Histogram Of Oriented Gradients Research Articles

Braille Character Recognition with Histogram of Oriented Gradients (HOG) and SVM-Based Image Processing

Braille Character Recognition with Histogram of Oriented Gradients (HOG) and SVM-Based Image Processing

TriCAFFNet: A Tri-Cross-Attention Transformer with a Multi-Feature Fusion Network for Facial Expression Recognition.

In recent years, significant progress has been made in facial expression recognition methods. However, tasks related to facial expression recognition in real environments still require further research. This paper proposes a tri-cross-attention transformer with a multi-feature fusion network (TriCAFFNet) to improve facial expression recognition performance under challenging conditions. By combining LBP (Local Binary Pattern) features, HOG (Histogram of Oriented Gradients) features, landmark features, and CNN (convolutional neural network) features from facial images, the model is provided with a rich input to improve its ability to discern subtle differences between images. Additionally, tri-cross-attention blocks are designed to facilitate information exchange between different features, enabling mutual guidance among different features to capture salient attention. Extensive experiments on several widely used datasets show that our TriCAFFNet achieves the SOTA performance on RAF-DB with 92.17%, AffectNet (7 cls) with 67.40%, and AffectNet (8 cls) with 63.49%, respectively.

The investigation of traditional models and machine learning models in dynamic facial expression recognition

In everyday life, dynamic facial expressions are merely continuous human responses to external events. However, in human-computer interaction, rapidly recognizing changes in facial expressions from video streams is a relatively complex process. This complexity renders Dynamic Facial Expression Recognition (DFER) a critical research task in the domains of computer vision and image processing. This paper analyses the correlations and contrasts between static and dynamic facial expression research, highlighting key issues in the study of dynamic facial expressions, such as dynamic feature extraction and frame extraction. After that, it enumerates significant algorithms in both traditional models and deep learning models, providing an analysis of the advantages and disadvantages of these two major approaches. At the same time, it investigates the reasons behind the transition of research models for DFER from traditional methods to deep learning approaches. The paper focuses on two notable models from each approach: Histogram of Oriented Gradient (HOG) for processing raw images, Support Vector Machine (SVM) for data classification in traditional models. Convolutional Neural Network (CNN) for spatial feature extraction and Long Short-Term Memory (LSTM) for temporal feature extraction in deep learning models. These models are discussed in detail concerning their strengths and weaknesses, operational processes, and performance outcomes. In the concluding section, the author summarizes the main factors influencing research in this field and the current challenges encountered. By focusing on future research directions, the paper also presents a review of recent methodologies and offers insightful research directions for further investigation.

Pyram: a robust and attack-resistant perceptual image hashing using pyramid histogram of gradients

Pyram: a robust and attack-resistant perceptual image hashing using pyramid histogram of gradients

Personalized Drone Interaction : Adaptive Hand Gesture Control with Facial Authentication

This paper presents a novel system for personalized drone interaction, integrating adaptive hand gesture control with facial authentication. Utilizing the DJI Tello drone equipped with a 5 MP camera, the system employs advanced computer vision and machine learning techniques to ensure secure and intuitive control. Facial recognition using the Histogram of Oriented Gradients (HOG) method and FaceNet model verifies user identity, while MediaPipe and a custom convolutional neural network (CNN) facilitate accurate hand gesture recognition. The system’s real-time processing capabilities ensure seamless and responsive user interaction. Experimental results demonstrate the system’s robustness and accuracy in various scenarios, highlighting its potential for diverse applications such as security, entertainment, and personal assistance.

An optimized method for mulberry silkworm, Bombyx mori (Bombycidae:Lepidoptera) sex classification using TLBPSGA-RFEXGBoost.

Silkworm seed production is vital for silk farming, requiring precise breeding techniques to optimize yields. In silkworm seed production, precise sex classification is crucial for optimizing breeding and boosting silk yields. A non-destructive approach for sex classification addresses these challenges, offering an efficient alternative that enhances both yield and environmental responsibility. Southern India is a hub for mulberry silk and cocoon farming, with the high-yielding double-hybrid varieties FC1 (foundation cross 1) and FC2 (foundation cross 2) being popular. Traditional methods of silkworm pupae sex classification involve manual sorting by experts, necessitating the cutting of cocoons - a practice with a high risk of damaging the cocoon and affecting yield. To address this issue, this study introduces an accelerated histogram of oriented gradients (HOG) feature extraction technique that is enhanced by block-level dimensionality reduction. This non-destructive method allows for efficient and accurate silkworm pupae classification. The modified HOG features are then fused with weight features and processed through a machine learning classification model that incorporates recursive feature elimination (RFE). Performance evaluation shows that an RFE-hybridized XGBoost model attained the highest classification accuracy, achieving 97.2% for FC1 and 97.1% for FC2. The model further optimized with a novel teaching learning-based population selection genetic algorithm (TLBPSGA) achieved a remarkable accuracy of 98.5% for FC1 and 98.2% for FC2. These findings have far-reaching implications for improving both the ecological sustainability and economic efficiency of silkworm seed production.

