Shape Database Research Articles

Study on the relationships between particle shapes and motion responses in the geotechnical coarse-grained system subjected to vibration loads

The vibration-induced deformation of coarse-grained soil originates from the internal particle motions, which are reflected in translational and rotational behaviors controlled by particle shapes. However, the mechanism by which particle shapes affect particle motions in granular systems remains unclear, and diverse shape parameters make it difficult to accurately express the motion behaviors through a single shape parameter. Leveraging the advantages of the discrete element method (DEM) and machine learning methods, therefore, the relationships between shape features and motion behaviors were explored in complex-shaped granular systems. Firstly, a shape database containing hundreds of gravel particles was constructed, from which 10 representative shape parameters were selected to characterize the Form, Sphericity, and Roundness features through hierarchical clustering and principal component analysis. Then, three DEM models, established based on the shape database, were simulated to obtain particles’ translational and rotational indicators. Following, a regression relationship between representative shape parameters and motion indicators was established through the XGBoost model, and the SHAP values were utilized to explore the main shape parameters influencing particle motions. The results indicate that particle motions in the upper layer are primarily influenced by the Form parameter, and the equiaxial shape can promote the vertical displacement. The particle motions in the middle layer are mainly controlled by the Sphericity and Roundness parameters, and the flatness or angular shape has a suppressing effect on the vertical displacement.

High-level aftereffects reveal the role of statistical features in visual shape encoding

Visual shape perception is central to many everyday tasks, from object recognition to grasping and handling tools.1,2,3,4,5,6,7,8,9,10 Yet how shape is encoded in the visual system remains poorly understood. Here, we probed shape representations using visual aftereffects-perceptual distortions that occur following extended exposure to a stimulus.11,12,13,14,15,16,17 Such effects are thought to be caused by adaptation in neural populations that encode both simple, low-level stimulus characteristics17,18,19,20 and more abstract, high-level object features.21,22,23 To tease these two contributions apart, we used machine-learning methods to synthesize novel shapes in a multidimensional shape space, derived from a large database of natural shapes.24 Stimuli were carefully selected such that low-level and high-level adaptation models made distinct predictions about the shapes that observers would perceive following adaptation. We found that adaptation along vector trajectories in the high-level shape space predicted shape aftereffects better than simple low-level processes. Our findings reveal the central role of high-level statistical features in the visual representation of shape. The findings also hint that human vision is attuned to the distribution of shapes experienced in the natural environment.

Research on fruit shape database mining to support fruit class classification using the shuffled frog leaping optimization (SFLO) technique

<abstract><p>Association rule mining (ARM) is a technique for discovering meaningful associations within databases, typically handling discrete and categorical data. Recent advancements in ARM have concentrated on refining calculations to reveal connections among various databases. The integration of shuffled frog leaping optimization (SFLO) processes has played a crucial role in this pursuit. This paper introduces an innovative SFLO-based method for performance analysis. To generate association rules, we utilize the apriori algorithm and incorporate frog encoding within the SFLO method. A key advantage of this approach is its one-time database filtering, significantly boosting efficiency in terms of CPU time and memory usage. Furthermore, we enhance the optimization process's efficacy and precision by employing multiple measures with the modified SFLO techniques for mining such information.The proposed approach, implemented using MongoDB, underscores that our performance analysis yields notably superior outcomes compared to alternative methods. This research holds implications for fruit shape database mining, providing robust support for fruit class classification.</p></abstract>

Agata characterisation and pulse shape analysis

The AGATA and GRETA spectrometers are large arrays of highly segmented HPGe detectors that use the technique of gamma ray tracking to reconstruct the scattering path of gamma rays interacting within the active material. A basic requirement is a precise reconstruction of the individual interaction locations within the detectors. This is possible through the use of pulse shape analysis which has to be conducted in real time due to the high data rates generated by the spectrometer. The methodologies that have been evaluated to perform this for AGATA are discussed along with the approaches used to calculate the pulse shape databases required by these algorithms. Finally, the performance and limitations of the existing approaches are reviewed.

