Geometric Feature Extraction Research Articles

Fused deep learning based Facial Expression Recognition of students in online learning mode

SummaryIn this research work, Facial Expression Recognition (FER) is used in the analysis of facial expressions during the online learning sessions in the prevailing pandemic situation. An integrated geometric and appearance feature extraction is presented for the FER of the students participating in the online classes. The integrated features provided a low‐dimensional significant feature area for better facial data representation. Feasible Weighted Squirrel Search Optimization (FW‐SSO) algorithm is applied for selecting the optimal features due to its efficient exploration of the search space and enhancement of the dynamic search. The output of the FW‐SSO algorithm is used for tuning the autoencoder. Autoencoder is used for combining the G&A features, for feature optimization process. Classification is done by using Long Short‐Term Memory (LSTM) network with Attention Mechanism (ALSTM), as it is highly efficient in capturing the long‐term dependency of the facial landmarks in the image/video sequences. The proposed fused deep learning method focuses on the fusion of the G&A features for high discrimination. Experimental analysis using FER‐2013 and LIRIS datasets demonstrated that the proposed method achieved maximum accuracy of 85.96% than the existing architectures and maximum accuracy of 88.24% than the VGGNet‐CNN architecture.

Devanagari handwritten characters recognition using DCT, geometric and hue moments feature extraction techniques

Devanagari handwritten characters recognition using DCT, geometric and hue moments feature extraction techniques

Monocular 3D object detection with Pseudo-LiDAR confidence sampling and hierarchical geometric feature extraction in 6G network

The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms. Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost, low-power solution compared to LiDAR solutions in the field of autonomous driving. However, this technique has some problems, i.e., (1) the poor quality of generated Pseudo-LiDAR point clouds resulting from the nonlinear error distribution of monocular depth estimation and (2) the weak representation capability of point cloud features due to the neglected global geometric structure features of point clouds existing in LiDAR-based 3D detection networks. Therefore, we proposed a Pseudo-LiDAR confidence sampling strategy and a hierarchical geometric feature extraction module for monocular 3D object detection. We first designed a point cloud confidence sampling strategy based on a 3D Gaussian distribution to assign small confidence to the points with great error in depth estimation and filter them out according to the confidence. Then, we present a hierarchical geometric feature extraction module by aggregating the local neighborhood features and a dual transformer to capture the global geometric features in the point cloud. Finally, our detection framework is based on Point-Voxel-RCNN (PV-RCNN) with high-quality Pseudo-LiDAR and enriched geometric features as input. From the experimental results, our method achieves satisfactory results in monocular 3D object detection.

Thermal heat distribution features for hand identification

Thermal imaging is a non-invasive and portable technique with growing use in medical and authentication applications. This research utilizes thermal images for hand identification. Existing hand identification methods mainly extract geometric features, such as the palm’s and fingers’ absolute sizes and ratios. In this work, subject identification based on spatial statistical thermal distribution features is examined. These features do not depend on the geometric shape of the hand, but rather capture only physiological properties and convert them to statistical features. Thus, our goal is to evaluate the ability to identify a hand by characterizing the thermal heat distribution pattern, without relaying on geometric proprieties.A novel image processing algorithm, which identifies and locates the hand posture from the image and extracts several features from 15 locations in the hand, was developed. Then, dimensionality reduction methods are applied to form a compact model of the data. The best model was selected based on the clustering quality. Classification of a single subject out of many resulted with accuracy of 94%. Classification of many subjects simultaneously resulted with accuracy of 91%. Identification of new image data is carried out in this low-dimensional space and results with an accuracy of 94%. In addition, the low-dimensional representation was used to explore time and environmental factors, which were found to have a low impact on the coded data, thus promoted the suitability of the proposed method.

Performance of CPU GPU Parallel Architecture on Segmentation and Geometrical Features Extraction of Malaysian Herb Leaves

Image recognition includes the segmentation of image boundary geometrical features extraction and classification is used in the particular image database development. The ultimate challenge in this task is it is computationally expensive. This paper highlighted a CPU GPU architecture for image segmentation and features extraction processes of 125 images of Malaysian Herb Leaves. Two GPUs and three kernels are utilized in the CPU GPU platform using MATLAB software. Each of herb image has pixel dimensions 16161080. The segmentation process uses the Sobel operator which is then used to extract the boundary points. Finally seven geometrical features are extracted for each image. Both processes are first executed on the CPU alone before bringing it onto a CPU GPU platform to accelerate the computational performance. The results show that the developed CPU GPU platform has accelerated the computation process by a factor of 4.13. However the efficiency shows a decline which suggests that the processors utilization must be improved in the future to balance the load distribution.

