Shape Classification Research Articles

Mangrove and microplastic pollution: A case study from a small island (Mauritius)

Marine sediments have been demonstrated to be a long-term sinks for microplastics and their contamination in mangrove sediment are of no exception with relatively scarce information available globally. This work aimed to determine the prevalence of microplastics in two natural mangrove forests of a small island developing state, Mauritius, with emphasis on the proximity of human settlement and anthropogenic activities. Sediments were collected in triplicates monthly from October to December 2018 at Ferney (remote site) and Mahebourg (populated site) in three tidal zones: seaward (Z1), middle (Z2) and landward zone (Z3). Microplastics retrieved were classified in terms of shape and size classes. Results showed the presence of microplastics in all sediment samples with average abundance of 107.4 ± 76.42 particles kg −1 at Ferney and 140.2 ± 85.38 particles kg −1 at Mahebourg. Average microplastics abundance was highest in the ZI and Z3 tidal zones and least in Z2 at Ferney and Mahebourg respectively. Majority of microplastics recovered were in the size class 800–1000 μm and 1000–2000 μm, and in the fragment and film shape that may be derived from the fragmentation of larger plastic debris. This study is an important baseline for mangrove protection as it provides a better understanding of microplastics pollution status and information for future planning of management strategies on a local and regional scale.

Semiparametric Multinomial Logistic Regression Model to Classify‎ ‎Shape Data

This article introduces a semiparametric multinomial logistic regression model to classify labeled configurations. In the regression model, the explanatory variable is the kernel function obtained using the power-divergence criterion. Also, the response variable was categorical and showed the class of each configuration. This semiparametric regression model is introduced based on distances defined in the shape space, and for this reason, the correct classification of shapes using this method has been improved compared to previous methods. ‎The performance of this model has been investigated in the comprehensive simulation study‎. ‎Two real datasets were analyzed using this article's method as an application‎. ‎Finally‎, ‎the method presented in this article was compared with the techniques introduced in the literature‎, ‎which shows the proper performance of this method in classifying configurations‎.

Investigating the impact of body shape on garment fit

PurposeBody shape is a critical variable influencing consumers' garment choices (Zakaria, 2017), yet research investigating how UK females with varying body shapes evaluate and experience fit is limited. Moreover, while digital methods exist to classify female body shapes, application in a commercial setting is limited. To fill this gap within the literature, this study aims to understand the influence of body shape variation on garment fit evaluations of 30 UK females aged 18–34 years.Design/methodology/approachThis study conducts a physical garment try-on session whereby 30 UK females aged 18–34 years were body-scanned and categorised into a body shape, using the Female Figure Identification Technique method. Participants verbalised their fit experiences during a physical try-on session through semi-structured interviews to gain a deeper understanding of individuals' fit appraisals.FindingsThe findings demonstrate that UK females who share the same body shape classification experience the same issues when appraising dress fit, challenging Makhanya and Mabuza (2020) who found that body shape does not influence apparel fit satisfaction. The results shed light on the importance of body shape during the fit appraisal process.Research limitations/implicationsDespite the contribution, future research to improve the limitations should be addressed. First, although it was necessary to investigate a UK demographic to address research gaps, the finding of this study cannot be generalised to the entire UK female population nor to other areas of the world. Hence, future research should overcome this limitation by extending this study further to other countries, cultures and ethnicities.Practical implicationsThe findings of the present study shed light on the role of body shape in determining satisfactory clothing fit and how females' fit experiences will differ depending on their body shape classification. Thus, fashion retailers should use this insight to better inform their promotional strategies, not only making them more inclusive but also to help assist this particular consumer segment with their clothing decisions based on their body shape.Originality/valueThe present study provides an in-depth understanding of how females with the same body shape experience garment fit, contributing novel findings to the literature through a mixed-method inquiry previously lacking in this area, with a UK demographic which has not previously been explored.

