Protrusion-oriented 3D mesh segmentation

In this paper, we present a segmentation algorithm which partitions a mesh based on the premise that a 3D object consists of a core body and its constituent protrusible parts. Our approach is based on prominent feature extraction and core approximation and segments the mesh into perceptually meaningful components. Based upon the aforementioned premise, we present a methodology to compute the prominent features of the mesh, to approximate the core of the mesh and finally to trace the partitioning boundaries which will be further refined using a minimum cut algorithm. Although the proposed methodology is aligned with a general framework introduced by Lin et al. (IEEE Trans. Multimedia 9(1):46–57, 2007), new approaches have been introduced for the implementation of distinct stages of the framework leading to improved efficiency and robustness. The evaluation of the proposed algorithm is addressed in a consistent framework wherein a comparison with the state of the art is performed.     

基于随机游走的医学超声图像分割

医学超声图像不可避免地存在斑点噪声、弱边界等问题,很难达到满意的分割效果。随机游走算法对噪声具有鲁棒性,对弱边界有良好的提取能力。将此算法应用于医学超声图像分割,通过融合区域信息与用户指定的种子点信息,借助于电路模拟以及组合Dirichlet问题,可以得到每个非种子点到标记了目标点或者背景点的概率,并对其赋予概率中最大的种子点所对应的标记,从而实现图像的分割。实验结果表明,该方法对医学超声图像的分割是有效的。此算法通过求解稀疏的、对称的、正定的线性方程的系统来获得Dirichlet问题的解,使计算速度大为提高。     

三维网格的Mean Shift并行分割算法

为克服Mean Shift算法复杂度高、速度慢的缺点,提出了一种改进的三维网格模型Mean Shift并行分割算法.该方法基于Mean Shift的基本思想和GPU的高性能并行计算能力,基于离散测地距离的局部极值提取三维网格模型的显著特征点,自显著特征点开始并发执行Mean Shift算法,实现了有意义的分割.与同类算法相比,该算法提高计算运行效率、改善了分割效果.     

Spectral 3D mesh segmentation with a novel single segmentation field

We present an automatic mesh segmentation framework that achieves 3D segmentation in two stages, hierarchical spectral analysis and isoline-based boundary detection. During the hierarchical spectral analysis stage, a novel segmentation field is defined to capture a concavity-aware decomposition of eigenvectors from a concavity-aware Laplacian. Specifically, a sufficient number of eigenvectors is first adaptively selected and simultaneously partitioned into sub-eigenvectors through spectral clustering. Next, on the sub-eigenvectors level, we evaluate the confidence of identifying a spectral-sensitive mesh boundary for each sub-eigenvector by two joint measures, namely, inner variations and part oscillations. The selection and combination of sub-eigenvectors are thereby formulated as an optimization problem to generate a single segmentation field. In the isoline-based boundary detection stage, the segmentation boundaries are recognized by a divide-merge algorithm and a cut score, which respectively filters and measures desirable isolines from the concise single segmentation field. Experimental results on the Princeton Segmentation Benchmark and a number of other complex meshes demonstrate the effectiveness of the proposed method, which is comparable to recent state-of-the-art algorithms.     

Cropping-resilient 3D mesh watermarking based on consistent segmentation and mesh steganalysis

Multimedia Tools and Applications - This paper presents a new approach to 3D mesh watermarking using consistent segmentation and mesh steganalysis. The method is blind, statistical, and highly...     

网格分割的3维网格模型非盲水印算法

目的 信息技术的发展使得面向3维模型版权保护的问题越来越突出,提出一种新的基于网格分割的3维网格模型非盲水印算法。方法 首先使用基于形状直径函数的网格分割算法对3维网格模型进行有意义的网格分割,然后计算每个分块的鲁棒重心并以此为中心将模型由直角坐标系转换到球面坐标系,最后通过调制每个顶点范数的分布来嵌入水印,在水印检测阶段使用非盲检测的方法提取水印。结果 针对目前基于网格分块的水印算法的网格分割不一致以及对分割边界依赖性过强等问题,引入基于形状直径函数的网格分割算法并在重对齐、重采样过程中加入待检测模型与原始模型分块匹配过程以保证网格分割的一致性,并且选取分块的顶点范数的分布作为水印嵌入基元,使得算法能够有效地减弱对分割边界的依赖性。结论 实验结果表明,该算法可以有效抵抗平移、旋转、缩放、噪声、细分、简化、剪切等常见的攻击以及多种攻击的联合攻击。     