Geometric Feature Extraction for Identification and Classification of Overlapping Cells for Leukaemia

This paper describes the study of overlapping leukaemia cells based on geometric features for identification and classification. Geometric features of blood cells are proposed to identify and classify overlapping cells into groups based on different overlapping degrees and the number of overlapped cells. In the proposed method, the percentage of average accuracy for identifying overlapping cells reached 98 percent. The proposed method can segment white blood cells from the overlapping cells with an overlapping degree of 70 percent. Improved Watershed Algorithm successfully increased 36.89 percent of accuracy in WBC segmentation. It reduced 46.12 percent of the over-segmentation problem. Tests of cell counting are conducted in the two stages, which are before and after the process of identification and classification of overlapping cells. The average percentage of total cell count is 83.31 percent, the average percentage of WBC counting is 84.8 percent, and the average percentage of RBC counting is 60.55 percent. The proposed method is efficient in identifying and classifying overlapping cells for increasing the accuracy of cell counting.

3D Face Geometry Optimization Using Artificial Intelligence and Computer Graphics

Human face plays an indispensable role in emotional expression and information exchange, which attracts large number of researchers to study face recognition. Nowadays, with the rapid development of computer graphics, artificial intelligence, and other technologies, the ability of the human vision system to recognize facial expressions and facial organs is enhanced. More and more experts think about how to make the computer vision system have this capability. By combining artificial intelligence and computer graphics, this paper studies how to optimize the 3D face network model and extract geometric features for 3D face recognition. We propose a 3D face network model based on Poisson equation to realize face hole recognition and boundary preprocessing. Besides, we also establish the 3D face surface equation and equal face value extraction and enhance the face feature based on facial semantic information. We study the hole repair of 3D face model based on Poisson equation integrating semantic information and achieve the purpose of optimizing the 3D face model. After the optimization, the method is compared with mesh repair and Poisson repair, which demonstrates that our Poisson-based 3D face hole repairing model obtains the best results among compared methods.

AGFP-Net: Attentive geometric feature pyramid network for land cover classification using airborne multispectral LiDAR data

Accurate land cover (LC) classification plays an important role in ecosystem protection, climate changes, and urban planning. The airborne multispectral LiDAR data are increasingly used for high-resolution and accurate LC classification tasks. However, most of the existing methods lack of the comprehensive extraction of the spatial geometric structure features, and ignore the fusion of multi-scale extracted features. In this paper, a point-wise deep learning-based method is proposed for LC classification based on airborne multispectral LiDAR data. We present a novel convolution operator to efficiently extract the spatial geometric structure features, called attentive graph geometric moments convolution (AGGM Convolution). Besides, to fuse the extracted multi-scale features, we propose a feature up-sampling module and construct a feature pyramid to integrate the features with different scales. The proposed method was evaluated using multispectral LiDAR data acquired with an airborne Teledyne Optech Titan system. In comparison with the previously developed state-of-the-art point cloud segmentation models, the proposed method behaves superiorly with an overall accuracy of 96.9% and a Kappa index of 0.950 on the test scenes. The quantitative assessments demonstrate that the proposed method performs effectively and efficiently in land cover classification tasks.

Mental arithmetic task detection using geometric features extraction of EEG signal based on machine learning.

Mental arithmetic analysis based on electroencephalogram (EEG) signals can help to understand some disorders such as attention deficit hyperactivity disorder, arithmetic disorder, or autism spectrum disorder in which learning is difficult. Most mental computation detection and classification systems rely on the characteristics of a single channel, however, the understanding of the connections between EEG channels, which certainly contains valuable information, is still evolving. The methods presented in this paper are the result of a research project that introduces an alternative method for better and faster receipt of information from the EEG signals of individuals, which are generally complex and nonlinear. The EEGs of 66 healthy individuals were recorded in two rest modes and mental task a designed, with a sampling frequency of 500 Hz. To classify these two modes, we extracted features from our recordings to differentiate the EEG signals of these two groups in a single channel as well as combine possible channels. The new method that was proposed was the extraction of several geometric features from Poincaré design analysis, which used the necessary comparison t-test to determine brain differences, with a significance level of less than 0.05 in the state of mental calculations and facial rest. Also, an artificial neural network (ANN) has been used for automatic learning and diagnosis in the two mentioned modes. The results of this paper show that by using a combination of geometric properties (sides, angles, shortest distance, slope, and coefficients of the third-degree equation) using selected channels (FP1, F7, C4, O1) can achieve 100 % accuracy. The sensitivity reached 100 %. As well as 100 % feature. With the help of mental calculation, it is possible to diagnose, treat, rehabilitate and rehabilitation people who have lost the function of a part of their brain due to a disease in this field (Tab. 6, Fig. 15, Ref. 45).

