Description of shape information for 2-D and 3-D objects

By E. Paquet, M. Rioux, Anil M. Murching, T. Naveen, Ali J. Tabatabai. Signal processing. Image communication, 2000

356 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1e93e63277c85eb6fd6bb2664a84f395e2497898

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Tools for 3D-object retrieval: Karhunen-Loeve transform and spherical harmonics (2001, methodology): “[5] used centers of gravity of triangles as vectors for the PCA with weights proportional to triangle areas.”
3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey (2014, background): “Examples in this category include geometric 3D moments [18], shape distribution [19], viewpoint feature histogram [20], and potential well space embedding [21].”
Rotational Projection Statistics for 3D Local Surface Description and Object Recognition (2013, background): “Examples of these algorithms include the geometric 3D moments (Paquet et al., 2000), shape distribution (Osada et al., 2002) and spherical harmonics (Funkhouser et al., 2003).”
A survey of content based 3D shape retrieval methods (2004, methodology): “Paquet et al. [ 98 ] apply bounding boxes, cords-based, moments-based and wavelet-based descriptors for 3D shape matching.”
3D Model Retrieval with Spherical Harmonics and Moments (2001, methodology): “Feature vectors for 3D model retrieval can be based on Fourier descriptors of silhouettes [1, 5], on 3D moments [8], rendered images or depth maps [5], or on volumetric representation of the model surface [2] or the corresponding volume (if the surface bounds a solid) [7, 6, 8].”
On Visual Similarity Based 3D Model Retrieval (2003, background): “(4) The fourth stage is the same as full comparison, but only the Zernike moment coefficients, quantized to 4 bits, are used.”