Article

3D local feature extraction method based on spherical harmonics transform

Authors:
Article

3D local feature extraction method based on spherical harmonics transform

If you want to read the PDF, try requesting it from the authors.

Abstract

This paper presents a novel spherical harmonics transform based 3D local feature extraction method and its application in 3D ear recognition. At first, the scale of the 3D model is normalized and the 3D points are resampled. Then the centers of local spheres are localized through grid dividing. Finally, the local spherical harmonics features are extracted and they are used for 3D ear recognition. Compared with global spherical harmonics feature, our proposed local spherical harmonics feature is more robust to pose variation and can describe the 3D model more efficiently. Extensive experimental results have testified the effectiveness of the proposed method.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
This correspondence studies a spatially localized spectral transform for signals on the unit sphere, which we call spatially localized spherical harmonics transform (SLSHT). For a systematic treatment, we explicitly express the transform in terms of rotated versions of an azimuthally symmetric window function and introduce the spatio-spectral SLSHT distribution with a succinct matrix representation. We present guidelines for the choice of the window function in the SLSHT, based on the inherent tradeoff between the spatial and spectral resolution of different window functions from the perspective of the uncertainty principle. We demonstrate the use of an eigenfunction window, obtained from the Slepian concentration problem on the sphere, as a good choice for window function. As an illustration, we apply the transform to the topographic map of Mars, which can reveal spatially localized spectral contributions that were not obtainable from traditional spherical harmonics analysis.
Conference Paper
Full-text available
In medical imaging research fields, three-dimensional (3D) shape modeling and analysis of anatomic structures with fewer parameters is one of important issues, which can be used for computer assisted diagnosis, surgery simulation, visualization and many medical applications. The 3-D object shape or surface can be expressed by spherical harmonics. In this paper, we present a spherical harmonics based 3-D shape modeling for spleen and evaluate its shape reconstruction accuracy. Spherical harmonics modeling (SPHARM) is a smooth, accurate fine-scale shape representation and given sufficiently small approximation error.
Conference Paper
Full-text available
As the amount of new information generated in the world rapidly increases, efficient search in collections of structured data, texts and multimedia objects. 3D objects are an important type of multimedia data with many applications. Recent developments in techniques for modeling, digitizing and visualizing 3D models have led to an increase in the number of available 3D models on the Internet and in domain-specific databases. For visualization, 3D model are represented as a surface, in particular as polygonal meshes. Many researchers have investigated the specific problems of content based 3D shape retrieval and in the related fields of computer vision, object recognition and geometric modeling.
Article
Recently the explosion of 3D models arouses the necessity to develop effective 3D model retrieval systems. From 1990s, a lot of researches have been carries on and various matching and retrieval algorithms have been proposed. In this paper, we summarize the up-to-date methods for content-based 3D retrieval and mining system. After introducing the system framework, we emphasize on the descriptors which are most vital to the performance before other interrelated technologies, including pose normalization, semantic function and relevance feedback, are discussed. Finally we give our conclusion and some challenges, together with the potential future directions.
Article
The mechanisms of the reaction of W and W+ with the N2O were investigated at the CCSD(T)/[SDD+6-311G(d)]//B3LYP/[SDD+6-31G(d)] level of theory. It was shown that the reaction of W(7S)+N2O(1Σ+) is a multi-state process, involves several lower-lying electronic states of numerous intermediates and transition states, and leads to oxidation, WO(3Σ)+N21Σg+ with a negligible barrier and/or nitration, WN(4Σ)+NO(2Π) with a barrier of 6.7kcal/mol relative to reactants. The reaction of W+ with N2O, resemble its neutral analog, proceeds via the insertion and direct abstraction pathway, leads to oxidation and nitration of the W-center.
Article
Methods for content-based similarity search are fundamental for managing large multimedia repositories, as they make it possible to conduct queries for similar content, and to organize the repositories into classes of similar objects. 3D objects are an important type of multimedia data with many promising application possibilities. Defining the aspects that constitute the similarity among 3D objects, and designing algorithms that implement such similarity definitions is a difficult problem. Over the last few years, a strong interest in 3D similarity search has arisen, and a growing number of competing algorithms for the retrieval of 3D objects have been proposed. The contributions of this paper are to survey a body of recently proposed methods for 3D similarity search, to organize them along a descriptor extraction process model, and to present an extensive experimental effectiveness and efficiency evaluation of these methods, using several 3D databases.
Article
We present a unified feature representation of 2.5D pointclouds and apply it to face recognition. The representation integrates local and global geometrical cues in a single compact representation which makes matching a probe to a large database computationally efficient. The global cues provide geometrical coherence for the local cues resulting in better descriptiveness of the unified representation. Multiple rank-0 tensors (scalar features) are computed at each point from its local neighborhood and from the global structure of the 2.5D pointcloud, forming multiple rank-0 tensor fields. The pointcloud is then represented by the multiple rank-0 tensor fields which are invariant to rigid transformations. Each local tensor field is integrated with every global field in a 2D histogram which is indexed by a local field in one dimension and a global field in the other dimension. Finally, PCA coefficients of the 2D histograms are concatenated into a single feature vector. The representation was tested on FRGC V2.0 data set and achieved 93.78% identification and 95.37% verification rate at 0.1% FAR. 2007 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
Article
In this paper, we propose two novel methods for face recognition under arbitrary unknown lighting by using spherical harmonics illumination representation, which require only one training image per subject and no 3D shape information. Our methods are based on the recent result which demonstrated that the set of images of a convex Lambertian object obtained under a wide variety of lighting conditions can be approximated accurately by a low-dimensional linear subspace. We provide two methods to estimate the spherical harmonic basis images spanning this space from just one image. Our first method builds the statistical model based on a collection of 2D basis images. We demonstrate that, by using the learned statistics, we can estimate the spherical harmonic basis images from just one image taken under arbitrary illumination conditions if there is no pose variation. Compared to the first method, the second method builds the statistical models directly in 3D spaces by combining the spherical harmonic illumination representation and a 3D morphable model of human faces to recover basis images from images across both poses and illuminations. After estimating the basis images, we use the same recognition scheme for both methods: we recognize the face for which there exists a weighted combination of basis images that is the closest to the test face image. We provide a series of experiments that achieve high recognition rates, under a wide range of illumination conditions, including multiple sources of illumination. Our methods achieve comparable levels of accuracy with methods that have much more onerous training data requirements. Comparison of the two methods is also provided.