2016
Journal article  Restricted

Scale space graph representation and kernel matching for non rigid and textured 3D shape retrieval

Garro V., Giachetti A.

Computational Theory and Mathematics  Scene Analysis  Spectral descriptors  Shape analysis  Artificial Intelligence  Computer Vision and Pattern Recognition  Software  Information Search and Retrieval  Applied Mathematics  Graph matching 

In this paper we introduce a novel framework for 3D object retrieval that relies on tree-based shape representations (TreeSha) derived from the analysis of the scale-space of the Auto Diffusion Function (ADF) and on specialized graph kernels designed for their comparison. By coupling maxima of the Auto Diffusion Function with the related basins of attraction, we can link the information at different scales encoding spatial relationships in a graph description that is isometry invariant and can easily incorporate texture and additional geometrical information as node and edge features. Using custom graph kernels it is then possible to estimate shape dissimilarities adapted to different specific tasks and on different categories of models, making the procedure a powerful and flexible tool for shape recognition and retrieval. Experimental results demonstrate that the method can provide retrieval scores similar or better than state-of-the-art on textured and non textured shape retrieval benchmarks and give interesting insights on effectiveness of different shape descriptors and graph kernels.

Source: IEEE transactions on pattern analysis and machine intelligence 38 (2016): 1258–1271. doi:10.1109/TPAMI.2015.2477823

Publisher: IEEE Computer Society., [New York], Stati Uniti d'America


Metrics



Back to previous page
BibTeX entry
@article{oai:it.cnr:prodotti:344207,
	title = {Scale space graph representation and kernel matching for non rigid and textured 3D shape retrieval},
	author = {Garro V. and Giachetti A.},
	publisher = {IEEE Computer Society., [New York], Stati Uniti d'America},
	doi = {10.1109/tpami.2015.2477823},
	journal = {IEEE transactions on pattern analysis and machine intelligence},
	volume = {38},
	pages = {1258–1271},
	year = {2016}
}