4D Facial Expression Recognition Using Geometric Landmark-based Axes-angle Feature Extraction

The primary goal of this paper is to describe a proposed framework for identifying human face expressions. A methodology has been proposed and developed to identify facial emotions using an axes-angular feature extracted from facial landmarks for 4D dynamic facial expression video data. The 4D facial expression recognition (FER) problem is modeled as an unbalanced problem using the full video sequence. The proposed dataset includes landmarks that are positioned to be fiducial features: around the brows, eyes, nose, cheeks, and lips. Following the initial facial landmark preprocessing, feature extraction is carried out. Input feature vectors from gamma axes and magnitudes in three-dimensional Euclidean space are constructed. This paper develops a new feature vector by concatenating the angle and magnitude features and compares them to a model created independently using angle features. In all three models, several filter-based feature selection techniques are used to estimate feature importance. The framework employs a multi-class support vector machine (SVM) on MATLAB, and the true positive rate (TPR) and average recognition rates (ARR) are used as performance metrics. In terms of average classification accuracy, the final results are compared to conventional state-of-the-art approaches. The results revealed a highly informative combined feature, demonstrating the efficiency of the proposed landmark-based strategy to classify facial expressions.

Classification of audio signals using spectrogram surfaces and extrinsic distortion measures

Representation of one-dimensional (1D) signals as surfaces and higher-dimensional manifolds reveals geometric structures that can enhance assessment of signal similarity and classification of large sets of signals. Motivated by this observation, we propose a novel robust algorithm for extraction of geometric features, by mapping the obtained geometric objects into a reference domain. This yields a set of highly descriptive features that are instrumental in feature engineering and in analysis of 1D signals. Two examples illustrate applications of our approach to well-structured audio signals: Lung sounds were chosen because of the interest in respiratory pathologies caused by the coronavirus and environmental conditions; accent detection was selected as a challenging speech analysis problem. Our approach outperformed baseline models under all measured metrics. It can be further extended by considering higher-dimensional distortion measures. We provide access to the code for those who are interested in other applications and different setups (Code: https://github.com/jeremy-levy/Classification-of-audio-signals-using-spectrogram-surfaces-and-extrinsic-distortion-measures).

Unconstrained Hand Dorsal Veins Image Database and Recognition System

Hand veins can be used effectively in biometric recognition since they are internal organs that, in contrast to fingerprints, are robust under external environment effects such as dirt and paper cuts. Moreover, they form a complex rich shape that is unique, even in identical twins, and allows a high degree of freedom. However, most currently employed hand-based biometric systems rely on hand-touch devices to capture images with the desired quality. Since the start of the COVID-19 pandemic, most hand-based biometric systems have become undesirable due to their possible impact on the spread of the pandemic. Consequently, new contactless hand-based biometric recognition systems and databases are desired to keep up with the rising hygiene awareness. One contribution of this research is the creation of a database for hand dorsal veins images obtained contact-free with a variation in capturing distance and rotation angle. This database consists of 1548 images collected from 86 participants whose ages ranged from 19 to 84 years. For the other research contribution, a novel geometrical feature extraction method has been developed based on the Curvelet Transform. This method is useful for extracting robust rotation invariance features from vein images. The database attributes and the veins recognition results are analyzed to demonstrate their efficacy.