Experimental observations of naturally occurring dust using a high-speed vacuum ultraviolet imaging system in EAST

In the ELMy H-mode experiment, naturally occurring dust originating at the high-field side is clearly observed using the high-speed vacuum ultraviolet imaging system developed on the Experimental Advanced Superconducting Tokamak (EAST). The main ablation cloud shape is similar to the classical shape observed in pellet fueling experiments. However, during the dust penetration, an erupted secondary cloudlet with a bent ‘cigar’ shape is observed and moves upwards along the direction perpendicular to the magnetic field line, which is different to the obviation in the pellet fueling experiments. This may be due to the ion diamagnetic drift effect. The velocities of the secondary cloudlet are estimated to be 50‒80 m s−1. In addition, a significant degradation of the plasma confinement is observed during the dust penetration.

Improving Automatic Melanoma Diagnosis Using Deep Learning-Based Segmentation of Irregular Networks.

Deep learning has achieved significant success in malignant melanoma diagnosis. These diagnostic models are undergoing a transition into clinical use. However, with melanoma diagnostic accuracy in the range of ninety percent, a significant minority of melanomas are missed by deep learning. Many of the melanomas missed have irregular pigment networks visible using dermoscopy. This research presents an annotated irregular network database and develops a classification pipeline that fuses deep learning image-level results with conventional hand-crafted features from irregular pigment networks. We identified and annotated 487 unique dermoscopic melanoma lesions from images in the ISIC 2019 dermoscopic dataset to create a ground-truth irregular pigment network dataset. We trained multiple transfer learned segmentation models to detect irregular networks in this training set. A separate, mutually exclusive subset of the International Skin Imaging Collaboration (ISIC) 2019 dataset with 500 melanomas and 500 benign lesions was used for training and testing deep learning models for the binary classification of melanoma versus benign. The best segmentation model, U-Net++, generated irregular network masks on the 1000-image dataset. Other classical color, texture, and shape features were calculated for the irregular network areas. We achieved an increase in the recall of melanoma versus benign of 11% and in accuracy of 2% over DL-only models using conventional classifiers in a sequential pipeline based on the cascade generalization framework, with the highest increase in recall accompanying the use of the random forest algorithm. The proposed approach facilitates leveraging the strengths of both deep learning and conventional image processing techniques to improve the accuracy of melanoma diagnosis. Further research combining deep learning with conventional image processing on automatically detected dermoscopic features is warranted.

Shape classification technology of pollinated tomato flowers for robotic implementation

Three pollination methods are commonly used in the greenhouse cultivation of tomato. These are pollination using insects, artificial pollination (by manually vibrating flowers), and plant growth regulators. Insect pollination is the preferred natural technique. We propose a new pollination method, using flower classification technology with Artificial Intelligence (AI) administered by drones or robots. To pollinate tomato flowers, drones or robots must recognize and classify flowers that are ready to be pollinated. Therefore, we created an AI image classification system using a machine learning convolutional neural network (CNN). A challenge is to successfully classify flowers while the drone or robot is constantly moving. For example, when the plant is shaking due to wind or vibration caused by the drones or robots. The AI classifier was based on an image analysis algorithm for pollination flower shape. The experiment was performed in a tomato greenhouse and aimed for an accuracy rate of at least 70% for sufficient pollination. The most suitable flower shape was confirmed by the fruiting rate. Tomato fruit with the best shape were formed by this method. Although we targeted tomatoes, the AI image classification technology is adaptable for cultivating other species for a smart agricultural future.

Application of neural network-based image analysis to detect sister chromatid cohesion defects

Sister chromatid cohesion (SCC) is mediated by the cohesin complex and its regulatory proteins. To evaluate the involvement of a protein in cohesin regulation, preparations of metaphase chromosome spreads and classifications of chromosome shapes after depletion of the target protein are commonly employed. Although this is a convenient and approved method, the evaluation and classification of each chromosome shape has to be performed manually by researchers. Therefore, this method is time consuming, and the results might be affected by the subjectivity of researchers. In this study, we developed neural network-based image recognition models to judge the positional relationship of sister chromatids, and thereby detect SCC defects. Transfer learning models based on SqueeezeNet or ResNet-18 were trained with more than 600 chromosome images labeled with the type of chromosome, which were classified according to the positional relationship between sister chromatids. The SqueezeNet-based trained model achieved a concordance rate of 73.1% with the sample answers given by a researcher. Importantly, the model successfully detected the SCC defect in the CTF18 deficient cell line, which was used as an SCC-defective model. These results indicate that neural-network-based image recognition models are valuable tools for examining SCC defects in different genetic backgrounds.