Quantifying urban air quality through multispectral satellite imagery and Google earth Engine

The escalating concerns surrounding urban air pollution's impact on both the environment and human health have prompted increased attention from researchers, policymakers, and citizens alike. As such, this study addresses growing concerns about urban air pollution's impact on the environment and human health, emphasizing the need for early, high-resolution PM2.5 pollutant measurements. Utilizing Google Earth Engine (GEE) machine learning algorithms, our study evaluates six models over four years in Tehran and Tabriz. Inputs include satellite imagery, meteorological data, and pollutant measurements from air quality stations. Four models—Histogram Gradient Boosting, Random Forest, Extreme Gradient Boosting, and Ada Boosted Decision Trees—outperform Support Vector Machine and Linear Regression. The selected model, a combination of decision tree algorithms and Ada Boost, achieves a notable correlation coefficient of 79.8% and an RMSE of 0.271 g/m3. This superior performance enables the generation of high-resolution (30-m) PM2.5 estimates for the two cities. The study's comprehensive approach, involving various data sources and advanced machine learning techniques, contributes a valuable method for accurate PM2.5 assessment. The findings hold significance for urban air quality management and provide a potential framework for generating detailed PM2.5 datasets based on Landsat images.

Research on the classification of complex noise-mixed microseismic events based on machine vision

Event classification is important for accurately monitoring and warning against rockburst hazards using microseismic technology. Here, we propose an automatic classification method for microseismic events based on machine vision. The method uses Histogram of Oriented Gradient (HOG) integrated with Support Vector Machine (SVM) as the core model (HOG-SVM, HSVM) to classify microseismic events. First, the method uses as input spectrograms generated from microseismic event signals recorded in the field. Next, the HOG method is used to accurately extract the spectral feature information of the useful signals of microseismic events under the interference of noisy signal. Finally, the extracted feature data is used to train SVM, after the training is completed, the SVM is used to classify the microseismic events. The performance of the method for categorizing microseismic events was tested using multiple independent test sets built from data monitored in the field of a mine in Shandong Province. The results show that the method can effectively extract the spectral feature information of useful signals of microseismic events contaminated with noise, with good classification accuracy and robustness to noise. It classifies microseismic events with high accuracy and efficiency compared to well-performing classification methods based on seismic source parameters and typical depth models. The method can provide technical support for the effective classification of microseismic events in complex construction sites, especially in noisy deep underground construction environments.

Advancements in object detection: From machine learning to deep learning paradigms

The evolution of object detection from traditional machine learning approaches to advanced deep learning techniques marks a significant milestone in the field of computer vision. Initially, object detection relied on algorithms such as Support Vector Machines (SVMs) and decision trees, leveraging handcrafted features like Histogram of Oriented Gradients (HOG) and Scale-Invariant Feature Transform (SIFT) for classification and recognition tasks. However, these methods exhibited limitations in scalability and adaptability to complex environments. The breakthrough came with the adoption of Convolutional Neural Networks (CNNs), which transformed the landscape by automating feature extraction, thereby enhancing detection accuracy and efficiency. Subsequent innovations in network architectures, such as R-CNN, YOLO, and SSD, have continually refined object detection capabilities, optimizing both speed and precision. This paper examines the progression of object detection technologies, focusing on the impact of deep learning models and the optimization of network structures. It also delves into the quantitative analysis of model performance, highlighting the role of data augmentation and advanced training techniques in overcoming real-world detection challenges. Through this exploration, the paper aims to provide comprehensive insights into the current state and future directions of object detection techniques.

MmWave-RM: A Respiration Monitoring and Pattern Classification System Based on mmWave Radar.