Automated classification of valvular heart diseases using FBSE-EWT and PSR based geometrical features

The growing prevalence and high mortality rate due to valvular heart diseases (VHD) are concerned. Therefore, its accurate, rapid, and early diagnosis is important. This study processes the phonocardiogram (PCG) signals for automatic detection of VHD associated with aortic stenosis (AS), mitral stenosis (MS), mitral valve prolapse (MVP) and mitral regurgitation (MR) which is originated by the MVP. In the proposed approach, we have used Fourier-Bessel series expansion-based empirical wavelet transform (FBSE-EWT) for capturing the non-stationary nature of PCG signals. It follows by selecting significant Fourier-Bessel intrinsic mode functions (FBIMFs) and extraction of geometrical features from two-dimensional phase space reconstruction (2D-PSRs) of the FBIMFs. To reduce the real-time processing load, the feature set dimension is reduced by using metaheuristics optimization-based features selection (FS) algorithms, namely, the salp swarm optimization algorithm (SSOA), emperor penguin optimization algorithm (EPOA), and tree growth optimization algorithm (TGOA). These FS methods have been tested and compared with machine learning classifiers. The result indicates the effectivity of FBSE-EWT based features extraction and used FS methods in classifying the intended categories of PCG signals. With the reduced features set, obtained with SSOA, the proposed approach has resulted in the highest classification accuracies of 98.53 %, 98.84 %, 99.07 % and 99.70 % respectively for the five classes, four classes, three classes, and two classes problems. Thus, besides aiding the cardiologists, this approach is also useful for developing wearable cardiac devices (as it uses a reduced feature set) for heart health monitoring and diagnosis purposes.

The Active Segmentation Platform for Microscopic Image Classification and Segmentation.

Image segmentation still represents an active area of research since no universal solution can be identified. Traditional image segmentation algorithms are problem-specific and limited in scope. On the other hand, machine learning offers an alternative paradigm where predefined features are combined into different classifiers, providing pixel-level classification and segmentation. However, machine learning only can not address the question as to which features are appropriate for a certain classification problem. The article presents an automated image segmentation and classification platform, called Active Segmentation, which is based on ImageJ. The platform integrates expert domain knowledge, providing partial ground truth, with geometrical feature extraction based on multi-scale signal processing combined with machine learning. The approach in image segmentation is exemplified on the ISBI 2012 image segmentation challenge data set. As a second application we demonstrate whole image classification functionality based on the same principles. The approach is exemplified using the HeLa and HEp-2 data sets. Obtained results indicate that feature space enrichment properly balanced with feature selection functionality can achieve performance comparable to deep learning approaches. In summary, differential geometry can substantially improve the outcome of machine learning since it can enrich the underlying feature space with new geometrical invariant objects.

Accuracy Assessment of Cultural Heritage Models Extracting 3D Point Cloud Geometric Features with RPAS SfM-MVS and TLS Techniques

A proper classification of 3D point clouds allows fully exploiting data potentiality in assessing and preserving cultural heritage. Point cloud classification workflow is commonly based on the selection and extraction of respective geometric features. Although several research activities have investigated the impact of geometric features on classification outcomes accuracy, only a few works focused on their accuracy and reliability. This paper investigates the accuracy of 3D point cloud geometric features through a statistical analysis based on their corresponding eigenvalues and covariance with the aim of exploiting their effectiveness for cultural heritage classification. The proposed approach was separately applied on two high-quality 3D point clouds of the All Saints’ Monastery of Cuti (Bari, Southern Italy), generated using two competing survey techniques: Remotely Piloted Aircraft System (RPAS) Structure from Motion (SfM) and Multi View Stereo (MVS) techniques and Terrestrial Laser Scanner (TLS). Point cloud compatibility was guaranteed through re-alignment and co-registration of data. The geometric features accuracy obtained by adopting the RPAS digital photogrammetric and TLS models was consequently analyzed and presented. Lastly, a discussion on convergences and divergences of these results is also provided.

Adaptive neighborhood size and effective geometric features selection for 3D scattered point cloud classification

Classification of 3D scatter and unorganized point cloud (PC) is an ongoing hard problem due to high redundancy, unbalanced sampling density, and large data structure of PC. Geometric and spectral features derived from the PC are generally used for classification. In this paper, an Omnivariance based adaptive neighborhood size selection method and a new feature set composed of 14 features are proposed for extraction of geometric features for each individual point within the local neighborhood. Performance of 8 modern classifiers with different strategies (i.e., boosting, ensemble, and deep learning etc.) were evaluated on the Oakland, Vaihingen, and ISPRS datasets. These 3 datasets are identified by 5, 9, and 2 distinct object classes, respectively. The results were compared with different neighborhood size selection methods (i.e., eigenentropy based, fixed number of the k-nearest neighbors) and feature set (i.e., 21 features). Only 3D local features were employed to classify datasets with varying characteristics and properties. The proposed optimum neighbor selection method and feature set provided the best statistical results with Auto-Encoder classifier (the overall accuracies are over 85%, 60% and, 90% the Oakland, Vaihingen, and ISPRS datasets, respectively). Especially for the ISPRS dataset, the Auto-Encoder obtained over 94%, 90%, and 93% precision, recall, and f-score, respectively.

