Filters








65,694 Hits in 2.9 sec

Local Signature Quantization by Sparse Coding [article]

Davide Boscaini, Umberto Castellani
2013 Eurographics Workshop on 3D Object Retrieval, EG 3DOR  
Preliminary experiments are performed on a standard dataset by showing a drastic improvement of the proposed method in comparison with well known local-to-global and global approaches.  ...  In this fashion the dictionary is used as global shape descriptor for shape retrieval purposes.  ...  The main steps are: • Local descriptor computation by diffusion geometry signatures [ASC11], • Dictionary learning by sparse coding [MBPS09, MBPS10] , • Shape matching by best generative signature estimation  ... 
doi:10.2312/3dor/3dor13/009-016 fatcat:rs4gxpks7fhfbk3gy6rfy4da3q

Learning-based deformation estimation for fast non-rigid registration

Min-Jeong Kim, Myoung-Hee Kim, Dinggang Shen
2008 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
Then, the constructed statistical model is used to generate a large number of sample deformation fields by resampling in the PCA space.  ...  First, a PCA-based statistical deformation model is constructed using the deformation fields obtained by conventional registration algorithms between a template image and training subject images.  ...  Sample shape deformations can be represented by coefficients in PCA space, and the warped template images can be compactly represented by signature maps as detailed in this section, thus we can use regression  ... 
doi:10.1109/cvprw.2008.4563006 pmid:20651935 pmcid:PMC2907542 dblp:conf/cvpr/KimKS08 fatcat:djcw5n5jc5f5tc6qyboumnpcyu

IDSS: deformation invariant signatures for molecular shape comparison

Yu-Shen Liu, Yi Fang, Karthik Ramani
2009 BMC Bioinformatics  
Many molecules of interest are flexible and undergo significant shape deformation as part of their function, but most existing methods of molecular shape comparison (MSC) treat them as rigid bodies, which  ...  may lead to incorrect measure of the shape similarity of flexible molecules.  ...  The database is provided by S Flores and M Gerstein. We also acknowledge support from the National Institute of Health (GM-075004).  ... 
doi:10.1186/1471-2105-10-157 pmid:19463181 pmcid:PMC2694795 fatcat:u4x45t3r75ha3gd3xsxpene3xe

Retrieval of Partially Visible Shapes through Structural Feature Indexing [chapter]

Hirobumi Nishida
2000 Lecture Notes in Computer Science  
Structural feature indexing is a potential approach to efficient shape retrieval from large image databases, but the indexing is sensitive to noise, scales of observation, and local shape deformations.  ...  Effectiveness is confirmed through experimental trials with a large database of boundary contours, and is validated by systematically designed experiments with a large number of synthetic data.  ...  In Section 4, the transformation rules of shape signatures are introduced to generate features that can be extracted from deformed patterns caused by noise and local shape deformations.  ... 
doi:10.1007/3-540-44522-6_22 fatcat:xatei7rkybenbhnmlfu6xdhov4

Wavelet-based feature extraction technique for fruit shape classification

Slamet Riyadi, Asnor Juraiza Ishak, Mohd Marzuki Mustafa, Aini Hussain
2008 2008 5th International Symposium on Mechatronics and Its Applications  
Abnormality in papaya fruit shape represents a defective fruit and is used as one of the main criteria to determine suitability of the fruit to be exported.  ...  This paper describes a waveletbased technique used to perform feature extraction to extract unique features which are then used in the classification task to discriminate deformed papaya fruits from well  ...  The column signature of well-formed shape has relatively smooth signature curve as compared to the deformed shape signature.  ... 
doi:10.1109/isma.2008.4648858 fatcat:d6uitw7hefhabft57kyqyjniju

Exploiting angular profiles signature for shape-based image classification and retrieval

Jamil Ahmad, Zahoor Jan, Khan Muhammad
2016 International Journal of Applied Pattern Recognition  
A new shape signature is introduced in this paper for representing shapes through angular profiles signature which are extracted from objects enclosed within minimum bounding circles.  ...  We have evaluated the discriminatory capabilities of this signature in shape recognition and retrieval on two shape datasets.  ...  shape signatures in response to shape deformation (see online version for colours) Shapes with increasing degree of deformation APS signature Shapes with increasing degree of deformation APS  ... 
doi:10.1504/ijapr.2016.10000657 fatcat:6cc2swtxenhzjnns6woxwjfqiy

Exploiting angular profiles signature for shape-based image classification and retrieval

Jamil Ahmad, Khan Muhammad, Zahoor Jan
2016 International Journal of Applied Pattern Recognition  
A new shape signature is introduced in this paper for representing shapes through angular profiles signature which are extracted from objects enclosed within minimum bounding circles.  ...  We have evaluated the discriminatory capabilities of this signature in shape recognition and retrieval on two shape datasets.  ...  shape signatures in response to shape deformation (see online version for colours) Shapes with increasing degree of deformation APS signature Shapes with increasing degree of deformation APS  ... 
doi:10.1504/ijapr.2016.079761 fatcat:sjjp2np4yvac3iuef3l3momd7a