基于区域离散曲率的三维网格分水岭分割

针对离散曲率估计对噪声敏感且特征值计算量大的特点提出了基于区域离散曲率的三维网格分水岭分割算法。寻找三维模型显著特征点;对三维模型进行预分割,确定分割带;在分割带区域上计算离散曲度极值点,利用测地距离和曲度极值点对三维模型进行分水岭分割。算法在分割前无需进行网格去噪,实验结果证明,对主体分支明显的模型具有较高的分割边缘准确度和较快的分割速度。     

An efficient and robust algorithm for 3D mesh segmentation

This paper presents an efficient and robust algorithm for 3D mesh segmentation. Segmentation is one of the main areas of 3D object modeling. Most segmentation methods decompose 3D objects into parts based on curvature analysis. Most of the existing curvature estimation algorithms are computationally costly. The proposed algorithm extracts features using Gaussian curvature and concaveness estimation to partition a 3D model into meaningful parts. More importantly, this algorithm can process highly detailed objects using an eXtended Multi-Ring (XMR) neighborhood based feature extraction. After feature extraction, we also developed a fast marching watershed-based segmentation algorithm followed by an efficient region merging scheme. Experimental results show that this segmentation algorithm is efficient and robust.     

A novel 3D mesh compression using mesh segmentation with multiple principal plane analysis

This paper proposes a novel scheme for 3D model compression based on mesh segmentation using multiple principal plane analysis. This algorithm first performs a mesh segmentation scheme, based on fusion of the well-known k-means clustering and the proposed principal plane analysis to separate the input 3D mesh into a set of disjointed polygonal regions. The boundary indexing scheme for the whole object is created by assembling local regions. Finally, the current work proposes a triangle traversal scheme to encode the connectivity and geometry information simultaneously for every patch under the guidance of the boundary indexing scheme. Simulation results demonstrate that the proposed algorithm obtains good performance in terms of compression rate and reconstruction quality.     

Variational mesh segmentation via quadric surface fitting

We present a new variational method for mesh segmentation by fitting quadric surfaces. Each component of the resulting segmentation is represented by a general quadric surface (including plane as a special case). A novel energy function is defined to evaluate the quality of the segmentation, which combines both $L^2$ and $L^{2,1}$ metrics from a triangle to a quadric surface. The Lloyd iteration is used to minimize the energy function, which repeatedly interleaves between mesh partition and quadric surface fitting. We also integrate feature-based and simplification-based techniques in the segmentation framework, which greatly improve the performance. The advantages of our algorithm are demonstrated by comparing with the state-of-the-art methods.     

Automatic mass segmentation on mammograms combining random walks and active contour

Accurate mass segmentation on mammograms is a critical step in computer-aided diagnosis (CAD) systems. It is also a challenging task since some of the mass lesions are embedded in normal tissues and possess poor contrast or ambiguous margins. Besides, the shapes and densities of masses in mammograms are various. In this paper, a hybrid method combining a random walks algorithm and Chan-Vese (CV) active contour is proposed for automatic mass segmentation on mammograms. The data set used in this study consists of 1095 mass regions of interest (ROIs). First, the original ROI is preprocessed to suppress noise and surrounding tissues. Based on the preprocessed ROI, a set of seed points is generated for initial random walks segmentation. Afterward, an initial contour of mass and two probability matrices are produced by the initial random walks segmentation. These two probability matrices are used to modify the energy function of the CV model for prevention of contour leaking. Lastly, the final segmentation result is derived by the modified CV model, during which the probability matrices are updated by inserting several rounds of random walks. The proposed method is tested and compared with other four methods. The segmentation results are evaluated based on four evaluation metrics. Experimental results indicate that the proposed method produces more accurate mass segmentation results than the other four methods.     

基于商空间粒度理论的三维网格分割方法

通过研究已有的网格分割和模型简化方法 ,分析三维模型的网格分割中的商空间粒度思想 ,并将商空间粒度计算引入到网格分割中 ,对网格分割过程进行描述 ,提出了基于粒度分层合成技术的网格分割方法。该算法通过分别提取模型中各三角形网格区域的几何特征构成不同的粒度区域 ,再根据粒度合成理论。将这些所形成的粒度组织起来 ,从而实现对三维网格的最终分割 ,为三角网格模型的简化提供了快速有效的方法。实验表明了该算法对于网格分割的有效性和正确性。     

Boundary-trimmed 3D triangular mesh segmentation based on iterative merging strategy

This paper presents a segmentation algorithm for 3D triangular mesh data. The proposed algorithm uses iterative merging of adjacent triangle pairs based on their orientations. The oversegmented regions are merged again in an iterative region merging process. Finally, the noisy boundaries of each region are refined. The boundaries of each region contain perceptually important geometric information of the entire mesh model. According to the purpose of the segmentation, the proposed mesh-segmentation algorithm supports various types of segmentation by controlling parameters.     

