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.     

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...     

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.     

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.     

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.     

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...     

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.     

Parallel anisotropic 3D mesh adaptation by mesh modification

Improvements to a local modification-based anisotropic mesh adaptation procedure are presented. The first improvement focuses on control of the local operations that modify the mesh to satisfy the given anisotropic mesh metric field. The second is the parallelization of the mesh modification procedures to support effective parallel adaptive analysis. The resulting procedures are demonstrated on general curved 3D domains where the anisotropic mesh size field is defined by either an analytic expression or by an adaptive correction indicator as part of a flow solution process.

---

基于轮廓线的三维网格曲面绘制

在融合了交互式轮廓绘制与网格造型技术的基础上,提出了一种快速三维网格曲面建模方法.根据绘制轮廓线的特征点分布,进行约束化三角网格剖分,提取二维轮廓线的骨架;选取骨架点和采样点投影到三维空间椭球曲面,并引入二面角原则,优化了空间离散数据点的三角化算法;最后缝合骨架点,获得三维网格曲面表示.实验结果表明了该算法的直观性、高效性.     

Consistent segmentation of 3D models

This paper proposes a method to segment a set of models consistently. The method simultaneously segments models and creates correspondences between segments. First, a graph is constructed whose nodes represent the faces of every mesh, and whose edges connect adjacent faces within a mesh and corresponding faces in different meshes. Second, a consistent segmentation is created by clustering this graph, allowing for outlier segments that are not present in every mesh. The method is demonstrated for several classes of objects and used for two applications: symmetric segmentation and segmentation transfer.     

3D object segmentation using B-Surface

3D object segmentation is important in computer vision such as target detection in biomedical image analysis. A new method, called B-Surface algorithm, is generated for 3D object segmentation. An improved 3D external force field combined with the normalized GVF is utilized. After the initialization of a surface model near the target, B-Surface starts to deform to locate the boundary of the object. First, it overcomes the difficulty that comes from analyzing 3D volume image slice by slice. And the speed of B-Surface deformation is enhanced since the internal forces are not needed to compute in every iteration deformation step. Next, the normal at every surface point can be calculated easily since B-Surface is a continuous deformable model. And it has the ability to achieve high compression ratio (ratio of data to parameters) by presenting the whole surface with only a relatively small number of control points. Experimental results and analysis are presented in this paper. We can see that the B-Surface algorithm can find the surface of the target efficiently.     

3D segmentation of abdominal CT imagery with graphical models,conditional random fields and learning

Probabilistic graphical models have had a tremendous impact in machine learning and approaches based on energy function minimization via techniques such as graph cuts are now widely used in image segmentation. However, the free parameters in energy function-based segmentation techniques are often set by hand or using heuristic techniques. In this paper, we explore parameter learning in detail. We show how probabilistic graphical models can be used for segmentation problems to illustrate Markov random fields (MRFs), their discriminative counterparts conditional random fields (CRFs) as well as kernel CRFs. We discuss the relationships between energy function formulations, MRFs, CRFs, hybrids based on graphical models and their relationships to key techniques for inference and learning. We then explore a series of novel 3D graphical models and present a series of detailed experiments comparing and contrasting different approaches for the complete volumetric segmentation of multiple organs within computed tomography imagery of the abdominal region. Further, we show how these modeling techniques can be combined with state of the art image features based on histograms of oriented gradients to increase segmentation performance. We explore a wide variety of modeling choices, discuss the importance and relationships between inference and learning techniques and present experiments using different levels of user interaction. We go on to explore a novel approach to the challenging and important problem of adrenal gland segmentation. We present a 3D CRF formulation and compare with a novel 3D sparse kernel CRF approach we call a relevance vector random field. The method yields state of the art performance and avoids the need to discretize or cluster input features. We believe our work is the first to provide quantitative comparisons between traditional MRFs with edge-modulated interaction potentials and CRFs for multi-organ abdominal segmentation and the first to explore the 3D adrenal gland segmentation problem. Finally, along with this paper we provide the labeled data used for our experiments to the community.     

Watermarking 3D mesh by spherical parameterization

In this paper, a robust 3D trianglular mesh watermarking algorithm is presented by applying spherical parameterization. First, we transform the coordinate signals of the 3D triangular mesh into spherical signals using a global spherical parameterization and an even sampling scheme. Then, spherical harmonic transformation is used to generate some data for embedding watermarks. As a result, the watermarks can be embedded in the Fourier-frequency domain of the original mesh. Experimental results show that our watermarking algorithm is robust since watermarks can be extracted without mesh alignment or re-meshing under a variety of attacks, including noise addition, crop, filtering, enhancement, rotation, translation, scale and re-sampling.