25,677 Hits in 3.0 sec

Robust Principal Curvatures on Multiple Scales [article]

Yong-Liang Yang, Yu-Kun Lai, Shi-Min Hu, Helmut Pottmann
2006 Symposium on geometry processing : [proceedings]. Symposium on Geometry Processing  
As to applications, we address computing principal curves and feature extraction on multiple scales.  ...  This also allows us to define principal curvatures "at scale r" in a way which is consistent with the classical setting.  ...  We have shown how to define and compute principal curvatures κ r 1 , κ r 2 on multiple scales, e.g. based on formulae (6) or (7).  ... 
doi:10.2312/sgp/sgp06/223-226 fatcat:wtc4lbvxwrekpb3vxetwzormeu

Principal Curvature-Based Region Detector for Object Recognition

Hongli Deng, Wei Zhang, Eric Mortensen, Thomas Dietterich, Linda Shapiro
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
The PCBR interest operator detects stable watershed regions within the multi-scale principal curvature image.  ...  Robustness across scales is achieved by selecting the maximal stable regions across consecutive scales.  ...  To achieve robust detections across multiple scales, the watershed is applied to the maxima of three consecutive images in the principal curvature scale space-similar to local scale-space extrema used  ... 
doi:10.1109/cvpr.2007.382972 dblp:conf/cvpr/DengZMDS07 fatcat:6pqmgyuqcfdmhe76inwda2y2ma

Robust principal curvatures using feature adapted integral invariants

Yu-Kun Lai, Shi-Min Hu, Tong Fang
2009 2009 SIAM/ACM Joint Conference on Geometric and Physical Modeling on - SPM '09  
A recent work by Yang et al. combines principal component analysis with integral invariants and computes robust principal curvatures on multiple scales.  ...  Principal curvatures and principal directions are fundamental local geometric properties. They are well defined on smooth surfaces.  ...  During this process, principal curvatures at each vertex on different scales need to be accessed frequently.  ... 
doi:10.1145/1629255.1629298 dblp:conf/sma/LaiHF09 fatcat:eui4vhijbva5hgu4s5gjyrhulq

Curvature-direction measures for 3D feature detection

JinJiang Li, Hui Fan
2013 Science China Information Sciences  
Therefore, feature extraction based on principal curvature direction is more robust and accurate.  ...  In this paper, we propose a new robust feature extraction algorithm for 3D models based on principal curvature direction.  ...  This paper introduces a robust principal curvature method based on integral invariants.  ... 
doi:10.1007/s11432-013-4991-6 fatcat:bqsvxhvexvbqvpyla4clja4ktu

Hand gesture recognition with depth data

Fabio Dominio, Mauro Donadeo, Giulio Marin, Pietro Zanuttigh, Guido Maria Cortelazzo
2013 Proceedings of the 4th ACM/IEEE international workshop on Analysis and retrieval of tracked events and motion in imagery stream - ARTEMIS '13  
of samples with a certain curvature at a certain scale level Distance features: one for each relevant finger in each gesture hypothesis  Curvature features: one for each curvature bin and scale level  ...  "Robust hand gesture recognition based on Finger-earth mover's distance with a commodity depth camera", ACM Multimedia 2011 Distance Features: Examples Curvature Features (1)  Computed on the edges  ... 
doi:10.1145/2510650.2510651 dblp:conf/mm/DominioDMZC13 fatcat:avvrcdfpdbgytfofct4h4ejxzu

Multi-Scale Salient Features for Analyzing 3D Shapes

Yong-Liang Yang, Chao-Hui Shen
2012 Journal of Computer Science and Technology  
In this paper, we present a new algorithm of extracting multi-scale salient features on meshes. This is based on robust estimation of curvature on multiple scales.  ...  up on large scale.  ...  Based on our multi-scale salient feature extraction, we can do the viewpoint selection on multiple scales.  ... 
doi:10.1007/s11390-012-1287-z fatcat:gwcipwcafbedtkgd7mlh35q2p4

Multiscale Characterizations of Surface Anisotropies

Tomasz Bartkowiak, Johan Berglund, Christopher A Brown
2020 Materials  
Principal directions are plotted for each calculated location on each surface, at each scale considered.  ...  Histograms in horizontal coordinates show altitude and azimuth angles of principal curvatures, elucidating dominant texture directions at each scale.  ...  and discovering a strong correlation with curvature, and of Torbjorn S.  ... 
doi:10.3390/ma13133028 pmid:32645867 pmcid:PMC7372363 fatcat:ayk2bkcbsfbovopkt2pa44lphq

DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares [article]

Yizhak Ben-Shabat, Stephen Gould
2020 arXiv   pre-print
We achieve state-of-the-art results on a benchmark normal and curvature estimation dataset, demonstrate robustness to noise, outliers and density variations, and show its application on noise removal.  ...  The method enables extracting normal vectors and other geometrical properties, such as principal curvatures, the latter were not presented as ground truth during training.  ...  -A scale-free method for robust surface fitting and normal estimation. -A method for principal curvature and geometric properties estimation without using ground truth labels.  ... 
arXiv:2003.10826v1 fatcat:zjjk7esufvg3njqtwtr2gacsie

