Simple Shape Descriptors Research Articles

The Shape of Relations to Come: Multidimensional Analyses of Complex Human Behavior

AbstractScience, understood to be the behavior of scientists, falls within the purview of behavior analysis. All scientists use scientific instruments to study a natural phenomenon, and for the behavior analyst, perhaps no tool is more important than the graph used to show changes in level, trend, and variability, and upon which behavior analysts make data-based decisions. Modern behaviorism as we know it dates back to the development of the cumulative recorder first developed in the 1930s. Though revolutionary to the science of behavior, two-dimensional graphs may be limited in application for analyzing complex human behavior. In the current article, we conceptualize verbal behavior as a multidimensional field of environmental relations, and introduce the use of multi-axial radar charts for its visual and quantitative analysis. From there, we survey the use of radar charts toward advancing a behavior-analytic understanding of human language and cognition. We demonstrate the use of radar charts for calculating simple shape descriptors as a quantitative measure of dynamic interactants, and show how they can be used to measure change over time.

A local-global shape characterization scheme using quadratic Bezier triangle aiding retrieval

Shape characterization plays a highly prominent role in retrieval and relies extremely upon descriptors inbuilt with lightweight operations and compaction qualities. However, realizing such a simple and robust shape descriptor capable of dealing with noise, variations in brightness, and deformations pose a significant challenge. In this regard, a simple and effective shape descriptor using the Quadratic Bezier Triangle (QBT) targeting shape matching and retrieval is presented in this work. The mechanism commences with triangular tessellation of each image followed by determining their side-wise intensity differences that are then mapped to QBT vertices to yield the order-wise control points. The maxima of the resulting points are transformed into the binary equivalent of the given shape that is compacted into octal values. Later, these localized values are globally transformed into shape histograms to yield the QBT-based Feature (QBTF) descriptor representing the given input. QBTFs performance is exhaustively analyzed in terms of Bulls Eye Retrieval (BER) score and classification accuracy using the public datasets namely Kimia-99, MPEG-7 CE-1 part B, PHOS, and Tari-1000. Relative BER investigations witnessed across diverse datasets reveal a consistent and improved score of 93% achieved by this scheme over its peers. Mathematical analysis of invariance, noise resilience, and the complexities involved in realizing QBTF, establish the robustness and suitability of this scheme for real-time shape description.

Effects of spatial energy distribution-induced porosity on mechanical properties of laser powder bed fusion 316L stainless steel

Laser powder bed fusion (LPBF) additive manufacturing (AM) offers a variety of advantages over traditional manufacturing, however its usefulness for manufacturing of high-performance components is currently hampered by internal defects (porosity) created during the LPBF process that have an unknown impact on global mechanical performance. By inducing porosity distributions through variations in print energy density and inspecting the resulting tensile samples using computed tomography, nearly 50,000 pores across 75 samples were identified. Porosity characteristics were quantitatively extracted from inspection data and compared with mechanical properties to understand the strength of relationships between porosity and global tensile performance. Useful porosity characteristics were identified for prediction of part performance. Results indicate that ductility and strain at ultimate tensile strength are the global tensile properties most significantly impacted by porosity and can be predicted with reasonable accuracy using simple porosity shape descriptors such as volume, diameter, and surface area. Moreover, it was found that the largest pores influenced behavior most significantly. Specifically, pores in excess of 125 µm in diameter were found to be a sufficient threshold for property estimation. These results establish an initial understanding of the complex defect-performance relationship in AM 316L stainless steel and can be leveraged to develop certification standards and improve confidence in part quality and reliability for the broader set of engineering alloys.

A Simple Shape Descriptor Merging Arithmetical Wrap Around Technique with Absolute Localized Pixel Differences

The quest for computationally simple, highly accurate and precise shape descriptors supporting retrieval continues to be an active research area in computer vision. In this paper, a simple feature descriptor is realized by blending Modulo Arithmetic (MA) with Local Absolute Pixel Differences (LAPD) labelled as MA-LAPD. MA initially refines edges of images through modulo normalization and later operated by LAPD to capture local texture patterns. Subsequently, LAPD encodes the local intensity transitions in eight directions with regard to center pixel. The two prominent directional indices are converted into unique decimal codes that represent each pixel position, thus, transforming each image into a collection of LAPD codes. The ensuing LAPD image is then fabricated into histograms for characterizing the distribution of local features, used for matching and retrieval. Quantitative and qualitative investigations on Kimia’s 99, MPEG-7 Part-B and Tari-1000 datasets reveal consistent Bull’s Eye Retrieval (BER) scores above 91%. Also, relative analysis exposes the superiority of MA-LAPD with its predecessors in majority of the datasets.