Obtaining an Object’s 3D Model Using Dual-Arm Robotic Manipulation and Stationary Depth Sensing

When humans want to understand an object&#x2019;s 3D shape, they watch the object from different viewpoints. Changing the viewpoint is either performed actively, i.e., moving eye sights or the human head, or passively, i.e., holding and reposing the object. Inspired by the humans&#x2019; passive policy, we propose a method to plan the motion for a dual-arm robot to hold and repose an object, capture multiple views using a stationary depth sensor mounted on the robot head, and obtain the object&#x2019;s 3D shape from the multiple views. Primarily, we develop algorithms to determine the Next Best Configuration (NBC) for observation and Next Best Regrasp/Grasp (NBR/G) poses while considering elements like the confidence of captured partial point clouds, robotic manipulability, robotic motion distances, and sensing ranges. We study the necessity and influence of these elements on the time costs and surface coverage quality in the experimental section using several representative objects. The results show that the elements play essential roles in supporting specific actions or suppressing certain costs. They help to secure efficient robot motion and satisfactory 3D shape recovery quality. <i>Note to Practitioners</i>&#x2014;This paper is motivated by the difficulties in using commercial 3D scanners. A commercial 3D scanner set usually comprises a scanning sensor, a rotating table, and editing software. To scan the 3D shape of an object, a human needs to place the object on the rotating table with different poses, let the scanner obtain several partial point clouds, and use the editing software to merge them into a final model. The human must carefully design the different poses by considering both the object&#x2019;s self obstructions and stable placements, which is tiring and difficult to be applied to large-scale tasks like building 3D shape databases containing many objects. On the other hand, although several robotic solutions exist for automatic scanning, they either use an eye-in-hand scanner to scan a stationary object or an arm to hold and move an object for scanning. In the former case, the bottom or downward faces of the object cannot be covered. In the latter case, the surface blocked by the fingers of the holding hand will be lost. The method proposed by this paper plans dual-arm robot motion to grasp and move objects for scanning. It automatically determines pick-up, rotation, and handover to maximize scanning coverage. Compared with commercial scanners and existing robotic solutions, the method performs automatic scanning with high coverage and is more advantageous for scanning many objects without human intervention.

통계적 신체 외형 데이터베이스를 활용한 실루엣으로부터의 3차원 인체 외형 예측

In this paper, we present a method for estimating full 3D shapes from given 2D silhouette images of human bodies. Because the silhouette only consists of the partial information on the true shape, it is an ill-posed problem. To address the problem, we use the statistical human shape space obtained from the existing large 3D human shape database. The method consists of three steps. First, we extract the boundary pixels and their appropriate normal vectors from the input silhouette images. Then, we initialize the correspondences of each pixel to the vertex of the statistically-deformable 3D human model. Finally, we numerically optimize the parameters of the statistical model to fit best to the given silhouettes. The viability and the robustness of the method is demonstrated with various experiments.

Spatial characterization of the effect of age and sex on macular layer thicknesses and foveal pit morphology.