Breathing is one of the body's most basic functions and abnormal breathing can indicate underlying cardiopulmonary problems. Monitoring respiratory abnormalities can help with early detection and reduce the risk of cardiopulmonary diseases. In this study, a 77 GHz frequency-modulated continuous wave (FMCW) millimetre-wave (mmWave) radar was used to detect different types of respiratory signals from the human body in a non-contact manner for respiratory monitoring (RM). To solve the problem of noise interference in the daily environment on the recognition of different breathing patterns, the system utilised breathing signals captured by the millimetre-wave radar. Firstly, we filtered out most of the static noise using a signal superposition method and designed an elliptical filter to obtain a more accurate image of the breathing waveforms between 0.1 Hz and 0.5 Hz. Secondly, combined with the histogram of oriented gradient (HOG) feature extraction algorithm, K-nearest neighbours (KNN), convolutional neural network (CNN), and HOG support vector machine (G-SVM) were used to classify four breathing modes, namely, normal breathing, slow and deep breathing, quick breathing, and meningitic breathing. The overall accuracy reached up to 94.75%. Therefore, this study effectively supports daily medical monitoring.

Analysis of banana plant health using machine learning techniques

The Indian economy is greatly influenced by the Banana Industry, necessitating advancements in agricultural farming. Recent research emphasizes the imperative nature of addressing diseases that impact Banana Plants, with a particular focus on early detection to safeguard production. The urgency of early identification is underscored by the fact that diseases predominantly affect banana plant leaves. Automated systems that integrate machine learning and deep learning algorithms have proven to be effective in predicting diseases. This manuscript examines the prediction and detection of diseases in banana leaves, exploring various diseases, machine learning algorithms, and methodologies. The study makes a contribution by proposing two approaches for improved performance and suggesting future research directions. In summary, the objective is to advance understanding and stimulate progress in the prediction and detection of diseases in banana leaves. The need for enhanced disease identification processes is highlighted by the results of the survey. Existing models face a challenge due to their lack of rotation and scale invariance. While algorithms such as random forest and decision trees are less affected, initially convolutional neural networks (CNNs) is considered for disease prediction. Though the Convolutional Neural Network models demonstrated impressive accuracy in many research but it lacks in invariance to scale and rotation. Moreover, it is observed that due its inherent design it cannot be combined with feature extraction methods to identify the banana leaf diseases. Due to this reason two alternative models that combine ANN with scale-invariant Feature transform (SIFT) model or histogram of oriented gradients (HOG) combined with local binary patterns (LBP) model are suggested. The first model ANN with SIFT identify the disease by using the activation functions to process the features extracted by the SIFT by distinguishing the complex patterns. The second integrate the combined features of HOG and LBP to identify the disease thus by representing the local pattern and gradients in an image. This paves a way for the ANN to learn and identify the banana leaf disease. Moving forward, exploring datasets in video formats for disease detection in banana leaves through tailored machine learning algorithms presents a promising avenue for research.

Classification of cotton crop disease using hybrid model and MDFC feature extraction method

AbstractA novel Modified Deep Fuzzy Clustering (MDFC) based classification model involves four major phases. They are preprocessing, segmentation, feature extraction and finally, detection and classification phase. To reduce noise and smooth the edges of the input image of the cotton crop, bilateral filtering is first used as a preprocessing approach. Next, a modified deep fuzzy clustering is suggested for the segmentation procedure that creates a collection of segments from the preprocessed image. The segmented image is then processed to extract relevant characteristics by using an enhanced Pyramid of Histogram Orientation Gradient (PHOG), Local Directional Ternary Pattern (LDTP), and statistical‐based features. In order to detect and classify cotton crop diseases more effectively, this paper proposes a hybrid system. Here, the features are put through a detection phase, after which the extracted features are trained in the Bidirectional Gated Recurrent Unit (Bi‐GRU) model to determine whether or not the cotton crop is infected. Once it is detected to be diseased, the type of disease is classified via an improved Recurrent Neural Network (RNN). In terms of several performance metrics, the proposed model is validated in comparison with the traditional approaches. The MDFC‐based classification model outperforms existing models with a specificity of 0.9687 at a learning rate of 90. In contrast, other models achieve lower specificities: Bi‐GRU (0.8436), RNN (0.8359), CNN (0.8654), LSTM (0.8769), SVM (0.7983), VGG16 (0.8619), DCNN (0.8725), BI‐RNN + BI‐LSTM (0.7869), and NN + CNN (0.85478).

Machine learning approach to predict the mechanical properties of cementitious materials containing carbon nanotubes

This research explores the use of machine learning to predict the mechanical properties of cementitious materials enhanced with carbon nanotubes (CNTs). Specifically, the study focuses on estimating the elastic modulus and flexural strength of these novel composite materials, with the potential to significantly impact the construction industry. Seven key variables were analyzed including water-to-cement ratio, sand-to-cement ratio, curing age, CNT aspect ratio, CNT content, surfactant-to-CNT ratio, and sonication time. Artificial neural network, support vector regression, and histogram gradient boosting, were used to predict these mechanical properties. Furthermore, a user-friendly formula was extracted from the neural network model. Each model performance was evaluated, revealing the neural network to be the most effective for predicting the elastic modulus. However, the histogram gradient boosting model outperformed all others in predicting flexural strength. These findings highlight the effectiveness of the employed techniques, in accurately predicting the properties of CNT-enhanced cementitious materials. Additionally, extracting formulas from the neural network provides valuable insights into the interplay between input parameters and mechanical properties.