The Analysis of Shape Features for the Purpose of Exercise Types Classification Using Silhouette Sequences

This paper presents the idea of using simple shape features for action recognition based on binary silhouettes. Shape features are analysed as they change over time within an action sequence. It is shown that basic shape characteristics can discriminate between short, primitive actions performed by a single person. The proposed approach is tested on the Weizmann database using a various number of classes. Binary foreground masks (silhouettes) are replaced with convex hulls, which highlights some shape characteristics. Centroid locations are combined with some other simple shape descriptors. Each action sequence is represented using a vector with shape features and Discrete Fourier Transform. Classification is based on leave-one-sequence-out approach and employs Euclidean distance, correlation coefficient or C1 correlation. A list of processing steps for action recognition is explained and followed by some experiments that yielded accuracy exceeding 90%. The idea behind the presented approach is to develop a solution for action recognition that could be applied in a kind of human activity recognition system associated with the Ambient Assisted Living concept, helping adults increasing their activity levels by monitoring them during exercises.

The Crystal Field Plasmon Splitting

We present an electromagnetic analogue of crystal (or ligand) field theory that describes geometric eigenmodes and the resonant plasmon wavelength in plasmonic nanocrystals in terms of a simple shape descriptor. Our model, crystal field plasmon splitting, is based on secular equations for geometric eigenmodes, allowing for the separation of pure shape from materials effects. As an example, the model is implemented to the experimental gold nanoparticles that undergo cube-to-sphere transition, showing that geometric eigenvalues change correspondingly in analogy to the atomic energy levels in Tanabe–Sugano correlation diagrams.

VOLUME ESTIMATION FROM SINGLE IMAGES: AN APPLICATION TO PANCREATIC ISLETS

The present paper deals with the problem of volume estimation of individual objects from a single 2D view. Our main application is volume estimation of pancreatic (Langerhans) islets and the single 2D view constraint comes from the time and equipment limitations of the standard clinical procedure.Two main approaches are followed in this paper. First, two regression-based methods are proposed, using a set of simple shape descriptors of the segmented image of the islet. Second, two example-based methods are proposed, based on a database of islets with known volume. For training and evaluation, islet volumes were determined by OPT microscopy and a semi-automatical stereological volume estimation using the so-called Fakir probes.The performance of the single image volume estimation methods is studied on a set of 99 islets from human donors. Further experiments were also performed on a stone dataset and on synthetic 3D shapes, generated using a flexible stochastic particle model. The proposed methods are fast and the experimental results show that in most situations the proposed methods perform significantly better than the methods currently used in clinical practice, which are based on simple spherical or ellipsoidal models.

A Posture Recognition System for Rat Cyborg Automated Navigation

Rat cyborg is a rat which can receive cerebral commands and act as human wants. The navigation task is a widely used scenario in which the rat cyborg is required to walk along a specified path according to commands. Mostly the commands are given by human operators, but there's a need for automatic control which is quite challenging since several modules need to be elaborately combined together to work as a whole, among which the monitoring system and the commands model are two major components. Previously, few attempts were made for behavior monitoring of rat cyborg. Existing works often implement an over-simple rat information extractor which is capable of giving only a few parameters of the rat cyborg, which greatly limited the performance of their automatic control accuracy. In response to this requirement, we develop a monitoring system that is capable of giving detailed motion parameters and accurate body postures of the rat cyborg. We explore the possibility of recognizing rat postures using shape information, which is described by the powerful Zernike moments. We propose several simple shape descriptors which are fast to compute and achieve acceptable performance.

Zircon grain shape holds provenance information: A case study from southwestern Australia

Detrital zircon geochronology is a powerful tool to address a range of geological questions related to sedimentary provenance. Nonetheless, non‐unique answers may result when igneous rocks of the same age are sourced from disparate locations. In an effort to resolve some of this issue in zircon provenance investigations, we explore the potential of detrital zircon grains to be linked to their original magmatic source through their grain shape. In order to develop this grain shape measure as a provenance tool, we first examine the relationships between chemistry and a range of different grain shape descriptors. We find grain shape to show a linear relationship to U‐concentration on a lithologic unit level. We interpret this relationship to be a function of crystal chemical control in igneous samples. Principal component analysis demonstrates the potential of simple grain shape descriptors (major axis, minor axis, and effective diameter) to characterize grains from particular rock units. Applying these same shape measures to sedimentary basins in the Proterozoic Albany–Fraser Orogen in southwest Australia allows us to closely replicate the findings of previous traditional U–Pb geochronological investigations in terms of grain provenance. In addition, we apply this technique to Mesozoic sediment on the southern margin of Australia and show for the first time that its detritus is more likely derived from the underlying crystalline basement rather than surrounding orogens that share similar magmatic ages.