Comparison of Six Different Methods for Measuring the Equine Hoof and Recording of its Three-Dimensional Conformation.

Different measuring techniques have been used to objectify the classification of hoof shape. The MicroScribe is a novel tool that might prove useful for measuring hooves without prior reconstruction or compensation of projection artefacts. The aim of this study was to compare biometric data of the equine hoof collected by the MicroScribe tool and measurements collected directly from hooves, scaled photographs and radiographs, from photogrammetry models and computed tomography datasets. The suitability of MicroScribe generated data to differentiate individual hoof conformations was tested. A total of 62 measures were recorded from 16 forehooves. 21 linear and nine angular measures were collected by at least four methods each, and evaluated further by analysis of variance (ANOVA) and multivariate analysis of variance (MANOVA). Ratios and differences of these measures were calculated as suitable for the definition of hoof shapes and analysed as well. Absolute equivalency of methods was detected for five linear and none of the angular measurements. The precision of the tested measurement methods was comparable. In some cases, different methods measure different structures. Radiographs tended to overestimate, while computed tomography slides to underestimate distances. Photogrammetry and scaled photographs were less suitable for measuring hoof angles. The MicroScribe tool can readily be used for hoof measurements. Its values for linear measures showed good equivalency with other methods based on real hooves. For angular measurements, the uneven hoof surface might introduce imprecision. Not all hoof conformations could be detected based on measuring results alone. Diagnosis by a skilled veterinarian is still essential.

Towards an unbiased shape classification of super-resolution microscopy localizations.

Single molecule localization microscopy (SMLM) captures biological structures at nanoscale spatial resolution and has become an important tool for discovery in cell biology in recent years. However, tools that enable robust quantification of complex biological structures have lagged behind. In this study, we developed a new method to quantitatively describe and classify a wide range of diverse biological structures in SMLM data and have applied it to describe the degradation process of neuronal Tau protein aggregates, an important precursor in neurodegenerative diseases.

Tekirdağ İli Tarım Parsellerinin Arazi Toplulaştırma Açısından Şekil Analizi ile Değerlendirilmesi

Shape irregularity is one of the most important factors that reduce agricultural efficiency and the sustainability of rural development. In the study, the shape of 346.740 agricultural parcels in Tekirdağ province was measured by the Parcel Shape Index (PSI) method, which integrates six different criteria (length of sides, acute angles, reflex angles, boundary points, compactness and regularity). The PSI method analyzes geometry more comprehensively than other classical shape methods. Determining the shape suitability of the parcels with this method and then the corrections to be made in the deformed parcels ensure that the negative effects of agricultural mechanization are minimized. In the research, shape suitability degrees were categorized into four groups; namely, highly irregular shapes, irregular shapes, regular shapes and near optimum shapes. It was determined that 17.27% of the parcels in the province have a highly irregular shape, 35.21% have an irregular shape, 35.54% have a regular shape and 11.98% have near optimum shape geometry. Land consolidation studies should be carried out urgently due to the shape irregularity affecting production throughout the province. PSI method can provide great benefits in the site selection before the land consolidation projects planned in Türkiye, at the scale of basin, village or rural county.

Multi-Index Grading Method for Pear Appearance Quality Based on Machine Vision

The appearance quality of fruits affects consumers’ judgment of their value, and grading the quality of fruits is an effective means to improve their added value. The purpose of this study is to transform the grading of pear appearance quality into the classification of the categories under several quality indexes based on industry standards and design effective distinguishing features for training the classifier. The grading of pear appearance quality is transformed into the classification of pear shapes, surface colors and defects. The symmetry feature and quasi-rectangle feature were designed and the back propagation (BP) neural network was trained to distinguish standard shape, apical shape and eccentric shape. The mean and variance features of R and G channels were used to train support vector machine (SVM) to distinguish standard color and deviant color. The surface defect area was used to participate in pear appearance quality classification and the gray level co-occurrence matrix (GLCM) features of defect area were extracted to train BP neural network to distinguish four common defect categories: tabbed defects, bruised defects, abraded defects and rusty defects. The accuracy rates of the above three classifiers reached 83.3%, 91.0% and 76.6% respectively, and the accuracy rate of pear appearance quality grading based on grading rules was 80.5%. In addition, the hardware system prototype for experimental purpose was designed, which have certain reference significance for the further construction of the pear appearance quality grading pipeline.