三维FMF的HFCM水声数据分割

针对三维水声数据背景复杂、受噪声干扰严重等特点,提出一种结合三维FMF的HFCM水声数据分割算法,以提高水声数据分割的精度和效率。该算法首先选取三维滤波窗口,利用最大熵阈值法计算出模糊阈值;再结合半高斯模糊隶属度函数对水声数据进行模糊中值滤波;最后采用HFCM算法对滤波后的数据进行分割。对两组不同的三维水声数据进行分割处理的结果表明该算法能够有效地降低噪声干扰,分割效果要优于未滤波的HFCM以及均衡FMF的HFCM分割算法,并且在分割效率上要明显优于传统的模糊C均值算法。     

Double watermarks of 3D mesh model based on feature segmentation and redundancy information

This paper presents a new robust, blind and good imperceptibility 3D mesh double watermarks algorithm. Two different kinds of watermarks are embedded into one 3D mesh model. One watermarking algorithm based on mesh feature segmentation and the DCT transformation, the other based on redundancy information of 3D model. The two watermarks do not disturb each other during embedding and extracting. Several mesh models are applied to test the robustness, imperceptibility and efficiency of the proposed algorithm. The experimental results show that the proposed watermark scheme can not only keep good imperceptibility but also resist various attacks, such as similarity transformations (translation, rotation, scaling and combinations of the three operations), file attack, signal processing attacks (noising, smoothing and vertex coordinate quantization) and connectivity attacks (cropping).     

A new semantic segmentation approach of 3D mesh using the stereoscopic image colors

Multimedia Tools and Applications - This paper introduces a new mesh segmentation approach into semantic parts, most closely resemble those made by humans, which is based on the pixel color of the...     

Automated hippocampal segmentation in 3D MRI using random undersampling with boosting algorithm

Pattern Analysis and Applications - The automated identification of brain structure in Magnetic Resonance Imaging is very important both in neuroscience research and as a possible clinical...     

3D anisotropic mesh adaptation by mesh modification

This paper describes an effective anisotropic mesh adaptation procedure for general 3D geometries using mesh modification operations. The procedure consists of four interacted high level components: refinement, coarsening, projecting boundary vertices and shape correction. All components are governed by an anisotropic mesh metric field that represents the desired element size and shape distribution. The paper presents the application for the procedure in anisotropic adaptive 3D simulations.     

Solution of the Skyrme HF + BCS equation on a 3D mesh

Over the years, the ev8 code has been a very useful tool for the study of nuclear mean-field theory. Its main characteristic is that it solves the Hartree-Fock plus BCS equations for Skyrme type functionals via a discretization of the individual wave-functions on a three-dimensional Cartesian mesh. This allows maximal flexibility in the determination of the nuclear shape by the variational process. For instance, the same mesh can be used to describe the oblate deformed, spherical, prolate deformed, superdeformed and fission configurations of a given nucleus. The quadrupole constraining operator yielding the deformation energy curve covering all these configurations is included in ev8. This version of the code is restricted to even-even nuclei.

Program summary

Title of program:ev8Catalogue identifier:ADWAProgram obtainable from: CPC Program Library, Queen's University of Belfast, N. IrelandProgram summary URL:http://cpc.cs.qub.ac.uk/summaries/ADWALicensing provisions: noneComputers on which the program has been tested: HP-RX4640, Compaq-Digital Alpha GS140, has run on several other platformsComputer for which the program is designed and others on which is has been tested:Unix, LinuxOperating systems or monitors under which the program has been tested:FORTRAN-90Programming language used:depends on problem; example given requires 60 MBMemory required to execute with typical data:yesNo. of lines in distributed program, including test data, etc.:11 524No. of bytes in distributed program, including test data, etc.:89 949Distribution format:tar.gzip fileNature of the physical problem:By means of the Hartree-Fock plus BCS method using Skyrme type functionals, ev8 allows a study of the evolution of the binding energy of even-even nuclei for various shapes determined by the most general quadrupole constraint.Solution method:The program expands the single-particle wave-functions on a 3D Cartesian mesh. The nonlinear mean-field equations are solved by the imaginary time step method. A quadratic constraint is used to obtain states corresponding to given values of the quadrupole tensor.Unusual features:The pairing correlations being included with the BCS method, a physically correct solution must not have any occupied single particle state in the continuum. This requires the Fermi energy of both nucleon species to be negative and their absolute value to be typically larger than twice the pairing gap.Running time:For the test case, which starts from Nilsson wave-functions, a deformed configuration of ⁸⁴Zr is obtained with an accuracy better than 0.1 keV in 157 s on a HP-RX4640. Starting from this solution, other deformed configurations are obtained in less than 1 min.