Characterizing the effect of age and sex on macular retinal layer thicknesses and foveal pit morphology is crucial to differentiating between natural and disease-related changes. We applied advanced image analysis techniques to optical coherence tomography (OCT) to: 1) enhance the spatial description of age and sex effects, and 2) create a detailed open database of normative retinal layer thickness maps and foveal pit shapes. The maculae of 444 healthy subjects (age range 21-88) were imaged with OCT. Using computational spatial data analysis, thickness maps were obtained for retinal layers and averaged into 400 (20 x 20) sectors. Additionally, the geometry of the foveal pit was radially analyzed by computing the central foveal thickness, rim height, rim radius, and mean slope. The effect of age and sex on these parameters was analyzed with multiple regression mixed-effects models. We observed that the overall age-related decrease of the total retinal thickness (TRT) (-1.1% per 10 years) was mainly driven by the ganglion cell-inner plexiform layer (GCIPL) (-2.4% per 10 years). Both TRT and GCIPL thinning patterns were homogeneous across the macula when using percentual measurements. Although the male retina was 4.1 μm thicker on average, the greatest differences were mainly present for the inner retinal layers in the inner macular ring (up to 4% higher TRT than in the central macula). There was an age-related decrease in the rim height (1.0% per 10 years) and males had a higher rim height, shorter rim radius, and steeper mean slope. Importantly, the radial analysis revealed that these changes are present and relatively uniform across angular directions. These findings demonstrate the capacity of advanced analysis of OCT images to enhance the description of the macula. This, together with the created dataset, could aid the development of more accurate diagnosis models for macular pathologies.

Mode shape database-based estimation for machine tool dynamics

The system dynamics of machine tools plays an important role in machine health monitoring and quality assessment of manufacturing products. For former identification methods, the system dynamics are achieved with premises that do not fit with the real cutting conditions, as experimental modal analysis is realized only in idle status, and operational modal analysis limits the excitation form for vibration. Meanwhile, the dynamics variation during the machining is viewed discretely with no proper handles for the changes caused by cutting position movements. In this study, a mode shape database-based TOMA (MSDB-TOMA) estimation method is proposed for the system dynamics of machine tools under variation caused by component movements. The establishment principle of a mode shape database for capturing dynamics variation influenced by movements of cutting positions is proposed, with good fitting performance proved in a finite element model (FEM) of a machine tool. After that, the performance of dynamics estimation with the proposed method is validated using matched mode shapes from the pre-built database. The estimation for system dynamics parameters, e.g., natural frequency, presents a maximum error of within 0.04%, which turns out to be precise when compared with the real value from modal analysis in simulation. The feasibility experiment on FEM for estimating dynamics variation with component movements indicates the possibility of in-process dynamics recognition for real machining using the proposed method.

Mode shape prediction based on convolutional neural network and autoencoder

Mode shape is a dynamic characteristic that plays an important role in civil engineering. In this paper, an approach to predict the mode shape of a bridge is proposed using a convolutional neural network (CNN) and an autoencoder. First, a large mode shape database of a bridge is established by the finite element method for training networks. Second, a mode shape tensor is formed based on the mode-shape results. Then, an autoencoder is trained to encode the tensor to a three-dimensional latent-space representation and restore it from the representations. The CNN can output the representation directly rather than the mode shape to reduce the training difficulty and improve the accuracy. The CNN takes 18 bridge design parameters and an original shape tensor, which is constructed based on 16 geometric parameters. An evaluation of the test set shows that the approach can predict the first three order mode shapes well, with the accuracy of 0.92, 0.83 and 0.79, while performs poorly in the fourth and fifth orders, with the accuracy of 0.68 and 0.63. In addition, the spatial distribution of the latent space representation is explored. The necessity of an autoencoder and the original shape tensor is demonstrated.

Multiple Damage Detection of an Offshore Helideck through the Two-Step Artificial Neural Network Based on the Limited Mode Shape Data.

A helideck is an essential structure in an offshore platform, and it is crucial to maintain its structural integrity and detect the occurrence of damage early. Because helidecks usually consist of complex lattice truss members, precise measurements are required for structural health monitoring based on accurate modal parameters. However, available sensors and data acquisition are limited. Therefore, we propose a two-step damage detection process using an artificial neural network. Based on the mode shape database collected from 137,400 damage scenarios by finite element analysis, the neural network in the first step was trained to estimate the mode shapes of the entire helideck model using the selected mode shape data obtained from the limited measuring points. Then, the neural network in the second step is consecutively trained to detect the location and amount of structural damage to individual parts. As a result, it is shown that the proposed procedure provides the damage detection capability with only a quarter of the entire mode shape data, while the estimation accuracy is sufficiently high compared to the single network directly trained using all mode shape data. It was also found that, compared to the network directly trained from the same data, the proposed technique tends to detect minor damages more accurately.