Simplification of Multi-Scale Geometry using Adaptive Curvature Fields [article]

Patrick Seemann, Simon Fuhrmann, Stefan Guthe, Fabian Langguth, and Michael Goesele
2016 arXiv   pre-print
Our algorithm is based on finding robust mean curvatures using the ball neighborhood, where the radius of a ball corresponds to the scale of the features.  ...  We present a novel algorithm to compute multi-scale curvature fields on triangle meshes.  ...  [LHF09] also use integral invariants based on the ball neighborhood to compute multi-scale principal curvatures.  ... 
arXiv:1610.07368v2 fatcat:quvj6xeujnasbll3wokemtjweu

Multi-scale Feature Extraction for 3D Models Using Local Surface Curvature

Huy Tho Ho, Danny Gibbins
2008 2008 Digital Image Computing: Techniques and Applications  
A local description of the surface is generated by fitting a surface to the neighbourhood of a keypoint and estimating its curvedness at multiple scales.  ...  Experimental results on a different number of models are shown to demonstrate the effectiveness and robustness of our approach.  ...  Doug Gray for his helpful comments on this work. We also would like to thank Ajmal S.  ... 
doi:10.1109/dicta.2008.64 dblp:conf/dicta/HoG08 fatcat:tskiy2qjnbfyxir77jfmhniirq

Principal curvatures from the integral invariant viewpoint

Helmut Pottmann, Johannes Wallner, Yong-Liang Yang, Yu-Kun Lai, Shi-Min Hu
2007 Computer Aided Geometric Design  
Recently an integral invariant solution of this problem was presented, which is based on principal component analysis of local neighbourhoods defined by kernel balls of various sizes.  ...  The extraction of curvature information for surfaces is a basic problem of Geometry Processing.  ...  Principal curves on multiple scales Similar to curvature estimators, we can also get estimators for principal directions.  ... 
doi:10.1016/j.cagd.2007.07.004 fatcat:azvjgincrng2jnmgdejb2iyt5u

Ear Structure Feature Extraction Based on Multi-scale Hessian Matrix

Ma Chi, Ban Xiaojuan, Wang Guosheng, Tian Ying
2013 International Journal of Signal Processing, Image Processing and Pattern Recognition  
In this paper, a new ear anatomy feature edge extraction method based on Hessian matrix is proposed. Stable edge is obtained from principal curvature image across scale space.  ...  Secondly, the 2D gray image in the pyramid was regarded as a surface, maximum and minimum principal curvature and their direction were calculated by using Hessian matrix, and principal curvature image  ...  To this end, we calculate the principal curvature of image in scale space.  ... 
doi:10.14257/ijsip.2016.9.5.14 fatcat:3qxkr3s7dndpjpweeh4lgccekm

Robust estimation of adaptive tensors of curvature by tensor voting

Wai-Shun Tong, Chi-Keung Tang
2005 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we propose a three-pass tensor voting algorithm to robustly estimate curvature tensors, from which accurate principal curvatures and directions can be calculated.  ...  To adapt to different scales locally, we define the RadiusHit of a curvature tensor to quantify estimation accuracy and applicability.  ...  Preprocessing to obtain a mesh and noise robustness are therefore issues, especially in the presence of multiple feature scales.  ... 
doi:10.1109/tpami.2005.62 pmid:15747797 fatcat:l3ghtkqagzbejdfzse6jngg2si

A Hierarchical Object Recognition System Based on Multi-scale Principal Curvature Regions

Wei Zhang, Hongli Deng, T.G. Dietterich, E.N. Mortensen
2006 18th International Conference on Pattern Recognition (ICPR'06)  
Image segments are obtained by a watershed transform of the principal curvature of a contrast enhanced image.  ...  This paper proposes a new generic object recognition system based on multi-scale affineinvariant image regions.  ...  One is to further improve the robustness of the principal curvature region detector.  ... 
doi:10.1109/icpr.2006.1195 dblp:conf/icpr/ZhangDDM06 fatcat:dugiuqywhraarfbqed7cmaqovm

Multi-scale feature extraction for 3d surface registration using local shape variation

Huy Tho Ho, Danny Gibbins
2008 2008 23rd International Conference Image and Vision Computing New Zealand  
The shape index at a point is calculated at multiple scales by fitting a surface to the local neighbourhoods of different sizes.  ...  Experimental results of applying the proposed feature extraction method on a variety of 3D models are shown to evaluate the effectiveness and robustness of our approach.  ...  Figure 2 : 2 Principal curvatures at a point P on a surface. : set of vertices and F = {f i } ∈ N 3 : set of facets. R = {r k }: a set of scales.  ... 
doi:10.1109/ivcnz.2008.4762120 fatcat:wtrk5zqskbd5dfecksxd3amp3q
« Previous Showing results 1 — 15 out of 25,677 results