Evaluating Diagnostic Thresholds for Pneumonia Severity Using HOG Features and Deep Learning Models

Pneumonia severity diagnosis is vital for effective and efficient patient treatment and management. This study evaluates the efficacy of different diagnostic thresholds for pneumonia severity using Histogram of Oriented Gradients (HOG) features and deep learning models on chest X-ray images. Utilizing the Kaggle chest X-ray dataset, HOG feature extraction was applied, followed by Pearson correlation to compare a randomly selected X-ray with pneumonia images. Three diagnostic thresholds were used for severity diagnosis. The results demonstrated that all thresholds performed well in detecting moderate cases, with Threshold1 and Threshold2 both achieving an accuracy of 89% and an F1-score of 0.94. Threshold3 had an accuracy of 66% and F1-scores of 0.62 and 0.94 in identifying mild and moderate cases, respectively. The evaluation metrics included accuracy, precision, recall, and F1-score. These findings suggest that careful selection of diagnostic thresholds can significantly impact the accuracy and reliability of pneumonia severity diagnosis using deep learning models, with potential applications in clinical settings.

Smart Face Attendance System using Facial Recognition

The SmartFace Attendance system using facial recognition represents a modern solution to automate attendance tracking processes in educational institutions and organizations. Leveraging advanced facial recognition technology, it offers accurate and efficient attendance management while addressing privacy concerns and ensuring user acceptance. The system utilizes state-of-the-art algorithms such as Convolutional Neural Networks (CNN), Histogram of Oriented Gradients (HOG), and Support Vector Machines (SVM) to detect and recognize faces in real-time captured images. By providing touchless operation and seamless integration with existing infrastructure, SmartFace Attendance system offers convenience and scalability for users across diverse environments. With robust security measures, adherence to ethical considerations, and compliance with legal regulations, it is poised to revolutionize attendance tracking practices, enhancing operational efficiency and improving user experiences in educational and organizational settings. Keywords—Online Attendance System, Energy Efficiency, Facial Recognition, Support Vector Machine(SVM), Decision Tree, Histogram of Oriented Gradients(HOG), Convolutional Neural Network(CNN), Database Management, Model Train- ing.

An Adversarial Example Method Based on Dropping Information to Improve Attack Capability

At present, deep neural network has been widely used in many research fields. However, with the in-depth research on artificial intelligence research, it is found that artificial intelligence technology based on deep neural networks bringsconvenience coming with potential security risks. For example, an attacker may misguide the image classification model to output a wrong result with high confidence by adding slight perturbations to a clean image via the adversarial example method. Compared with the previous methods of adding additional information to the images to generate adversarial examples, Ranjie Duan et al. proposed the AdvDrop algorithm. In this algorithm, adversarial examples are generated by deleting the existing information of the images, which is realized by adjusting the quantization step. However, in the quantization process, the AdvDrop algorithm does not consider the different effects of different gradient values of the quantization table on the adversarial effect. In this regard, AdvDrop+ is proposed, that is, in each iteration, the quantization tables are updated according to the gradient numerical values scaled with a factor. To find the proper scaling factor, we find the gradient value of the highest frequency in the gradient histogram and compute its logarithm and the final result is the scaling factor. The experiments show that AdvDrop+ has better attack performance than AdvDrop under the setting of target attack with nearly the same image distortion. At the same time, AdvDrop+ retains the characteristic of AdvDrop, which can drop information.