Stochastic PCA-Based Bone Models from Inverse Transform Sampling: Proof of Concept for Mandibles and Proximal Femurs

Principal components analysis is a powerful technique which can be used to reduce data dimensionality. With reference to three-dimensional bone shape models, it can be used to generate an unlimited number of models, defined by thousands of nodes, from a limited (less than twenty) number of scalars. The full procedure has been here described in detail and tested. Two databases were used as input data: the first database comprised 40 mandibles, while the second one comprised 98 proximal femurs. The “average shape” and principal components that were required to cover at least 90% of the whole variance were identified for both bones, as well as the statistical distributions of the respective principal components weights. Fifteen principal components sufficed to describe the mandibular shape, while nine components sufficed to describe the proximal femur morphology. A routine has been set up to generate any number of mandible or proximal femur geometries, according to the actual statistical shape distributions. The set-up procedure can be generalized to any bone shape given a sufficiently large database of the respective 3D shapes.

A 3D Printed Physical Human–Robot Interface Based on a Sizing System to Facilitate Customization: Wearable Robots for Paraplegia

Wearable robots that assist paraplegia patients should be manufactured according to the shape of the individual wearer. With the development of advanced three-dimensional (3D) printing technologies, such customizations are becoming available. However, conventional 3D printing customization requires extensive template remodeling, which is non-productive and inefficient. This study proposes a 3D-printed (3DP) physical human–robot interface (pHRI) based on a sizing system that facilitates customization to body shapes. The proposed system is a pre-developed pHRI in various sizes and shapes using a human body shape database. Conformity of shapes and dimensions were evaluated visually via shape deviation analysis for 10 persons having paraplegia. With the proposed 3DP-pHRI, the trunk comprised 18 sections and the shank comprised nine. A biased trend of coverage rates in the shank 3DP-pHRI size system was identified. The trunk and shank subsystems were found to be adequate in terms of shapes and dimensions, with values within the mean deviation range of ±10 mm. A novel 3DP-pHRI size system facilitating customization tool for fabricating wearable robots for paraplegia patients according to body shape was developed, and its effectiveness was assured. The new system can be used for various wearable robot pHRIs, and the database is expected to supply a comprehensive pHRI template library.

Triaxial Discrete Element Simulation of Soil–Rock Mixture with Different Rock Particle Shapes under Rigid and Flexible Loading Modes

Three-dimensional scanning technology was used to construct the database of natural block stone shapes with different particle sizes. On the basis of Particle Flow Code 3D, a discrete element random model of soil–rock mixtures with different stone contents and shapes was established. A flexible boundary loading method of multisection wall was adopted to simulate the flexible film constraint mode of indoor triaxial test. Large-scale triaxial numerical simulation tests were carried out on the soil–rock mixture with different stone contents, stone shapes, and loading modes to analyze the macromechanics, microscopic deformation, and failure laws under various working conditions. Results showed that under the flexible loading mode, the stress curve of the samples with low stone content (0%–20%) has no obvious peak value and the deformation is mainly shear shrinkage. The stress curve of the samples with high stone content (40%–60%) showed the obvious peak value, and the dilatancy was prominent. Under the action of vertical load, the specimen bulged and formed multiple fork shear bands. Compared with the flexible loading mode, the rigid loading mode showed that the strength of the specimen increased in the rigid loading mode, and the cohesion and internal friction angle improved overall, but the friction energy was basically the same. During shearing, no obvious bulging was noted at the edge of the sample, and the shear bands were K-shaped and diagonal. The shape of block stone had significant influence on the strength, friction energy, and shear band shape of the soil–rock mixture.

