Local Descriptors Research Articles

Correction: Why local softness and local hyper-softness are more appropriate local reactivity descriptors than dual descriptor and Fukui functions?

Correction: Why local softness and local hyper-softness are more appropriate local reactivity descriptors than dual descriptor and Fukui functions?

Learning more discriminative local descriptors with parameter-free weighted attention for few-shot learning

Learning more discriminative local descriptors with parameter-free weighted attention for few-shot learning

Face Gender Classification using Combination of LPQ-Self PCA

The age factor had a significant impact on human faces, potentially influencing the performance of existing gender classification systems. This research proposed a new method that combined local descriptors such as Local Binary Patterns (LBP) and Local Phase Quantization (LPQ) with Self-Principal Component Analysis (Self-PCA) as a feature extraction technique. The use of Self-PCA was chosen for its ability to address the age factor in human facial images, while also leveraging local descriptors to capture features from these images. The primary focus was to compare the performance of Self-PCA with LPQ+Self-PCA, along with the additional comparison of LBP+Self-PCA, in the task of gender classification using facial images. Euclidean distance served as the classifier, and the evaluation was conducted using the FG-Net and ORL datasets. The combination of LPQ+Self-PCA showed an improvement in accuracy by 57.85% compared to the combination of LBP+Self-PCA, which provided an accuracy of 56.47%. Meanwhile, using Self-PCA alone gave an accuracy of 55.37% on the FG-Net. In contrast, on the ORL dataset, both combinations gave the same accuracy result as Self-PCA, which was 90.14%, for images without blurring.

Electronic contribution of ligands and metal in palladium and palladium-tin bimetallic complexes: A comparative study of reactivity descriptors using different ligands

The study of reactivity descriptors at the global and local levels provides valuable insights into the electronic properties of transition metal catalysts. This study focuses on the understanding of global and local reactivity descriptors of various palladium and palladium-tin bimetallic complexes using different ligands. A comparative analysis of the electronic contribution of three different ligands such as cyclooctadiene (COD), triphenylphosphine (PPh3), and N-heterocyclic carbene (NHC) in these complexes was undertaken. The changes in the electronic parameters were observed for the corresponding bimetallic complexes containing tin as the second metal partner.

Characterizing grain boundary network length features through a harmonic representation

When modeling and characterizing grain boundary networks (GBNs), there are situations where local descriptors such as triple junction fractions (TJFs) and special boundary fractions are identical between two microstructures, but the performance or properties between the two are distinct. These differences are caused by higher length-scale features that cannot be identified using local structural descriptors. Spectral graph theory (SGT) has been used previously to encode network length features, but did not enable direct quantitative comparisons between the structures that cause property differences. In this paper, we derive a harmonic representation of diffusion on GBNs based on SGT. This method enables direct quantitative comparisons between GBNs for microstructures with different morphologies, and identifies network length features responsible for structural and performance differences, which local descriptors cannot explain. We show an interpretation of the eigenmodes generated by this method that explains long-range structural causes of certain property differences. We apply this method to a large library of microstructures, and identify structural classes through clustering. We show that equal proportioned TJF and J1 dominated microstructures are the most sensitive to network length differences because of boundary configurations, while J2-J3 dominated structures are the least sensitive. This method also identifies network length features that result in anomalous percolation/non-percolation compared to predictions based on local correlations alone.

Early detection of Alzheimer’s disease using squeeze and excitation network with local binary pattern descriptor

Early detection of Alzheimer’s disease using squeeze and excitation network with local binary pattern descriptor

Efficient Crowd Anomaly Detection Using Sparse Feature Tracking and Neural Network