Unveiling Visual Treasures: Harnessing Deep Learning for Content-Based Image Retrieval

Objective: An essential aspect of computer vision is content-based image retrieval (CBIR), which enables users to search for images based on their visual content instead of created annotations. Advances in technology have resulted in a significant rise in the complexity of multimedia content and the emergence of new research fields centered on similar multimedia material retrieval. The efficacy of retrieval is impacted by the limits of the present CBIR systems, which result from overlooked algorithms and computing restrictions. Methods: This research introduces a novel approach employing the Siamese Edge Attention Layered Convonet (SEAL Convonet) for Image Retrieval. We utilize the CBIR image dataset through Gaussian smoothing to enhance image quality for data preprocessing and the Canny Edge Detector (CED) for edge detection, following pre-processing. The Histogram of Oriented Gradients (HOG) is used for feature extraction to extract complex textures and patterns from the images. Findings: This approach is implemented and tested through simulations as well as the results indicate a substantial positive deviation in the performance and retrieval of the images compared to existing methods. The performance metrics are accuracy (97 %), precision (94 %), recall (91 %), F1-Score (97 %), False Positive Rate (FNR) (0.0013), Matthew's correlation coefficient (MCC) (0.85), and False Negative Rate (FPR) (0.0036) show the measurements of this proposed model. Application: The state of the art in this work is researching the influence of optimizers on the accuracy process, as indicated by the findings. Keywords: CBIR, Gaussian smoothing, Canny Edge Detector, Histogram of oriented gradients (HOG), Siamese Edge Attention Layered convonet (SEAL Convonet), Database

Beyond local patches: Preserving global–local interactions by enhancing self-attention via 3D point cloud tokenization

Transformer-based architectures have recently shown impressive performance on various point cloud understanding tasks such as 3D object shape classification and semantic segmentation. Particularly, this can be attributed to their self-attention mechanism, which has the ability to capture long-range dependencies. However, current methods have constrained it to operate in local patches due to its quadratic memory constraints. This hinders their generalization ability and scaling capacity due to the loss of non-locality in early layers. To tackle this issue, we propose a window-based transformer architecture that captures long-range dependencies while aggregating information in the local patches. We do this by interacting each window with a set of global point cloud tokens — a representative subset of the entire scene — and augmenting the local geometry through a 3D Histogram of Oriented Gradients (HOG) descriptor. Through a series of experiments on segmentation and classification tasks, we show that our model exceeds the state-of-the-art on S3DIS semantic segmentation (+1.67% mIoU), ShapeNetPart part segmentation (+1.03% instance mIoU) and performs competitively on ScanObjectNN 3D object classification.11The code and trained models shall be made publicly available.

Predictive ultrafast laser-induced formation of MoOx using machine learning algorithms

This research introduces an innovative methodology leveraging machine learning algorithms to predict the outcomes of experimental and numerical tests with femtosecond (fs) laser pulses on 500-nm-thick molybdenum films. The machine learning process encompasses several phases, including data acquisition, pre-processing, and prediction. This framework effectively simulates the interaction between fs laser pulses and the surface of molybdenum thin films, enabling precise control over the creation of MoO x phases. The exceptional precision of fs laser pulses in generating molybdenum oxides at localized micrometer scales is a significant advantage. In this study, we explored and evaluated 13 different machine learning methods for predicting oxide formation results. Our numerical results indicate that the extra trees (ET) and gradient boosting (GB) algorithms provide the best performance in terms of mean squared error, mean absolute error, and R-squared values: 48.44, 3.72, and 1.0 for ET and 32.25, 3.72, and 1.0 for GB. Conversely, support vector regression (SVR) and histogram gradient boosting (HGB) performed the worst, with SVR yielding values of 712.48, 15.27, and 0.163 and HGB yielding values of 434.29, 16.37, and 0.548. One of the most significant aspects of this research is that training these algorithms did not require hyperparameter optimization, and the training and validation process only needed 54 experimental samples. To validate this, we used a technique known as leave-one-out cross-validation, which is a robust validation method when the available data is limited. With this research, we aim to demonstrate the capability of machine learning algorithms in applications where data is limited due to the high cost of real experimentation, as is often the case in the field of optics.

Automated Early Detection of Plant Diseases a Machine Learning Approach

This study introduces an innovative strategy for the early detection of plant diseases leveraging machine learning algorithms, a crucial step towards bolstering global food security. Despite the importance of early disease detection for mitigating crop losses, inadequate infrastructure often hinders swift and accurate identification. This paper addresses these challenges by utilizing the Random Forest algorithm to distinguish between healthy and diseased plant leaves using a specially curated dataset. Our proposed method involves comprehensive phases of dataset creation, feature extraction, classifier training, and subsequent classification. For the extraction of image features, the Histogram of Oriented Gradient (HOG) technique is utilized, offering a robust method for image analysis. Embracing the capabilities of publicly accessible, large-scale datasets, our method provides a scalable solution to plant disease detection. The empirical results demonstrate promising levels of accuracy in disease monitoring, presenting transformative potential for disease management practices in agriculture. Particularly in resourceconstrained settings, our machine learning approach paves the way for efficient and effective plant disease detection, carrying significant implications for future crop protection strategies.