Particle shape characterisation and classification using automated microscopy and shape descriptors in batch manufacture of particulate solids

It is known that size alone, which is often defined as the volume-equivalent diameter, is not sufficient to characterize many particulate products. The shape of crystalline products can be as important as size in many applications. Traditionally, particulate shape is often defined by several simple descriptors such as the maximum length and the aspect ratio. Although these descriptors are intuitive, they result in a loss of information about the original shape. This paper presents a method to use principal component analysis to derive simple latent shape descriptors from microscope images of particulate products made in batch processes, and the use of these descriptors to identify batch-to-batch variations. Data from batch runs of both a laboratory crystalliser and an industrial crystallisation reactor are analysed using the described approach. Qualitative and quantitative comparisons with the use of traditional shape descriptors that have physical meanings and Fourier shape descriptors are also made.

Fish Shape Recognition using Multiple Shape Descriptors

This paper studies recognition of fish shapes using both Region based and Contour based shape based descriptors[9]. Moment Invariants are chosen as the Region based descriptor and the Simple (geometric) shape descriptors (SSD) are used as Contour based shape descriptors. The shapes are varied through scaling and rotation. Manhattan Distance is used as the classifier. The study of the recognition rate by using moment invariants and simple shape descriptors is done separately. Each moment invariant (M1 , M2 , M3 , M4 and M5) is studied separately and jointly. Then simple shape descriptors are combined with moment invariants to get hybrid feature vectors for improving recognition rate. General Terms Fish Shape recognition

A New Method for Shape and Texture Classification of Orthopedic Wear Nanoparticles

Detailed morphologic analysis of particles produced during wear of orthopedic implants is important in determining a correlation among material, wear, and biological effects. However, the use of simple shape descriptors is insufficient to categorize the data and to compare the nature of wear particles generated by different implants. An approach based on Discrete Fourier Transform (DFT) is presented for describing particle shape and surface texture. Four metal-on-metal bearing couples were tested in an orbital wear simulator under standard and adverse (steep-angled cups) wear simulator conditions. Digitized Scanning Electron Microscope (SEM) images of the wear particles were imported into MATLAB to carry out Fourier descriptor calculations via a specifically developed algorithm. The descriptors were then used for studying particle characteristics (shape and texture) as well as for cluster classification. Analysis of the particles demonstrated the validity of the proposed model by showing that steep-angle Co-Cr wear particles were more asymmetric, compressed, extended, triangular, square, and roughened at 3 Mc than after 0.25 Mc. In contrast, particles from standard angle samples were only more compressed and extended after 3 Mc compared to 0.25 Mc. Cluster analysis revealed that the 0.25 Mc steep-angle particle distribution was a subset of the 3 Mc distribution.

A Simple Method for Calculating Valve Curvature

Many closely related diatom species are differentiated by simple morphometric characters such as length, width, and striae density. In addition, simple shape descriptors, such as curvature of the valve, can also be distinguishing morphometric characters. The curvature calculation described here is an intermediate technique between simple, direct measurements (i.e., length, width) and more complex descriptors of shape. The goal of this work is to develop a simple technique to calculate diatom curvature. Curvature is calculated from the length of a chord and the length of its sagitta (the perpendicular segment between the chord to the midpoint of the arc). These parameters correspond to diatom valve length and valve deflection from the chord and are incorporated into the equation: κ; = 2h(l2 h2)-1(where κ; = curvature, l = half of the chord length, and h = sagitta length). This equation can be utilized to estimate the curvature of the valve margin, valve margin asymmetry, and other morphological structures including apices and central area shape, and complex valve shapes.

Automatic detection of blue-white veil and related structures in dermoscopy images

Dermoscopy is a non-invasive skin imaging technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. One of the most important features for the diagnosis of melanoma in dermoscopy images is the blue-white veil (irregular, structureless areas of confluent blue pigmentation with an overlying white “ground-glass” film). In this article, we present a machine learning approach to the detection of blue-white veil and related structures in dermoscopy images. The method involves contextual pixel classification using a decision tree classifier. The percentage of blue-white areas detected in a lesion combined with a simple shape descriptor yielded a sensitivity of 69.35% and a specificity of 89.97% on a set of 545 dermoscopy images. The sensitivity rises to 78.20% for detection of blue veil in those cases where it is a primary feature for melanoma recognition.