Time-Resolved Geometric Feature Tracking Elucidates Laser-Induced Keyhole Dynamics

During laser melting of metals, localized metal evaporation resulting in the formation of a keyhole shaped cavity can occur if processing conditions are chosen with high power density. An unstable keyhole can have deleterious effects in certain applications (e.g., laser powder bed fusion) as it increases the likelihood of producing defects such as porosity. In this work, we propose a pipeline that enables complete segmentation and extraction of various geometric features in keyholing conditions. In situ synchrotron high-speed X-ray visualization at the Advanced Photon Source provides large datasets of experimental images with a high spatio-temporal resolution across a range of laser parameters for Ti-6Al-4V. Computer vision image processing techniques were used to extract time-resolved quantitative geometric features (e.g., depth, width, front wall angle) throughout keyhole evolution which were subsequently analyzed to understand the relationship between the variation of local keyhole geometry and processing conditions. This analysis is the first to employ a data-driven approach to further our understanding of the keyholing process regime.

Weld pool and keyhole geometric feature extraction in K-TIG welding with a gradual gap based on an improved HDR algorithm

The change of the gap width is one of the important factors that affect the quality of K-TIG welding, and it is difficult to keep the gap consistent in the welding of large workpieces. Vision technology is a reliable method of weld pool monitoring. To avoid the influence of the strong arc of K-TIG welding, this paper designed a real-time HDR system and based on which, a weld pool and keyhole geometric feature extraction algorithm was proposed. The designed HDR system includes an automatic exposure algorithm which is suitable for HDR and an improved HDR fusion algorithm which uses exposure instead of exposure time for HDR fusion. Finally, the dynamic behavior of the weld pool and weld forming with gradually changing gap were analyzed. And conclude that under the same gap, whether the gap changed from small to large or from large to small suddenly, the weld pool will collapse. In the case of the same gap change rate, the weld forming of the welding direction from a large gap to a small gap is much worse than that from a small gap to a large gap. Therefore, it is necessary to avoid a welding direction from a large gap to a narrow gap.

Combined Use of 3D and HSI for the Classification of Printed Circuit Board Components

Successful recycling of electronic waste requires accurate separation of materials such as plastics, PCBs and electronic components on PCBs (capacitors, transistors, etc.). This article therefore proposes a vision approach based on a combination of 3D and HSI data, relying on the mutual support of the datasets to compensate existing weaknesses when using single 3D- and HSI-Sensors. The combined dataset serves as a basis for the extraction of geometric and spectral features. The classification is performed and evaluated based on these extracted features which are exploited through rules. The efficiency of the proposed approach is demonstrated using real electronic waste and leads to convincing results with an overall accuracy (OA) of 98.24%. To illustrate that the addition of 3D data has added value, a comparison is also performed with an SVM classification based only on hyperspectral data.

Detection of Sickle Cell Anemia Through Contour Evidence Extraction and Estimation

Diagnosis of sickle cell anemia by manual visual inspection through microscope is time consuming and causes human errors. Observational errors occur mostly due to overlapping of cells in blood smear image. Here, an automatic segmentation approach is introduced which isolates sickle cells from all other cells within a blood sample. The proposed system is an approach to find the elliptically shaped sickle cells through geometric feature extraction and contour based segmentation to isolate sickle cells. This technique is a method of isolating sickle cells from other cells within blood sample using cell morphology. A combined approach of extraction of seed points, contour extraction and estimation of contours is used for separation of sickle cells from red blood cells. The methods used for the extraction of seed points are by Ultimate Erosion for Convex Sets and Fast Radial Symmetry transform. The contour evidence is extracted by associating edges of the cells to the seed points. The overlapping and clustered cells in image are identified using ellipse fitting method for contour estimation. Using the seed points and the contour extraction, the edges of the cells are estimated. The lines joining the shape of cells are drawn through estimation of shape of contour. This eliminates cells other than elliptical shaped cells. The proposed system can successfully isolate sickle cells from healthy blood cells within the blood smear image. This automated system has a better accuracy and faster computation speed compared to the existing methods for the detection of sickle cells. This identification methodology helps the health professionals for faster diagnosis.