Crowd anomaly detection is crucial in enhancing surveillance and crowd management. This paper proposes an efficient approach that combines spatial and temporal visual descriptors, sparse feature tracking, and neural networks for efficient crowd anomaly detection. The proposed approach utilises diverse local feature extraction methods, including SIFT, FAST, and AKAZE, with a sparse feature tracking technique to ensure accurate and consistent tracking. Delaunay triangulation is employed to represent the spatial distribution of features in an efficient way. Visual descriptors are categorised into individual behaviour descriptors and interactive descriptors to capture the temporal and spatial characteristics of crowd dynamics and behaviour, respectively. Neural networks are then utilised to classify these descriptors and pinpoint anomalies, making use of their strong learning capabilities. A significant component of our study is the assessment of how dimensionality reduction methods, particularly autoencoders and PCA, affect the feature set’s performance. This assessment aims to balance computational efficiency and detection accuracy. Tests conducted on benchmark crowd datasets highlight the effectiveness of our method in identifying anomalies. Our approach offers a nuanced understanding of crowd movement and patterns by emphasising both individual and collective characteristics. The visual and local descriptors facilitate high-level analysis by closely relating to semantic information and crowd behaviour. The analysis observed shows that this approach offers an efficient framework for crowd anomaly detection, contributing to improved crowd management and public safety. The proposed model achieves accuracy of 99.5 %, 96.1%, 99.0% and 88.5% in the UMN scenes 1, 2, and 3 and violence in crowds datasets, respectively.

Towards semantically continuous unpaired image-to-image translation via margin adaptive contrastive learning and wavelet transform

Unpaired image-to-image translation aims to preserve the semantics of the input image while mimicking the style of target domains without paired data. However, existing methods often suffer from semantic distortions if the source and target domains have large mismatched semantics distributions. To address semantic distortions in translation outputs without paired supervision, we propose a Margin Adaptive Contrastive Learning Network (MACL-Net) that drives contrastive learning as a local semantic descriptor while using a pre-trained Vision Transformer (ViT) as a global semantic descriptor to learn domain-invariant features in the translation process. Specifically, we design a novel margin adaptive contrastive loss to enforce intra-class compactness and inter-class discrepancy. Besides, to better retain the semantic structure of the translated image and improve its fidelity, we use Discrete Wavelet Transform (DWT) to supplement the low-frequency and high-frequency information of the input image into the generator, and effectively fuse the feedforward features and inversed frequency information through a novel normalization scheme, Feature-Frequency Transformation Normalization (FFTN). In terms of experimental results, MACL-Net effectively reduces semantic distortions and generates translation outputs that outperform state-of-the-art techniques both quantitatively and qualitatively.

DeepAVP-TPPred: identification of antiviral peptides using transformed image-based localized descriptors and binary tree growth algorithm.

Despite the extensive manufacturing of antiviral drugs and vaccination, viral infections continue to be a major human ailment. Antiviral peptides (AVPs) have emerged as potential candidates in the pursuit of novel antiviral drugs. These peptides show vigorous antiviral activity against a diverse range of viruses by targeting different phases of the viral life cycle. Therefore, the accurate prediction of AVPs is an essential yet challenging task. Lately, many machine learning-based approaches have developed for this purpose; however, their limited capabilities in terms of feature engineering, accuracy, and generalization make these methods restricted. In the present study, we aim to develop an efficient machine learning-based approach for the identification of AVPs, referred to as DeepAVP-TPPred, to address the aforementioned problems. First, we extract two new transformed feature sets using our designed image-based feature extraction algorithms and integrate them with an evolutionary information-based feature. Next, these feature sets were optimized using a novel feature selection approach called binary tree growth Algorithm. Finally, the optimal feature space from the training dataset was fed to the deep neural network to build the final classification model. The proposed model DeepAVP-TPPred was tested using stringent 5-fold cross-validation and two independent dataset testing methods, which achieved the maximum performance and showed enhanced efficiency over existing predictors in terms of both accuracy and generalization capabilities. https://github.com/MateeullahKhan/DeepAVP-TPPred.

AUD-Net: A Unified Deep Detector for Multiple Hyperspectral Image Anomaly Detection via Relation and Few-Shot Learning.

