Comparison of HK and SC Curvature Descriptions in a Scale-Space for the Purpose of 3D Object Recognition

Date

2009-01-01

Author

Akagündüz, Erdem
Ulusoy, İlkay

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

171
views

0
downloads

Most 3D object recognition methods use mean-Gaussian curvatures (HK) [2] or shape index-curvedness (SC) [3] values for classification. Although these two curvature descriptions classify objects into same categories, their mathematical definitions vary. In this study a comparion between the two curvature description is carried out for the purpose of 3D object recognition. Since unlike S; H, K and C values are not invariant of scale and resolution, a method to set them fully invariant to any transforation is proposed. The results show that scale and resolution invariant HK curvatire values gives better recognition results compared to SC curvature values.

URI

https://hdl.handle.net/11511/94121

DOI

https://doi.org/10.1109/siu.2009.5136551

Conference Name

IEEE 17th Signal Processing and Communications Applications Conference

Collections

Graduate School of Informatics, Conference / Seminar

Suggestions

OpenMETU
Core

Analysis of Alternative Performance Metrics for Compressive Spectral Imaging Gundogan, Utku; Öktem, Sevinç Figen (null; 2020-10-07) Compressive spectral imaging is a technique that reconstructs the three-dimensional (3D) spectral data cube from limited number of two-dimensional (2D) measurements. In order to obtain this data cube, the technique makes use of the theory of compressed sensing, and employs both an optical and a computational system. However, this optical system can be designed with multiple variations. To evaluate the performance of different designs, there is a need for metrics that are reliable and fast to compute. Curren...
Experimental study on the sensitivity of autocalibration to projective camera model parameters Hassanpour, Reza; Atalay, Mehmet Volkan (2006-04-01) Existing methods of 3-D object modeling and recovering 3-D data from uncalibrated 2-D images are subject to errors introduced by assumptions about camera parameters and mismatches in finding point pairs in the images. In this study, we experimentally evaluate the effect of each of these assumptions together with the inaccuracy in the measurements in the images. Sensitivity of reconstruction errors to inaccuracies in the estimation of camera parameters and mismatches due to noise in input data is measured us...
Silhouette-based 3d reconstruction by energy minimization Mengi, Emre; Atalay, Mehmet Volkan; Department of Computer Engineering (2003) To generate a model of an object in the framework of silhouette based recon struction from multiple views, various energy minimization techniques with dif ferent surface representations are used. Initially, original 3D snakes with layered parametric representation is applied. Snake is deformed to minimize an energy functional imposing smoothness and attraction towards 3D surface points de tected from 2D images. Secondly, a representation in spherical coordinates is suggested and the definition of the energy...
Measurement of the ratio of inclusive jet cross sections using the anti-k(T) algorithm with radius parameters R=0.5 and 0.7 in pp collisions at root s=7 TeV Chatrchyan, S.; et. al. (American Physical Society (APS), 2014-10-01) Measurements of the inclusive jet cross section with the anti-k(T) clustering algorithm are presented for two radius parameters, R = 0.5 and 0.7. They are based on data from LHC proton-proton collisions at root s = 7 TeV corresponding to an integrated luminosity of 5.0 fb(-1) collected with the CMS detector in 2011. The ratio of these two measurements is obtained as a function of the rapidity and transverse momentum of the jets. Significant discrepancies are found comparing the data to leading-order simulat...
Non-parametric and semi-parametric regional modeling of the ionospheric vertical total electron content using ground-based GPS observations Durmaz, Murat; Karslıoğlu, Mahmut Onur; Department of Geodetic and Geographical Information Technologies (2013) Different global and regional models have been proposed for modeling of Vertical Total Electron Content(VTEC). Basis functions such as Spherical Harmonics and tensor products of univariate B-Splines are used for global and regional modeling respectively. The coefficients of the basis functions and Differential Code Biases (DCB) of satellites and receivers are treated as parameters and estimated from geometry-free linear combinations. In this work, a new approach based on non-parametric and semi-parametric m...

Citation Formats

E. Akagündüz and İ. Ulusoy, “Comparison of HK and SC Curvature Descriptions in a Scale-Space for the Purpose of 3D Object Recognition,” presented at the IEEE 17th Signal Processing and Communications Applications Conference, Antalya, Türkiye, 2009, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/94121.