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
Skeleton Pruning Recongizing Shapes by Skeleton Similarity Recongizing Shapes by Skeleton Similarity

Recognizing Shapes by Skeleton Similarity

Shape similarity based on correspondence of the skeleton endpoints . 
The red outlines represent the DCE-derived contour.
Similar structures at skewed angles can be easily matched. Despite distortion, the stability of skeletons obtained by our method allows for shape similarity recognition.
Corresponding points between two horse images. Corresponding points between two flower images.
Even though shapes of a similar nature may be viewed from different angles or viewed in a different position, the skeletal structures are robust enough to still allow shape recognition.
Corresponding points between two hand images. Corresponding points between two person images.