This article addresses the problem of the building an out-of-the-box deep detector, motivated by the need to perform anomaly detection across multiple hyperspectral images (HSIs) without repeated training. To solve this challenging task, we propose a unified detector [anomaly detection network (AUD-Net)] inspired by few-shot learning. The crucial issues solved by AUD-Net include: how to improve the generalization of the model on various HSIs that contain different categories of land cover; and how to unify the different spectral sizes between HSIs. To achieve this, we first build a series of subtasks to classify the relations between the center and its surroundings in the dual window. Through relation learning, AUD-Net can be more easily generalized to unseen HSIs, as the relations of the pixel pairs are shared among different HSIs. Secondly, to handle different HSIs with various spectral sizes, we propose a pooling layer based on the vector of local aggregated descriptors, which maps the variable-sized features to the same space and acquires the fixed-sized relation embeddings. To determine whether the center of the dual window is an anomaly, we build a memory model by the transformer, which integrates the contextual relation embeddings in the dual window and estimates the relation embeddings of the center. By computing the feature difference between the estimated relation embeddings of the centers and the corresponding real ones, the centers with large differences will be detected as anomalies, as they are more difficult to be estimated by the corresponding surroundings. Extensive experiments on both the simulation dataset and 13 real HSIs demonstrate that this proposed AUD-Net has strong generalization for various HSIs and achieves significant advantages over the specific-trained detectors for each HSI.

Exploring the efficacy of Congo Red dye as a corrosion inhibitor for aluminum in HCl solution: An interdisciplinary study with RSM modeling and theoretical simulations

This study investigates Congo Red Textile Dye (CRD) as a corrosion inhibitor for aluminum in a 1.0 mol/L hydrochloric acid solution. Utilizing a comprehensive suite of analytical techniques, including gravimetric analysis, scanning electron microscopy (SEM), ultraviolet–visible spectrophotometry (UV–Vis), Electrochemical Impedance Spectroscopy (EIS), and Potentiodynamic Polarization curves (PDP), we assessed CRD’s adsorption mechanism and its corrosion inhibition effectiveness. Significant corrosion mitigation was observed, with the efficiency of inhibition EI (%) increasing alongside CRD concentration, achieving a maximum efficiency of 87.5 %. This enhancement in EI (%) decreases with rising temperatures, assessed across a range from 298 to 323 K. Response surface methodology (RSM) and central composite design (CCD) were employed for accurate corrosion rates (Vcorr) and EI (%) prediction. Additionally, theoretical analysis was performed using global and local reactivity descriptors along with molecular dynamics (MD) simulations. Theoretical results confirmed the widespread presence of nucleophilic and electrophilic sites, along with a strong affinity for the Al surface, suggesting CRD’s potential for enhancing corrosion resistance. This study proposes a potential pathway for the valorization of Congo Red dye, utilizing concentrations within non-toxic thresholds, thereby aligning with environmental safety and industrial application considerations.

R‐Vine Copulas for Data‐Driven Quantification of Descriptor Relationships in Porous Materials

AbstractLocal variations in the 3D microstructure can control the macroscopic behavior of heterogeneous porous materials. For example, the permittivity through porous sheets or membranes is governed by local high‐volume pathways or bottlenecks. Due to local variations, unfeasibly large amounts of microstructure data may be needed to reliably predict such material properties directly from image data. Here it is demonstrated that a vine copula approach provides parametric models for local microstructure descriptors that compactly capture the 3D microstructure including its local variations and efficiently probe it with respect to selected, measurable properties. In contrast to common methods of complexity reduction, the proposed approach creates parametric models for the multivariate probability distribution of high‐dimensional descriptor vectors that inherently contain the complex, nonlinear dependencies between these descriptors. Therein, material properties are offered in physically motivated distributions of microstructure descriptors rather than as normally distributed data. Applied to porous fiber networks (paper) before and after unidirectional compression, it is shown that the copula‐based models reveal material‐characteristic relationships between two or more microstructure descriptors. In this way, the presented modeling approach can provide deeper insight into the microscopic origin of effective macroscopic properties of heterogeneous porous materials.

LGD: A fast place recognition method based on the fusion of local and global descriptors

Place recognition, which is also known as loop detection, has been one of the main problems in the field of robot navigation, and it is crucial in realizing high-performance simultaneous localization and mapping (SLAM). Most of the existing methods directly construct local or global descriptors with point clouds, ignoring the offset of different visits in the same place. To overcome the current limitations, this study emphasizes the importance of point cloud features in improving the environment recognition precision and proposes an innovative framework that combines local features that are spatially invariant and prominent descriptive global features as a representation of a laser scanner frame. The feature center of the laser point cloud is obtained by computing local feature points with spatial invariance, which improves the offset between the original point cloud and the feature center. Furthermore, a coarse-to-fine hierarchical recognition strategy is developed to improve the efficiency of place recognition. An evaluation with different offsets and synthesis is conducted on the publicly available KITTI and self-developed CHDloop datasets. The experimental results show that the proposed method can improve time efficiency by more than 18% compared to the SC and ISC, and there are also significant improvements in the recall rate and accuracy in slight lane-change scenarios. Moreover, the proposed method can obtain rich lane-change loops in moderate and large lane-change scenarios where the SC and ISC fail to obtain effective loops. The proposed method can be used as a lightweight and interpretable approach for place recognition, which not only can be quickly deployed in any SLAM framework but can also efficiently handle more complex place recognition issues in urban environments.