Transformer High-Voltage Primary Coil Quality Detection Method Based on Machine Vision

Aiming at the problems of low efficiency and low accuracy in manual detection of winding angle and wire spacing during automatic winding of high-voltage primary coils of transmission and distribution transformers, a detection scheme using machine vision is proposed. Firstly, the coil image is acquired by the industrial camera, the detection region is segmented, and the ROI (region of interest) image is pre-processed. For winding angle detection, we propose a slicing method for image graying to reduce the interference caused by uneven light irradiation. The gray image is converted to a binary image, and wire skeleton extraction is performed; the skeleton is identified using the Hough transform for feature straight lines, and the winding angle is then calculated. For wire spacing detection, we propose an intersection of the perpendicular lines method, which extracts edge coordinates using contour images and performs endpoint pixel expansion and shape classification. Use the intersection of the vertical lines to determine the centroid coordinates of the wire outline, calculate the pixel distance of the adjacent centroid, and obtain the wire spacing by combining pixel calibration. Comparison experiments have shown that the solution has a high detection accuracy (0.01 mm), and the error of the integrated detection results is not higher than 10%, which enables the real-time detection of coil winding status and corrects the winding process according to the visual real-time detection result to improve the finished product quality of coils.

Stereodivergent Desymmetrization of Phenols En Route to Modular Access to Densely Functionalized Quinazoline and Oxazine Scaffolds

The de novo assembly of stereochemically and skeletally diverse scaffolds is a powerful tool for the discovery of novel chemotypes. Hence, the development of modular, step- and atom-economic synthetic methods to access stereochemically and skeletally diverse compound collection is particularly important. Herein, we show a metal-free, stereodivergent build/couple/pair strategy that allows access to a unique collection of benzo[5,6][1,4]oxazino[4,3-a]quinazoline, quinolino[1,2-a]quinazoline and benzo[b]benzo [4,5]imidazo[1,2-d][1,4]oxazine scaffolds with complete diastereocontrol and wide distribution of molecular architectures. This metal-free process proceeds via desymmetrization of phenol derivatives. The cascade unites Mannich with aza-Michael addition reactions, providing expeditious entries to diverse classes of molecular shapes in a single operation.

Peritumoral imaging features of thymic epithelial tumors for the prediction of transcapsular invasion: beyond intratumoral analysis

The purpose of this study was to differentiate cases without transcapsular invasion (Masaoka-Koga stage I) from cases with transcapsular invasion (Masaoka-Koga stage II or higher) in patients with thymic epithelial tumors (TETs) using tumoral and peritumoral computed tomography (CT) features. This retrospective study included 116 patients with pathological diagnoses of TETs. Two radiologists evaluated clinical variables and CT features, including size, shape, capsule integrity, presence of calcification, internal necrosis, heterogeneous enhancement, pleural effusion, pericardial effusion, and vascularity grade. Vascularity grade was defined as the extent of peritumoral vascular structures in the anterior mediastinum. The factors associated with transcapsular invasion were analyzed using multivariable logistic regression. In addition, the interobserver agreement for CT features was assessed using Cohen's or weighted kappa coefficients. The difference between the transcapsular invasion group and that without transcapsular invasion was evaluated statistically using the Student's t-test, Mann-Whitney U test, chi-square test, and Fisher's exact test. Based on pathology reports, 37 TET cases without and 79 with transcapsular invasion were identified. Lobular or irregular shape [odds ratio (OR): 4.19; 95% confidence interval (CI): 1.53-12.09; P = 0.006], partial complete capsule integrity (OR: 5.03; 95% CI: 1.85-15.13; P = 0.002), and vascularity grade 2 (OR: 10.09; 95% CI: 2.59-45.48; P = 0.001) were significantly associated with transcapsular invasion. The interobserver agreement for shape classification, capsule integrity, and vascularity grade was 0.840, 0.526, and 0.752, respectively (P < 0.001 for all). Shape, capsule integrity, and vascularity grade were independently associated with transcapsular invasion of TETs. Furthermore, three CT TET features demonstrated good reproducibility and help differentiate between TET cases with and without transcapsular invasion.

