Use Of Geometric Features Research Articles

A support vector machine and image processing based approach for counting open cotton bolls and estimating lint yield from UAV imagery

Cotton boll count is an important phenotypic trait that aids in a better understanding of the genetic and physiological mechanisms of cotton growth. Several computer vision technologies are available for cotton boll segmentation. However, estimating the number of cotton bolls in a segmented cluster of cotton bolls is a challenging task due to the complex shapes of cotton bolls. This study proposed a combination of spectral-spatial and supervised machine learning based methods for cotton boll candidate recognition and counting from high resolution RGB images obtained from unmanned aerial vehicles (UAVs). An algorithm consisting of machine vision, band-mean filter, Otsu thresholding, red/blue band ratio filter, and geometrical characteristics-based error removal techniques, was employed to detect open cotton boll pixels under several environmental settings. In addition, a support vector machine (SVM) based encoding method was developed using geometric features of cotton boll candidates to predict the number of cotton bolls from the segmented cotton boll candidates. This algorithm was implemented over three experiment sites with three cotton varieties, two tillage practices, seven cover crop treatments, two irrigation regimes (irrigated and rainfed), 26 irrigation levels, and two sensors (DJI FC6310 RGB and MicaSense Rededge) capturing images at two spatial resolutions (0.75 cm and 1.07 cm) over two growing seasons (2019 and 2021). These different experimental settings allowed the proposed approaches to be validated against a variety of complex backgrounds. A visual inspection of 1000 randomly selected pixels revealed that the proposed cotton boll candidate recognition approach was highly effective in segmenting cotton bolls and background pixels, with high classification accuracy (> 95%) and a low number of falsely classified pixels (precision > 0.96; recall > 0.93). A high correlation between ground truth observations and predicted cotton boll count indicated that the use of geometric features of segmented candidates as predictors in association with the SVM model demonstrated a good performance in estimating boll count from recognized cotton boll candidates. Furthermore, linear regression analyses revealed that both boll count and candidate area are potential predictors of lint yield, with boll count being a better predictor than candidate area. Overall, the study demonstrated that machine vision/learning techniques can be potentially used on UAV images to count the number of cotton bolls and predict lint yield over large acreages with reasonable accuracy.

Computational Investigation of Micro-channel Heat Sink with Rectangular Shape Obstacles

Nowadays a lot of interest is given to the geometrical modification of heat sink systems to cool down the electronic components. To improve the performance index of the heat sinks, the use of geometrical features with different shapes and at different locations on the surface can be a valuable approach. In this paper, the effect of rectangular shape obstacles on the micro channel heat sink (MCHS) performance is studied. Due to surface features, vortex is developed which helps to increase the heat transfer rate. Numerical modeling software Comsol Multiphysics with heat transfer in fluid physics is used to investigate the characteristics of a micro-channel heat sink. The numerical result shows that the heat transfer rate can be improved through an appropriate arrangement of rectangular shape obstacles, on the heat sink. Numerical analysis and the comparison is carried out for micro-channel heat sink with and without obstacles. In this paper, various parameters like temperature rise, cell Peclet number and Mean effective thermal conductivity are studied.

Computer-Assisted Analysis of Human Semen Concentration and Motility

Computer-assisted semen analysis systems insist on evaluating sperm characteristics. These systems afford capacity to study and evaluate sperm statistical and morphological characteristics such as concentration, morphology, and motility, which have an important role in diagnosis and treatment of male infertility. In this paper, the proposed algorithm allows the assessment of concentration and motility rate of sperms in microscopic videos. First, enhancement process is required because of microscopic images limitations such as low contrast and noises. Then, for true sperm recognition among noise and debris, a hybrid approach is proposed using a combination between segmentation techniques. After, the use of geometric features of the bounding ellipse of the sperm head led to define sperm concentration. Finally, inter-frame difference is applied for motile sperm detection. The proposed method was tested on microscopic videos of human semen; the performance of this method is analyzed in terms of speed, accuracy, and complexity. Obtained results during the experiments are very promising compared with those obtained by the traditional assessment, which is the most widely used and approved in the laboratories.