Comprehensive study of Fenton reaction efficiency on textile wastewater treatment from dye solution to real effluent with emphasis on Fukui function analysis

This study investigated the continuous degradation monitoring of three reactive dyes, reactive yellow 176 (RY), reactive Blue 4 (RB) and reactive red 293 (RR), both in separate solutions and in a mixture, along with their corresponding dye bath and industrial dyeing effluent, using Fenton reaction. A kinetic study was conducted to compare the degradation efficiency of the studied solutions. This work provides important yield of dye degradation, where the results showed that RB, RY, and RR had 96.64 %, 92.47 %, and 73.27 % color removal, respectively, within a two-hour reaction time. The pseudo-second-order model fit well to describe the degradation of RR and RY, while the zero-pseudo-order model provided a better fit for RB. The dye mixture exhibited 57 % color removal, whereas the dyeing bath and real effluent showed 41 % and 36 % removal, respectively, over a two-hour reaction time. Moreover, significant reductions in chemical oxygen demand (COD) and biological oxygen demand over 5 days (BOD5) were observed, with the real effluent demonstrating a 73.91 % COD reduction and an 86.66 % reduction in BOD5. The COD and BOD5 reductions for the dye bath were 67.53 % and 95 %, respectively. Additionally, COD and BOD5 reductions of 72.96 % and 96.66 %, respectively, were observed for the dye bath. DFT calculations were employed to elucidate the regioselectivity of radical oxidation of the three reactive dyes by Fenton's reagent, providing insights into global and local reactivity descriptors. Toxicity studies further underscored the efficacy of the Fenton reaction in wastewater treatment. Additionally, UV–visible spectral analysis before and after 12 h of Fenton reaction revealed total discolouration and a reduction in UV and visible peaks across all reactions, indicating comprehensive dye degradation and reduction.

Study anti-viral drugs for their efficiency against multiple SARS CoV-2 drug targets within molecular docking, molecular quantum similarity, and chemical reactivity indices frameworks

The study focused on drug discovery for COVID-19, emphasizing the challenges posed by the pandemic and the importance of understanding the virus’s biology. The research utilized molecular docking and quantum similarity analyses to explore potential ligands for SARS-CoV-2 RNA-dependent RNA polymerase. Docking Results Docking outcomes for various ligands, including Oseltamivir, Prochloraz, Valacyclovir, Baricitinib, Molnupiravir, Penciclovir, Famciclovir, Lamivudine, and Nitazoxanide, were presented. Interactions between ligands and specific residues in the RNA-dependent RNA polymerase were analyzed. Reactivity Descriptors Global parameters, such as electronic chemical potential, chemical hardness, global softness, and global electrophilicity, were computed for the ligands. For the local reactivity descriptors, the Fukui Functions were used. Fukui functions, representing electrophilic and nucleophilic sites, were calculated for selected ligands (Valacyclovir and Penciclovir). Nucleophilic character assignments for specific molecular regions were discussed, providing insights into potential charge-donating interactions. Results and Discussion Challenges in COVID-19 drug discovery, such as virus mutability, rapid evolution, and resource limitations, were summarized. Progress in vaccine development and the need for ongoing research to address variants and breakthrough cases were emphasized. Overlap Operator Analysis Higher MQSM between Lamivudine and Molnupiravir (0.5742) indicates structural and electronic similarity. Lowest MQSM between Oseltamivir and Prochloraz (0.2233) implies structural dissimilarity. Coulomb Operator Analysis Higher MQSM between Lamivudine and Molnupiravir (0.9178) suggests both structural and electronic similarity. Lowest MQSM between Baricitinib and Famciclovir (0.6001) indicates greater structural diversity. Measurements above 0.5 in Table 3 suggest electronic similarity, emphasizing the electronic aspects in molecular analysis. In this sense, it study employed a multi-faceted approach combining molecular docking, quantum similarity analyses, and chemical reactivity assessments to explore potential drug candidates for COVID-19. The findings provide valuable insights into ligand interactions, reactivity patterns, and the challenges associated with drug discovery in the context of the global pandemic.