A Non-rigid Feature Extraction Method for Shape Recognition

Jon Almaz´n, Alicia Fornes, Ernest Valveny
2011 2011 International Conference on Document Analysis and Recognition  
It has been applied to signature verification and shape recognition tasks demonstrating high accuracy and low computational cost.  ...  This paper presents a methodology for shape recognition that focuses on dealing with the difficult problem of large deformations.  ...  However, due to the rigidity of the model, large deformations cause large differences in the spatial information encoded by the BSM.  ... 
doi:10.1109/icdar.2011.200 dblp:conf/icdar/AlmazanFV11 fatcat:qemk76novjbuflgepftlbillnm

Signature inversion caused by shape change in 84Rb

Shuifa Shen, Jiahui Gu, Shuanghui Shi, Jingyi Liu, Jianzhong Zhou, Wenqing Shen
2003 Physics Letters B  
The interpretation within the projected shell model shows that the signature inversion displayed in the positive-parity yrast band in this nucleus is a signal of a substantial quadrupole shape change with  ...  increasing spin where the nucleus evolves from a prolate shape at low spin through a triaxial shape to an oblate shape at high spin.  ...  The vacuum is obtained by diagonalizing a deformed Nilsson Hamiltonian [13] followed by a BCS calculation.  ... 
doi:10.1016/s0370-2693(03)00002-9 fatcat:xt4boxlzwnghrmbvbl4xh3kzmi

Local Diffusion Map Signature for Symmetry-aware Non-rigid Shape Correspondence

Meng Wang, Yi Fang
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
The local diffusion map signature is able to capture the concise geometric essence that is deformation-insensitive and symmetry-aware.  ...  The developed shape signature, named local diffusion map signature (LDMS), is obtained by projecting heat diffusion distribution on 3D surface into 2D images along the surface normal direction with orientation  ...  In this paper, we proposed a shape signature, named local diffusion map signature (LDMS), that capture the deformation-insensitive and symmetry-aware geometric essence.  ... 
doi:10.1145/2964284.2967277 dblp:conf/mm/WangF16 fatcat:vs6zpzsxj5ar7iwlud5jsuzbvq

A fast modal space transform for robust nonrigid shape retrieval

Jianbo Ye, Yizhou Yu
2015 The Visual Computer  
In this paper, we take advantages of functional operators as characterizations of shape deformation, and further propose a framework to design novel shape signatures for encoding nonrigid geometries.  ...  signature.  ...  for constructing informative shape signatures.  ... 
doi:10.1007/s00371-015-1071-5 fatcat:mcw22plna5di5fdqghuyth2qe4

The wave kernel signature: A quantum mechanical approach to shape analysis

Mathieu Aubry, Ulrich Schlickewei, Daniel Cremers
2011 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)  
We introduce the Wave Kernel Signature (WKS) for characterizing points on non-rigid three-dimensional shapes.  ...  As an application of the WKS in shape analysis we show results on shape matching.  ...  Figure 4 shows respective signatures of a specific point on the shape before (blue) and after (red) deformation of the shape.  ... 
doi:10.1109/iccvw.2011.6130444 dblp:conf/iccvw/AubrySC11 fatcat:lamjjf7cgja3tieoqgtwrvap4m

Quadrupole pairing interaction and signature inversion

F.R Xu, W Satuła, R Wyss
2000 Nuclear Physics A  
Our calculations show that signature inversioncan appear already at axially symmetric shapes.  ...  pairing and deformation self consistent mean field calculations.  ...  Finally, the equilibrium deformations are calculated by minimizing the total Routhian with respect to the shape parameters (shape self-consistency).  ... 
doi:10.1016/s0375-9474(99)00817-9 fatcat:zd6nj2srxzhyxfirb6zbw2x3bi

A sparse coding approach for local-to-global 3D shape description

Davide Boscaini, Umberto Castellani
2014 The Visual Computer  
A drastic improvement of the proposed method is observed by showing that sparse coding approach is particularly suitable for local-to-global description and outperforms other approaches such as the bag  ...  In this fashion the dictionary is used as global shape descriptor for shape retrieval purposes.  ...  Fig. 4 4 Class-signature dissimilarity matrix for noise deformations.  ... 
doi:10.1007/s00371-014-0938-1 fatcat:5l2hn5ghgrewrdzumwo3bjy2im

Shape Analysis Using the Edge-Based Laplacian [chapter]

Furqan Aziz, Richard C. Wilson, Edwin R. Hancock
2012 Lecture Notes in Computer Science  
We commence by presenting a new mesh characterization based on the adjacency matrix of the mesh that captures both the geometric and topological properties of the shape.  ...  We use the edge-based eigenvalues to develop a novel method for defining pose-invariant signatures for non-rigid three-dimensional shapes based on the edge-based heat kernel.  ...  Edwin Hancock was supported by a Royal Society Wolfson Research Merit Award.  ... 
doi:10.1007/978-3-642-34166-3_42 fatcat:xzv7e634znav3blzpovxrktw6m
« Previous Showing results 1 — 15 out of 65,694 results