Geometrical background of architectural-planning organization of crimean-tatar housing

Problem statement. The article provides a brief overview of the geometric prerequisites for the selection of architectural and planning solutions of the Crimean Tatar housing in the XVIII − XIX centuries. in the mountainous, foothill and steppe regions of the Crimea. Identified some of the geometric features of architectural and planning decisions of the organization of the Crimean Tatar housing. Over a number of epochs, the complex evolution of ethno-cultural traditions, which are based on ancient layers of the history of culture, is reflected in the architecture of the Crimean Tatars. Not the last place in such a hierarchy is occupied by questions of geometric order, in a certain way characterizes the morphology of architecture of the Crimean Tatars. The development of architecture in modern society is a rather complicated process. On the one hand, there is an obvious tendency towards universal globalization, which threatens to level national cultures. On the other hand, there is a growing tendency in the world to preserve and enhance national cultural values, to strengthen the self-awareness of each nation, to ensure the flourishing of its culture, to revive the origins of folk art and architecture. Under these conditions, it is necessary to recall the relevance of the process of reviving the Crimean-Tatar architecture. One of the constituent features of the composite organization of the Crimean Tatar housing of the XVIII − XIX centuries. in the mountainous, foothill and steppe regions of the Crimea, there is a system for applying geometric bases both in the planning organization of housing and in other aspects: orientation to the cardinal points, insolation, lighting, and the like. The purpose of the article is the establishment of geometric prerequisites for architectural planning decisions of the Crimean Tatar dwelling, and their importance for the formation of architecture in the Crimea in the 20th century . in the context of the reconstruction of the prerequisites, patterns and peculiarities of the development of the Crimean Tatar architecture. Conclusions. The study of the geometric premises of the architectural and planning organization of the Crimean Tatar housing allowed to determine that geometric prerequisites and geometric means of design and construction are important for the architectural planning organization of the Crimean Tatar housing. Geometric prerequisites include: important positions of rational use of geometric features of the relief, principles of rational geometry, which are based on natural, ethnic and extreme influences. Geometry is used: to determine spatial forms; to create forms that are considered harmonious, and accordingly for the planning of buildings and their environment in accordance with mathematical, aesthetic and sometimes religious principles; to decorate buildings with mathematical objects, such as tessellation; and to address environmental issues, such as minimizing the swirling winds at the bottom of the skyscrapers. It is proved that the formation and development of the Crimean Tatar architecture is inextricably linked with the evolution of its architectural and planning characteristics, which are directly related to the geometry. The study allowed to establish some geometric features of architectural and planning decisions of the organization of the Crimean Tatar housing in the XVIII − XIX centuries. in the mountainous, foothill and steppe regions of the Crimea.

Extraction of Character Regions through Machine Learning and Filtering

Characters in images are able to provide main information of the image. Therefore, it is important to analyze various kinds of image data and accurately extract the characters in images. This study proposes a new method of excluding background regions and accurately detecting character regions from input images with the uses of MCT features and Adaboost algorithm. The proposed method first extracts candidate character regions from input images with the uses of MCT features and Adaboost algorithm. It then excludes non-character regions and detects real character regions from the extracted candidate regions with the use of geometrical features. In the experiment of this study, the proposed method more robustly detected character regions from various input color images than a conventional method. For performance comparison, this study compared the method based on existing texture analysis and the proposed method. In this study, to qualitatively evaluate the performance of the proposed method of extracting license plate regions, the accuracy measure was defined. The measure is used to show the ratio of the accurately extracted character regions to all character regions of an image. The conventional method using the frequency factor-based texture information had many errors of character region detection, since it failed to execute binarization of background and character regions properly. On contrary, the proposed method made use of MCT features and Adaboost algorithm, effectively filtered candidate regions with the use of geometrical features, so that it detected character regions more accurately. The proposed character detection method is expected to be usefully applied to the fields of pattern recognition and image processing, such as store sign recognition and license plate recognition.

RESIDUAL SHUFFLING CONVOLUTIONAL NEURAL NETWORKS FOR DEEP SEMANTIC IMAGE SEGMENTATION USING MULTI-MODAL DATA

Abstract. In this paper, we address the deep semantic segmentation of aerial imagery based on multi-modal data. Given multi-modal data composed of true orthophotos and the corresponding Digital Surface Models (DSMs), we extract a variety of hand-crafted radiometric and geometric features which are provided separately and in different combinations as input to a modern deep learning framework. The latter is represented by a Residual Shuffling Convolutional Neural Network (RSCNN) combining the characteristics of a Residual Network with the advantages of atrous convolution and a shuffling operator to achieve a dense semantic labeling. Via performance evaluation on a benchmark dataset, we analyze the value of different feature sets for the semantic segmentation task. The derived results reveal that the use of radiometric features yields better classification results than the use of geometric features for the considered dataset. Furthermore, the consideration of data on both modalities leads to an improvement of the classification results. However, the derived results also indicate that the use of all defined features is less favorable than the use of selected features. Consequently, data representations derived via feature extraction and feature selection techniques still provide a gain if used as the basis for deep semantic segmentation.

