Recognition of shapes by editing shock graphs

@inproceedings{citeulike:1167607, abstract = {This paper presents a novel recognition framework which is based on matching shock graphs of 2D shape outlines, where the distance between two shapes is defined to be the cost of the least action path deforming one shape to the other. Two key issues are addressed which render the implementation of this framework practical. First, the shape space is partitioned by defining an equivalence class on shapes, where two shapes with the same shock graph topology are considered equivalent. The space of deformations is then discretized based on a formal enumeration of all possible transitions, where the shock graph topology changes, by defining all deformations with the same sequence of shock graph transitions as equivalent. Second, we employ a graph edit distance algorithm that searches in the space of all possible transition sequences and finds the globally optimal sequence in polynomial time. The effectiveness of the proposed technique in the presence of a variety of visual transformations including occlusion, articulation and deformation of parts, shadow and highlights, viewpoint variation, scale, and boundary perturbations is demonstrated. Indexing into two separate databases of roughly 100 shapes results in 100\% accuracy for top three matches and 99.5\% for the next three matches}, citeulike-article-id = {1167607}, journal = {Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on}, pages = {755--762 vol.1}, posted-at = {2007-03-16 13:32:59}, priority = {2}, title = {Recognition of shapes by editing shock graphs}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=937602}, volume = {1}, year = {2001} }

TY - CONF ID - citeulike:1167607 L3 - citeulike-article-id:1167607 N2 - This paper presents a novel recognition framework which is based on matching shock graphs of 2D shape outlines, where the distance between two shapes is defined to be the cost of the least action path deforming one shape to the other. Two key issues are addressed which render the implementation of this framework practical. First, the shape space is partitioned by defining an equivalence class on shapes, where two shapes with the same shock graph topology are considered equivalent. The space of deformations is then discretized based on a formal enumeration of all possible transitions, where the shock graph topology changes, by defining all deformations with the same sequence of shock graph transitions as equivalent. Second, we employ a graph edit distance algorithm that searches in the space of all possible transition sequences and finds the globally optimal sequence in polynomial time. The effectiveness of the proposed technique in the presence of a variety of visual transformations including occlusion, articulation and deformation of parts, shadow and highlights, viewpoint variation, scale, and boundary perturbations is demonstrated. Indexing into two separate databases of roughly 100 shapes results in 100% accuracy for top three matches and 99.5% for the next three matches JF - Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on EP - 762 vol.1 TI - Recognition of shapes by editing shock graphs VL - 1 SP - 755 PY - 2001/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=937602 ER -