'center points' constructed from segments on edge image.
  • The contour is a sequence of segment-pairs associated with the center points on the edge image.
  • A reference shape model guides the robots motion and gives sensor information of what to look for.

Reference Shape Model