An Internal Crown Geometric Model for Conifer Species Classification With High-Density LiDAR Data

The knowledge of the tree species is a crucial information that governs the success of precision forest management practice. High-density small footprint multireturn airborne light detection and ranging (LiDAR) scanning can collect a huge amount of point samples containing structural details of the forest vertical profile, which can reveal important structural information of the forest components. LiDAR data have been successfully used to distinguish between coniferous and deciduous/broadleaved tree species. However, species classification within a class (e.g., the conifer class) using LiDAR data is a challenging problem when considering the tree external crown characteristics only. This paper presents a novel method for conifer species classification based on the use of geometric features describing both the internal and external structures of the crown. The internal crown geometric features (IGFs) are defined based on a novel internal branch structure model, which uses 3-D region growing and principal component analysis to delineate the branch structure of a conifer tree accurately. IGFs are used together with external crown geometric features to perform conifer species classification. Three different support vector machines have been considered for classification performance evaluation. The experimental analysis conducted on high-density LiDAR data acquired over a portion of the Trentino region in Italy proves the effectiveness of the proposed method.

A Classification-Segmentation Framework for the Detection of Individual Trees in Dense MMS Point Cloud Data Acquired in Urban Areas

In this paper, we present a novel framework for detecting individual trees in densely sampled 3D point cloud data acquired in urban areas. Given a 3D point cloud, the objective is to assign point-wise labels that are both class-aware and instance-aware, a task that is known as instance-level segmentation. To achieve this, our framework addresses two successive steps. The first step of our framework is given by the use of geometric features for a binary point-wise semantic classification with the objective of assigning semantic class labels to irregularly distributed 3D points, whereby the labels are defined as “tree points” and “other points”. The second step of our framework is given by a semantic segmentation with the objective of separating individual trees within the “tree points”. This is achieved by applying an efficient adaptation of the mean shift algorithm and a subsequent segment-based shape analysis relying on semantic rules to only retain plausible tree segments. We demonstrate the performance of our framework on a publicly available benchmark dataset, which has been acquired with a mobile mapping system in the city of Delft in the Netherlands. This dataset contains 10.13 M labeled 3D points among which 17.6 % are labeled as “tree points”. The derived results clearly reveal a semantic classification of high accuracy (up to 90.77 %) and an instance-level segmentation of high plausibility, while the simplicity, applicability and efficiency of the involved methods even allow applying the complete framework on a standard laptop computer with a reasonable processing time (less than 2.5 h).

Analytical and numerical investigations on the accuracy and robustness of geometric features extracted from 3D point cloud data

In photogrammetry, remote sensing, computer vision and robotics, a topic of major interest is represented by the automatic analysis of 3D point cloud data. This task often relies on the use of geometric features amongst which particularly the ones derived from the eigenvalues of the 3D structure tensor (e.g. the three dimensionality features of linearity, planarity and sphericity) have proven to be descriptive and are therefore commonly involved for classification tasks. Although these geometric features are meanwhile considered as standard, very little attention has been paid to their accuracy and robustness. In this paper, we hence focus on the influence of discretization and noise on the most commonly used geometric features. More specifically, we investigate the accuracy and robustness of the eigenvalues of the 3D structure tensor and also of the features derived from these eigenvalues. Thereby, we provide both analytical and numerical considerations which clearly reveal that certain features are more susceptible to discretization and noise whereas others are more robust.

Non-interferometric GB-SAR measurement: application to the Vallcebre landslide (eastern Pyrenees, Spain)

Abstract. In the last decade, ground-based interferometry has proven to be a powerful technique for continuous deformation monitoring of landslides, glaciers, volcanoes, or manmade structures, among others. However, several limitations need to be addressed in order to improve the performances of the technique, especially for long-term monitoring. These limitations include the reduction of measurable points with an increase in the period of observation, the ambiguous nature of the phase measurements, and the influence of the atmospheric phase component. In this paper, a new procedure to process the amplitude component of ground-based synthetic aperture radar (GB-SAR) data acquired in discontinuous mode is compared and validated. The use of geometric features of the amplitude images combined with a matching technique will allow the estimation of the displacements over specific targets. Experimental results obtained during 19 months, in eight different campaigns carried out in the active landslide of Vallcebre (eastern Pyrenees, Spain), were analysed. During the observed period, from February 2010 to September 2011, displacements up to 80 cm were measured. The comparison with other surveying technique shows that the precision of the method is below 1 cm.