LAGOS‐US RESERVOIR: A database classifying conterminous U.S. lakes 4 ha and larger as natural lakes or reservoir lakes

AbstractThe LAGOS‐US RESERVOIR data module classifies all 137,465 lakes ≥ 4 ha in the conterminous U.S. into three categories using a machine learning predictive model based on visual interpretation of lake outlines and a lake shape classification rule. Natural Lakes (NLs) are defined as naturally formed, lacking large, flow‐altering structures; Reservoir Class A's (RSVR_A) are defined as lakes likely human‐made or human‐altered by a large water control structure; and Reservoir Class B's (RSVR_Bs) are lakes likely human‐made but are not connected to streams and have a shape rare in NLs. We trained machine learning models on 12,162 manually classified lakes to predict assignment as an NL or RSVR, then further classified RSVRs based on NHD Fcodes, isolation, and angularity. Our classification indicates that &gt; 46% of lakes ≥ 4 ha in the conterminous U.S. are reservoir lakes. These data can be easily combined with other LAGOS‐US modules and U.S. national databases for the broad‐scale study of reservoir lakes and NLs.

Revisiting the effect of sabot on the incident signals of split-Hopkinson pressure bar

In typical split-Hopkinson pressure bar set-ups, the striker bar is propelled in a barrel of larger diameter. Teflon/brass sabots are used to concentrically-align the striker inside the barrel. The influence of the area mismatch between barrel and striker, length of the sabots and interface condition between sabot and striker are analyzed in detail using finite element simulations. We show that for a given geometry of the sabot, a frictionless interface does not alter the incident signals. In the presence of friction, the incident signals deviate from the classical trapezoidal shape. The magnitude of the deviation depends on the geometry of the sabot. As an alternative to the shrink/press fitted sabot, a stepped striker is used to eliminate some issues faced during the usage of the shrink/press-fitted sabot. The stepped striker has a non-uniform diameter such that at two locations its diameter is that of the barrel, and at other locations it has the same diameter as the incident bar. The influence of the geometry of the stepped striker on the distortion of the incident signal is investigated in detail using the method of characteristics. A parametric study is used to quantify this distortion for various geometric configurations of the stepped striker. Three striker geometries are chosen from these configurations to validate the parametric study using experiments. High strain rate characterization of SS304 is also carried using these strikers to illustrate the effect of the geometry of the stepped striker on the stress versus strain and strain rate versus strain response.

Deformable Protein Shape Classification Based on Deep Learning, and the Fractional Fokker-Planck and Kähler-Dirac Equations.

The classification of deformable protein shapes, based solely on their macromolecular surfaces, is a challenging problem in protein-protein interaction prediction and protein design. Shape classification is made difficult by the fact that proteins are dynamic, flexible entities with high geometrical complexity. In this paper, we introduce a novel description for such deformable shapes. This description is based on the bifractional Fokker-Planck and Dirac-Kähler equations. These equations analyse and probe protein shapes in terms of a scalar, vectorial and non-commuting quaternionic field, allowing for a more comprehensive description of the protein shapes. An underlying non-Markovian Lévy random walk establishes geometrical relationships between distant regions while recalling previous analyses. Classification is performed with a multiobjective deep hierarchical pyramidal neural network, thus performing a multilevel analysis of the description. Our approach is applied to the SHREC'19 dataset for deformable protein shapes classification and to the SHREC'16 dataset for deformable partial shapes classification, demonstrating the effectiveness and generality of our approach.