Non Rigid 3D Shape Partial Matching Based on Deep Feature Fusion

<p indent=0mm>To meet the requirements of massive and heterogeneous 3D shape partial matching and intelligent retrieval technology, a 3D shape local matching method based on the deep fusion feature of F-PointCNN is proposed. First, the feature bag (BoF) learning model is used to propose an geometric image representation, which can not only effectively distinguish heterogeneous non-rigid 3D models of the same kind, but also reveal the structural similarity of large-scale incomplete 3D models. Next, a cascaded convolutional neural network slearning framework (F-PointCNN) is constructed, where BoF-CNN learns the deep global feature from BoF geometric images and establishes the point feature representation that integrates the local feature and the global feature; Point-CNN refines the point feature and generates deep feature representation which effectively improves the discriminative ability and robustness. Finally, the local shape matching of non rigid 3D model is realized by cross matrix measurement. The open non-rigid 3D shape databases are used to carry out a series of experiments, the results show that the features extracted by proposed method have stronger discriminative ability in large-scale transformation shape classification and higher precision in partial shape matching.

Adapted Jacobi Orthogonal Invariant Moments for Image Representation and Recognition

Images recognition and classification require an extraction technique of feature vectors of these images. These vectors must be invariant to the three geometric transformations: rotation, translation and scaling. Several authors used the theory of orthogonal moments to extract the feature vectors of images. Jacobi moments are orthogonal moments, which have been widely applied in imaging and pattern recognition. However, the invariance to rotation of Cartesian Jacobi moments is very difficult to obtain. In this paper, we obtain at first a set of transformed orthogonal Jacobi polynomials, called “Adapted Jacobi polynomials”. Based on these polynomials, a set of orthogonal moments is presented, named adapted Jacobi moments (AJMs). These moments are orthogonal on the rectangle $$\left[ {0, N\left] { \times } \right[0, M} \right],$$ where $$N \times M$$ is the size of the described image. We also provide a new series of feature vectors of images based on adapted Jacobi orthogonal invariants moments, which are a linear combination of geometric moment invariants, where the latest ones are invariant under rotation, translation and scaling of the described image. Based on k-NN algorithm, we apply a new 2D image classification system. We introduce a set of experimental tests in pattern recognition. The obtained results express the efficiency of our method. The performance of these feature vectors is compared with someones extracted from Hu, Legendre and Tchebichef invariant moments using three different 2D image databases: MPEG7-CE shape database, Columbia Object Image Library (COIL-20) database and ORL database. The results of the comparative study show the performance and superiority of our orthogonal invariant moments.

Shape retrieval by using multi‐scale angle‐based representation and dynamic label propagation

To improve the robustness and discrimination power of the triangle-area representation, a novel shape matching method based on multi-scale angle representation is proposed in this study. By analysing the configurations of different sample points from each shape contour, shape descriptors are constructed by using space angles at different scale levels. With the proposed shape representation, the multi-scale information of shape contours is efficiently described, and the dynamic programming is further used to determine the correspondence between samples from different shapes and calculate the shape distance in the feature matching step. Moreover, to improve the shape retrieval results based on pairwise shape distances, the dynamic label propagation is introduced as the post-processing step. Unlike previous distance learning methods learning the database manifold implicitly, the authors method retrieves relative objects on the shortest paths from near to far explicitly, and the underlying structure can be effectively captured. The proposed method tested on different shape databases provides the performances superior to many other methods, and it can be applied to visual data processing and understanding of the internet of things.