ELMP-Net: The successive application of a randomized local transform for texture classification

This work proposes a method for texture classification based on the successive application of a local transform presented here for the first time. Such transform comprises two steps: (1) We built a two-layer mapping relating each pixel with its neighborhood, with the weights in the first layer randomly assigned; (2) We use the parameters learned by such mapping to transform the original image. Finally, we extract local descriptors at different stages of the successive application of this transform to compose the texture descriptors. The performance of our method is verified in the classification of benchmark texture databases and compared with state-of-the-art approaches. We also present an application for plant species identification. The results confirm our expectation that a model that is not based on the classical learning-based approach can still be competitive in texture analysis.

Automatic oral cancer detection and classification using modified local texture descriptor and machine learning algorithms

Automatic oral cancer detection and classification using modified local texture descriptor and machine learning algorithms

Feature Engineering Versus Deep Learning for Scene Recognition: A Brief Survey

Scene recognition is an important computer vision task that has evolved from the study of the biological visual system. Its applications range from video surveillance, autopilot systems, to robotics. The early works were based on feature engineering that involved the computation and aggregation of global and local image descriptors. Several popular image features such as SIFT, SURF, HOG, ORB, LBP, KAZE, etc. have been proposed and applied to the task with successful results. Features can be either computed from the entire image on a global scale, or extracted from local sub-regions and aggregated across the image. Suitable classifier models are deployed that learn to classify these features. This review paper analyzes several of these handcrafted features that have been applied to the scene recognition task over the past decades, and tracks the transition from the traditional feature engineering to deep learning which forms the current state of the art in computer vision. Deep learning is now deemed to have overtaken feature engineering in several computer vision applications. Deep convolutional neural networks and vision transformers are the current state of the art for object recognition. However, scenes from urban landscapes are bound to contain similar objects posing a challenge to deep learning solutions for scene recognition. In our study, a critical analysis of feature engineering and deep learning methodologies for scene recognition is provided, and results on benchmark scene datasets are presented, concluding with a discussion on challenges and possible solutions that may facilitate more accurate scene recognition.

Beyond Local Structures in Critical Supercooled Water through Unsupervised Learning.

The presence of a second critical point in water has been a topic of intense investigation for the last few decades. The molecular origins underlying this phenomenon are typically rationalized in terms of the competition between local high-density (HD) and low-density (LD) structures. Their identification often requires designing parameters that are subject to human intervention. Herein, we use unsupervised learning to discover structures in atomistic simulations of water close to the liquid-liquid critical point (LLCP). Encoding the information on the environment using local descriptors, we do not find evidence for two distinct thermodynamic structures. In contrast, when we deploy nonlocal descriptors that probe instead heterogeneities on the nanometer length scale, this leads to the emergence of LD and HD domains rationalizing the microscopic origins of the density fluctuations close to criticality.

Discriminative Suprasphere Embedding for Fine-Grained Visual Categorization.

Despite the great success of the existing work in fine-grained visual categorization (FGVC), there are still several unsolved challenges, e.g., poor interpretation and vagueness contribution. To circumvent this drawback, motivated by the hypersphere embedding method, we propose a discriminative suprasphere embedding (DSE) framework, which can provide intuitive geometric interpretation and effectively extract discriminative features. Specifically, DSE consists of three modules. The first module is a suprasphere embedding (SE) block, which learns discriminative information by emphasizing weight and phase. The second module is a phase activation map (PAM) used to analyze the contribution of local descriptors to the suprasphere feature representation, which uniformly highlights the object region and exhibits remarkable object localization capability. The last module is a class contribution map (CCM), which quantitatively analyzes the network classification decision and provides insight into the domain knowledge about classified objects. Comprehensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed method in comparison with state-of-the-art methods.