Automatic Image Guidance for Assessment of Placenta Location in Ultrasound Video Sweeps.

Ultrasound-based assistive tools are aimed at reducing the high skill needed to interpret a scan by providing automatic image guidance. This may encourage uptake of ultrasound (US) clinical assessments in rural settings in low- and middle-income countries (LMICs), where well-trained sonographers can be scarce. This paper describes a new method that automatically generates an assistive video overlay to provide image guidance to a user to assess placenta location. The user captures US video by following a sweep protocol that scans a U-shape on the lower maternal abdomen. The sweep trajectory is simple and easy to learn. We initially explore a 2-D embedding of placenta shapes, mapping manually segmented placentas in US video frames to a 2-D space. We map 2013 frames from 11 videos. This provides insight into the spectrum of placenta shapes that appear when using the sweep protocol. We propose classification of the placenta shapes from three observed clusters: complex, tip and rectangular. We use this insight to design an effective automatic segmentation algorithm, combining a U-Net with a CRF-RNN module to enhance segmentation performance with respect to placenta shape. The U-Net+CRF-RNN algorithm automatically segments the placenta and maternal bladder. We assess segmentation performance using both area and shape metrics. We report results comparable to the state-of-the-art for automatic placenta segmentation on the Dice metric, achieving 0.83 ± 0.15 evaluated on 2127 frames from 10 videos. We also qualitatively evaluate 78,308 frames from 135 videos, assessing if the anatomical outline is correctly segmented. We found that addition of the CRF-RNN improves over a baseline U-Net when faced with a complex placenta shape, which we observe in our 2-D embedding, up to 14% with respect to the percentage shape error. From the segmentations, an assistive video overlay is automatically constructed that (i) highlights the placenta and bladder, (ii) determines the lower placenta edge and highlights this location as a point and (iii) labels a 2-cm clearance on the lower placenta edge. The 2-cm clearance is chosen to satisfy current clinical guidelines. We propose to assess the placenta location by comparing the 2-cm region and the bottom of the bladder, which represents a coarse localization of the cervix. Anatomically, the bladder must sit above the cervix region. We present proof-of-concept results for the video overlay.

A cluster analysis of some shapes of diatom valves

The results of the application of a cluster analysis to the shapes of some diatom valves are presented in the paper. The cluster analysis uses numeric descriptors of the shapes. To get such descriptors, the outlines of shapes have been transformed to the sequences of normalized and coordinated coefficients of elliptic Fourier transform. The coefficients have been used to construct shape dendrograms with the help of thee variants of hierarchical cluster analysis. The dendrograms have been truncated at the level of 6, 10 and 20 clusters. From the obtained clusters the stable groups of shapes, that are presented in all variant of clustering, have been separated. For each shape group an average shape have been constructed, which has been considered as a type shape. The type shapes are used as a template for the classification of the other shapes of diatom valves.

Classification of male upper body shape: An innovative approach

This study aims at the proposition of a novel strategy to classify the upper body silhouette of the male population into different shapes. Instead of using an existing measuring scheme based on linear evaluation of the body, we devise the use of angle-based anthropometric data to capture the exhibited curvature of the upper body. The objectives are attained by quantifying and employing the chest-waist (CW) angle and hip-waist (HW) angle in the instigation of a more appropriate classification of the upper body. A sample of 241 males aged 17–29 years was scanned through a 3D body scanner to gather the anthropometric data including chest girth, waist girth, and hip girth and their respective heights. In the next phase, the extracted information was used to calculate the angles. Based on the empirical realizations of the resulting indices, criteria defining the classifications of the body shape were determined. The operational environment is further enriched by considering varying levels of angular differences capable of offering more notable stratification of the upper male body shapes. It is realized that the angular difference of 10° between the CW and HW angles results in the more prominent classification of the upper male body. The proposed body classification technique classifies the sample of 241 males into three body shapes that are, straight (61%), hourglass (36.51%), and torch shape (2.48%). The classification scheme proposed in this study is a step toward achieving a high degree of customer satisfaction regarding clothing fit. It is a reference for coming research in body shape classification to achieve clothing fit in customized clothing.