New set of adapted Gegenbauer–Chebyshev invariant moments for image recognition and classification

Orthogonal moments and their invariants to geometric transformations for gray-scale images are widely used in many pattern recognition and image processing applications. In this paper, we propose a new set of orthogonal polynomials called adapted Gegenbauer–Chebyshev polynomials (AGC). This new set is used as a basic function to define the orthogonal adapted Gegenbauer–Chebyshev moments (AGCMs). The rotation, scaling, and translation invariant property of (AGCMs) is derived and analyzed. We provide a novel series of feature vectors of images based on the adapted Gegenbauer–Chebyshev orthogonal moments invariants (AGCMIs). We practice a novel image classification system using the proposed feature vectors and the fuzzy k-means classifier. A series of experiments is performed to validate this new set of orthogonal moments and compare its performance with the existing orthogonal moments as Legendre invariants moments, the Gegenbauer and Tchebichef invariant moments using three different image databases: the MPEG7-CE Shape database, the Columbia Object Image Library (COIL-20) database and the ORL-faces database. The obtained results ensure the superiority of the proposed AGCMs over all existing moments in representation and recognition of the images.

A New Measure to Characterize the Degree of Self-Similarity of a Shape and Its Applicability.

We propose a new measure (Γ) to quantify the degree of self-similarity of a shape using branch length similarity (BLS) entropy which is defined on a simple network consisting of a single node and its branches. To investigate the properties of this measure, we computed the Γ values for 70 object groups (20 shapes in each group) in the MPEG-7 shape database and performed grouping on the values. With relatively high Γ values, identical groups had visually similar shapes. On the other hand, the identical groups with low Γ values had visually different shapes. However, the aspect of topological similarity of the shapes also warrants consideration. The shapes of statistically different groups exhibited significant visual difference from each other. Also, in order to show that the Γ can have a wide variety of applicability when properly used with other variables, we showed that the finger gestures in the (Γ, Z) space are successfully classified. Here, the Z means a correlation coefficient value between entropy profiles for gesture shapes. As shown in the applications, Γ has a strong advantage over conventional geometric measures in that it captures the geometrical and topological properties of a shape together. If we could define the BLS entropy for color, Γ could be used to characterize images expressed in RGB. We briefly discussed the problems to be solved before the applicability of Γ can be expanded to various fields.

3D shape clustering with Nonnegative Least Squares coding and fusion on multilayer graphs

The well-known method of spectral clustering for 3D shape datasets is revisited. The graph construction by NNLS (Nonnegative Least Squares) coding technique is at the core of our method. Using graph-based encoding techniques and well-known shape descriptors, a framework is presented here which is applied to 3D shape clustering. Provided a shape database, a graph is first constructed. Weights in the graph are calculated so as to approximate each shape as a sparse linear combination of the remaining dataset objects. This framework is further enhanced by using the multilayer graphs process combining NNLS with L2graph. The L2graph is a sparse similarity graph, which conveys complementary information to NNLS coding. A criterion for the complementary action of the two graphs in terms of graph distance is also presented. Experimental results conducted on SHREC10, SHREC11 and SCHREC15 datasets validate the excellent performance of our clustering framework.

New families of stable simplicial filtration functors

When quantifying the topological properties of a metric dataset using persistent homology, the first step is to produce a simplicial filtration on the data. The Čech and Vietoris-Rips filtrations are two of the workhorses of persistent homology, but over time, various other filtrations which capture different properties of data or have different computational burdens have been introduced. Towards a program of characterizing all the possible simplicial filtrations on a metric dataset, we introduce and develop the framework of valuation-induced stable filtration functors. This framework is based on the concept of curvature sets due to Gromov, and encapsulates the Vietoris-Rips and various other filtrations while simultaneously providing a model for generating families of novel filtration functors that capture diverse features present in datasets. We further extend this foundation by incorporating the notion of basepoint-dependent filtration functors and proving the associated functoriality and stability properties. This rich theoretical framework provides a unifying language for various extant simplicial filtrations, and is also a mechanism for generating arbitrarily large families of novel filtration functors with control over basepoint dependence/independence as well as the locality of the filtration. We exemplify our constructions on both toy datasets and on 3D shapes from a publicly available shape database. Our paper is accompanied by a Matlab software package incorporating an interactive platform for visualizing and testing new filtrations on datasets.