Use of geometric features of principal components for indexing a biometric database

Financial inclusion is the delivery of financial services at affordable cost to sections of disadvantaged and low income segments of society. It has several leakages such as security threats and transaction frauds in the available system. The use of biometrics in the financial inclusion is a near perfect solution to such security threats. Such a biometric system should be fast enough to recognise/identify a subject from a large database. This paper proposes an indexing technique for a biometric database consisting of variable number of features with high dimensions. The technique makes use of geometric properties of principal components of features. Unlike existing indexing techniques, it inserts fewer features into a hash table. It reduces both computational and memory costs significantly. The geometric properties of principal components of features are found to be robust to handle translation and rotation effects. The proposed technique has been tested on palmprint biometric databases viz. PolyU [25], CASIA [26] and IITK which have 7752, 5239 and 549 images respectively. It is found to be more efficient than any other existing indexing techniques.

Method of Remote Sensing Image Fine Classification Based on Geometric Features and SVM

In order to overcome the phenomenon of foreign bodies in the same spectrum in remote sensing images, as needs of land-use surveys, traditional methods often can’t get good results. In this paper, an efficient method for dividing the classifying results of traditional methods into further items is proposed and studied. Our approach to remote sensing image fine classification is based on both geometric features and SVM. By making full use of geometric features in the structure of property characteristics, we produce rules of the morphological characteristics and distribution. With deductive reasoning, we further classify the classifying results of SVM classifier. Tests showed that the method can be better broken down into the waters of rivers, lakes, reservoirs and ponds.

Method of Remote Sensing Image Fine Classification Based on Geometric Features and SVM

In order to overcome the phenomenon of foreign bodies in the same spectrum in remote sensing images, as needs of land-use surveys, traditional methods often can’t get good results. In this paper, an efficient method for dividing the classifying results of traditional methods into further items is proposed and studied. Our approach to remote sensing image fine classification is based on both geometric features and SVM. By making full use of geometric features in the structure of property characteristics, we produce rules of the morphological characteristics and distribution. With deductive reasoning, we further classify the classifying results of SVM classifier. Tests showed that the method can be better broken down into the waters of rivers, lakes, reservoirs and ponds.

Study on the Algorithms of Holes Feature Recognition in Auto Body Panels Based on UG

Feature recognition is the key technology in establishing auto body panel CAPP system. For regular parts, it has made great achievements in features recognition, which has laid a foundation for feature recognition for complex shape parts, such as auto body panels. This paper has classified holes feature into two-dimensional holes, three-dimensional holes and special holes according to its forming and function properties, and established process expression mode of holes feature on account of the requirement of CAPP system. Algorithms have been developed for holes feature recognition based on recognition rules making use of geometric features of holes’ boundary in UG software, two-dimensional holes and three-dimensional holes can be automatically distinguished, circle holes and non circle holes can also be differentiated automatically, further more, the algorithms can give radius of circle hole and minimum radius of curvature of shaped hole’ boundaries.

Intrinsic Statistics on Riemannian Manifolds: Basic Tools for Geometric Measurements

In medical image analysis and high level computer vision, there is an intensive use of geometric features like orientations, lines, and geometric transformations ranging from simple ones (orientations, lines, rigid body or affine transformations, etc.) to very complex ones like curves, surfaces, or general diffeomorphic transformations. The measurement of such geometric primitives is generally noisy in real applications and we need to use statistics either to reduce the uncertainty (estimation), to compare observations, or to test hypotheses. Unfortunately, even simple geometric primitives often belong to manifolds that are not vector spaces. In previous works [1, 2], we investigated invariance requirements to build some statistical tools on transformation groups and homogeneous manifolds that avoids paradoxes. In this paper, we consider finite dimensional manifolds with a Riemannian metric as the basic structure. Based on this metric, we develop the notions of mean value and covariance matrix of a random element, normal law, Mahalanobis distance and χ2 law. We provide a new proof of the characterization of Riemannian centers of mass and an original gradient descent algorithm to efficiently compute them. The notion of Normal law we propose is based on the maximization of the entropy knowing the mean and covariance of the distribution. The resulting family of pdfs spans the whole range from uniform (on compact manifolds) to the point mass distribution. Moreover, we were able to provide tractable approximations (with their limits) for small variances which show that we can effectively implement and work with these definitions.