Fuzzy shape based motion evaluation of left ventricle using genetic algorithm

A shape based non-rigid cardiac motion study is presented using simple fuzzy shape descriptors. The objective of this work is to evaluate the detail point wise motion trajectories from sequential contours. The shape correspondence on endocardial contour has been performed in multiple stages with well-defined, level specific curvature information. We incorporate non-uniform expansion and contraction of shape matched templates to optimize the correspondence in each level. However, final flow field evaluation is a constrained optimization problem, which results into a smooth mapping of contours. Constrained non-linear optimization with genetic algorithm has shown considerable promise in solving this problem. The results are quite consistent when correlated with the movement of implanted markers in an experimental set-up. Even though tracking contours in the reverse direction is irrelevant from a practical standpoint a good correlation between motions in either direction is observed. The algorithm has been tested over sets of 2D images to quantify the motion of left ventricle (LV) using two different imaging modalities.

The use of momentum-space descriptors for predicting octanol–water partition coefficients

We extend previous work on quantitative structure–activity and structure–property relationships using molecular descriptors based on quantities determined from the momentum-space ( p-space) electron density. In particular, we introduce new molecular descriptors that are related to the p-space information entropy. We also examine the use of a simple molecular shape descriptor, X. For the LC 50 toxicity data of a series of saturated alcohols, the simple shape descriptor is found to be remarkably successful, and a correlation is observed between X and the entropy-like p-space descriptors. We develop a promising 13-descriptor regression model for the log P values of a set of 76 chemically diverse molecules. Similar approaches, combining simple classical parameters with p-space quantities, are likely to prove useful for more complex QSAR/QSPR problems.

Towards on-line quantification of flocs and filaments by image analysis

A fully automatic image analysis method for recognizing flocs and filaments in an activated sludge sample was developed. Five simple shape descriptors, namely the aspect ratio, the roundness, the form factor, the fractal dimension and the reduced radius of gyration, were assessed on their capability to identify flocs and filaments in a binary image.

Path-Integral Calculation of the Mean Number of Overcrossings in an Entangled Polymer Network

A quantitative characterization of entanglements between polymer chains is essential for understanding the behavior of polymer solutions. When dealing with unknotted open chains, that characterization must rely on geometrical (rather than topological) measures of entanglement complexity. In this work, we deal with a simple geometrical shape descriptor: the mean overcrossing number of a set of curves. This descriptor provides a physically intuitive characterization of self-entanglements in a chain or entanglements in a network. Many of the analytical properties of the mean overcrossing number are still not well understood. In part, this is due to the use of numerical algorithms for its computation. Path-integral formalisms offer an improvement over this situation, by providing analytical expressions for the geometrical descriptors or, at least, more efficient algorithms for their evaluation. In this work, we discuss an approach to represent overcrossing numbers by path integrals. The formalism is general ...

Invariant distributions for shapes in sequences of randomly-divided rectangles

Interest has been shown in Markovian sequences of geometric shapes. Mostly the equations for invariant probability measures over shape space are extremely complicated and multidimensional. This paper deals with rectangles which have a simple one-dimensional shape descriptor. We explore the invariant distributions of shape under a variety of randomised rules for splitting the rectangle into two sub-rectangles, with numerous methods for selecting the next shape in sequence. Many explicit results emerge. These help to fill a vacant niche in shape theory, whilst contributing at the same time, new distributions on [0,1] and interesting examples of Markov processes or, in the language of another discipline, of stochastic dynamical systems.

Invariant distributions for shapes in sequences of randomly-divided rectangles

Interest has been shown in Markovian sequences of geometric shapes. Mostly the equations for invariant probability measures over shape space are extremely complicated and multidimensional. This paper deals with rectangles which have a simple one-dimensional shape descriptor. We explore the invariant distributions of shape under a variety of randomised rules for splitting the rectangle into two sub-rectangles, with numerous methods for selecting the next shape in sequence. Many explicit results emerge. These help to fill a vacant niche in shape theory, whilst contributing at the same time, new distributions on [0,1] and interesting examples of Markov processes or, in the language of another discipline, of stochastic dynamical systems.