Improved Part-Based Segmentation of Voxel Shapes by Skeleton Cut Spaces

We present a new method for part-based segmentation of voxel shapes that uses medial surfaces to define a segmenting cut at each medial voxel. The cut has several desirable properties – smoothness, tightness, and orientation with respect to the shape’s local symmetry axis, making it a good segmentation tool. We next analyze the space of all cuts created for a given shape and detect cuts which are good segment borders. Our method is robust to noise, pose invariant, independent on the shape geometry and genus, and is simple to implement. We demonstrate our method on a wide selection of 3D shapes.KeywordsPart-based segmentationMedial surfacesSkeletonization

Rotational diffusion of deformable macromolecules with mean local cylindrical symmetry

The structural organization of the PsaC protein in Photosystem I from single crystal EPR and X-ray crystallographic studies

With the development of medium- and high-resolution satellites, successfully segmenting differently sized geo-objects remains a challenging issue in the framework of geographic object-based image analysis (GEOBIA). The hybrid image segmentation method is a good alternative to produce good segmentation that best matched the different sizes of geo-objects. However, the existing methods almost use a certain scale or other segmentation parameters (SPs) to control the sizes and shapes of segments. This will lead to two issues: (1) one single scale is impossible to segment every geo-object well due to the land cover complexity within remote-sensing imageries; (2) over- and under-segmented regions still occur in the segmentation results, whatever using any advanced segmentation methods. To solve the above problems, this paper developed a hybrid image segmentation method with local scale-guided hierarchical region merging and further over- and under-segmentation processing. First, the primitive segmentation was produced and then stratified into layers with different land covers. Then, the local scale was calculated for a more objective merging process in the separating layers. Third, the over- and under-segmentation at separating layers was recognized and re-processed for achieving a fine segmentation. To validate the proposed method, it was applied to three test images of gaofen-1 satellite with different land cover types, and ten competing methods were compared. The visual and quantitative results indicated the advantage of our method in segmenting out different sizes of geo-objects, which can effectively reduce the over- and under-segmentation error.

Given a measurable space (X, M) there is a (Galois) connection between sub-sigma-algebras of M and equivalence relations on X. On the other hand equivalence relations on X are closely related to congruences on stochastic relations. In recent work, Doberkat has examined lattice properties of posets of congruences on a stochastic relation and motivated a domain-theoretic investigation of these ordered sets. Here we show that the posets of sub-sigma-algebras of a measurable space do not enjoy desired domain-theoretic properties and that our counterexamples can be applied to the set of smooth equivalence relations on an analytic space, thus giving a rather unsatisfactory answer to Doberkat's question.

In the area of 3D shape analysis, research in mesh segmentation has always been an important topic, as it is a fundamental low-level task which can be utilized in many applications including computer-aided design, computer animation, biomedical applications and many other fields. We define the automatic robust mesh segmentation (ARMS) method in this paper, which 1) is invariant to isometric transformation, 2) is insensitive to noise and deformation, 3) performs closely to human perception, 4) is efficient in computation, and 5) is minimally dependent on prior knowledge. In this work, we develop a new framework, namely the Center-Shift, which discovers meaningful segments of a 3D object by exploring the intrinsic geometric structure encoded in the biharmonic kernel. Our Center-Shift framework has three main steps: First, we construct a feature space where every vertex on the mesh surface is associated with the corresponding biharmonic kernel density function value. Second, we apply the Center-Shift algorithm for initial segmentation. Third, the initial segmentation result is refined through an efficient iterative process which leads to visually salient segmentation of the shape. The performance of this segmentation method is demonstrated through extensive experiments on various sets of 3D shapes and different types of noise and deformation. The experimental results of 3D shape segmentation have shown better performance of Center-Shift, compared to state-of-the-art segmentation methods.

We propose a new method for fully-automatic landmark detection and shape segmentation in X-ray images. Our algorithm works by estimating the displacements from image patches to the (unknown) landmark positions and then integrating them via voting. The fundamental contribution is that, we jointly estimate the displacements from all patches to multiple landmarks together, by considering not only the training data but also geometric constraints on the test image. The various constraints constitute a convex objective function that can be solved efficiently. Validated on three challenging datasets, our method achieves high accuracy in landmark detection, and, combined with statistical shape model, gives a better performance in shape segmentation compared to the state-of-the-art methods.

