A 2D Shape Structure for Decomposition and Part Similarity

Kathryn Leonard (1) , Géraldine Morin (2, 3) , Stefanie Hahmann (4) , Axel Carlier (2, 3)

1 California State University Channel Islands
2 IRIT-REVA - Real Expression Artificial Life
3 Toulouse INP - Institut National Polytechnique (Toulouse)
4 IMAGINE - Intuitive Modeling and Animation for Interactive Graphics & Narrative Environments

This paper presents a multilevel analysis of 2D shapes and uses it to find similarities between the different parts of a shape. Such an analysis is important for many applications such as shape comparison, editing, and compression. Our robust and stable method decomposes a shape into parts, determines a parts hierarchy, and measures similarity between parts based on a salience measure on the medial axis, the Weighted Extended Distance Function, providing a multi-resolution partition of the shape that is stable across scale and articulation. Comparison with an extensive user study on the MPEG-7 database demonstrates that our geometric results are consistent with user perception.

Mots clés: medal axis; WEDF; 2D shape; shape structure; shape decomposition; part similarity

Domaines: Géométrie algorithmique [cs.CG]

Kathryn Leonard, Géraldine Morin, Stefanie Hahmann, Axel Carlier. A 2D Shape Structure for Decomposition and Part Similarity. ICPR 2016 - 23rd International Conference on Pattern Recognition, Dec 2016, Cancun, Mexico. pp.3216-3221, ⟨10.1109/ICPR.2016.7900130⟩. ⟨hal-01374810⟩