Theory of Relaxation of Quadrupolar Nuclei in Deformable Molecules in Isotropic Solutions. Application to DNA

We propose a novel method for pose-consistent segmentation of non-rigid 3D shapes into visually meaningful parts. The key idea is to study the shape in the framework of quantum mechanics and to group points on the surface which have similar probability of presence for quantum mechanical particles. For each point on an object's surface these probabilities are encoded by a feature vector, the Wave Kernel Signature (WKS). Mathematically, the WKS is an expression in the eigenfunctions of the Laplace-Beltrami operator of the surface. It characterizes the relation of surface points to the remaining surface at various spatial scales. Gaussian mixture clustering in the feature space spanned by the WKS signature for shapes in several poses leads to a grouping of surface points into different and meaningful segments. This enables us to perform consistent and robust segmentation of new versions of the shape. Experimental results demonstrate that the detected subdivision agrees with the human notion of shape decomposition (separating hands, arms, legs and head from the torso for example). We show that the method is robust to data perturbed by various kinds of noise. Finally we illustrate the usefulness of a pose-consistent segmentation for the purpose of shape retrieval.

Spatial structures of complexes [DyAc]2+, [DyBz]2+, [DyAc2]+ and [DyBz2]+ in aqueous solutions (Ac− and Bz−, acetate and benzoate anions, respectively) are studied using the paramagnetic double refraction method. The polyhedra of [DyAc(H2O)6]2+ and [DyBz(H2O)6]2+ are dodecahedra with ligands coordinated at one of the edges. In the complexes [DyAc2(H2O)4]+ and [DyBz2(H2O)4]+ the ligands are coordinated at the edges of a square antiprism at an angle of 50 (55)° to the local symmetry axis of higher symmetry.

CHAPTER 8 - Decision Theoretic and Bayesian Approach in Testing and Estimation

Deep Learning Facilitates Automation of Wall Layer Quantification in Heart Transplant Coronary OCT

Mission segment division of the whole aeroengine loading spectrum based on flight actions

To decouple dimensional flow perturbation quantities, a probe optimization method is proposed for multi-wire constant temperature anemometry in transonic flow conditions. Historically, hotwire measurements of density, velocity, and total temperature fluctuations in transonic flows are challenging due to the complexity of calibration and difficulties in obtaining a probe with favorably conditioned sensitivity matrix. Based on universal empirical correlation for heated cylinders in compressible flow, the current method relies on evaluation of wire-voltage sensitivities to density, velocity, and total temperature perturbations. To maximize the signal-to-noise ratio (SNR) of the decoupling, a two-step optimization-sifting procedure is developed. The first-step optimization maximizes a value function geared towards lower sensitivity-matrix condition numbers, better robustness against wire temperature-setting errors, and large sensitivities. From the resulting Pareto front, the second step sifts further through the candidate probes by decoupling simulated noisy voltage and ranking the probes by their decoupling quality. The performance of the optimal wire temperatures and diameters combination is contrasted against probes stemming from a naive selection from the parameter space. According to the artificial data, only the optimal probes enable decoupling with reasonable SNR. Finally, the research effort proposes guidelines to define a probe with desirable properties, applicable across a wide range of transonic flow conditions.

We present O-CNN , an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis. Built upon the octree representation of 3D shapes, our method takes the average normal vectors of a 3D model sampled in the finest leaf octants as input and performs 3D CNN operations on the octants occupied by the 3D shape surface. We design a novel octree data structure to efficiently store the octant information and CNN features into the graphics memory and execute the entire O-CNN training and evaluation on the GPU. O-CNN supports various CNN structures and works for 3D shapes in different representations. By restraining the computations on the octants occupied by 3D surfaces, the memory and computational costs of the O-CNN grow quadratically as the depth of the octree increases, which makes the 3D CNN feasible for high-resolution 3D models. We compare the performance of the O-CNN with other existing 3D CNN solutions and demonstrate the efficiency and efficacy of O-CNN in three shape analysis tasks, including object classification, shape retrieval, and shape segmentation.