Histogram Of Oriented Gradients Research Articles

Research on the Contrast Enhancement Algorithm for X-ray Images of BiFeO3 Material Experiment

High-Temperature Materials Science Experiment Cabinet on the Chinese Space Station is mainly used to carry out experimental research related to high-temperature materials science in microgravity. It is equipped with an X-ray transmission imaging module, which is applied to realize transmission imaging of material samples under microgravity. However, the X-ray light source is far away from the experimental samples, and the images obtained by the module are blurred, so it is impossible to accurately observe the morphological changes during the melting and solidification processes of high-temperature materials. To address this issue, this paper proposed a contrast enhancement algorithm specifically designed for X-ray images obtained during the experiments of high-temperature materials. The algorithm is based on gradient three-interval equalization, and it is combined with a Gaussian function to expand the gradient histogram. Meanwhile, the local gray level information within each gradient interval is corrected by designing an improved adaptive contrast enhancement algorithm. By comparing with Adaptive Histogram Equalization (AHE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithms, EnlightenGAN, and Wavelet algorithms, the Contrast Enhancement based contrast-changed Image Quality measure (CEIQ) and Measure of Enhancement (EME) are improved by an average of 56.97%, 10.58%, and Measure of Entropy (MOE) are improved by an average of 7.74 times. The experimental results show that the algorithm makes the image details clearer on the basis of image contrast enhancement. The solid-liquid interface in the image can be clearly observed after contrast enhancement. The algorithm provides strong support for the study of interface dynamics during the experiment process of high-temperature materials.

Ensemble learning model for concrete delamination depth detection using impact echo

Delamination in concrete structures typically arises from the expansion of steel bar corrosion and the separation of the bonding layer. The presence of these delamination defects leads to a reduction in overall structural integrity, safety, and longevity. However, the delamination depth localization remains challenging. To address this issue, this paper introduces a predictive approach that combines time-frequency features extracted from vibration signals with ensemble learning models. The innovation presented in this paper can be summarized in two key aspects: (1) Signal time-frequency spectrograms are transformed into image features using the Histogram of Oriented Gradients (HOG) method, which serves as input attributes. The utilization of ensemble learning models facilitates both rapid and precise depth estimation of delamination signals, especially those with shallow defects. (2) By analyzing the time-frequency spectrogram of the vibration signals, a double exponential model is established between the depth-to-thickness ratio of delamination and the pixel matrix Eulerian distance. This may provide a new perspective for the depth estimation of delamination defects whose corresponding main frequencies are difficult to locate due to the influence of geometry and boundary effects. Laboratory experiments were conducted on concrete slab with simulated delamination defects at different depths to confirm the proposed method's effectiveness.

Ultra-deep channel sand body target recognition method based on improved deep learning under UAV cluster

Abstract River sand bodies have complex and changeable characteristics and distribution. In order to improve the accuracy and efficiency of target recognition, this study proposes a target recognition method of ultra-deep river sand bodies with improved deep learning under unmanned aerial vehicle (UAV) cluster. By constructing the cooperative target allocation model of UAV group, it is ensured that the targets of ultra-deep and large-area river sand bodies are collected. The gradient histogram is used to extract the image characteristics of ultra-deep river sand body and enhance the target image of ultra-deep river sand body. Bi-directional long short-term memory (Bi-LSTM) network model is constructed by introducing bidirectional recurrent neural network (RNN) to improve deep learning. Bi-LSTM neural network is used to construct the target recognition model of ultra-deep river sand body and complete the target recognition. The experimental results show that this method can extract the target edge completely and recognize the image edge accurately, and the average recognition accuracy under different ambiguities is higher than 95. It is proved that this method has high accuracy in sand body feature extraction and classification and has great application potential in river sand body target recognition.

Adam golden search optimization enabled DCNN for classification of breast cancer using histopathological image

Breast Cancer (BC) is a killing disorder, every year it kills millions of human beings. Early diagnosis is the only way to mitigate the mortality rate. Among all kinds of screening methods, medical imaging is an essential method for screening BC. Existing medical imaging alters the tissue structure and cell morphology. To overcome these limitations, histopathology image is used because it can support the decision of pathologists about the closeness or the non-appearance of a disease, as well as it can help in infection development estimation. Hence, this research develops an efficient method for BC classification using the proposed Adam Golden Search Optimization-based Deep Convolutional Neural Network (AGSO-DCNN). Initially, Gaussian filter-enabled pre-processing is utilized for mitigating the noises composed in the input images. Afterwards, k-means clustering is used to feed the input images into the segmentation phase to reduce the complexity of the image. Then, to extract features like shape features, statistical features, Local Vector Patterns (LVP), and Pyramid Histogram of Oriented Gradients (PHOG) feature extraction is performed. Thereafter, the obtained features are forwarded to the multi-grade BC classification stage, where DCNN is employed for classifying the image into six categories, such as apoptosis, tubule, mitosis, non-tubule, tumour nuclei, and non-tumor nuclei. DCNN is trained by the formulated AGSO mechanism, which is obtained by incorporating the Adam Optimizer and Golden Search Optimization (GSO) algorithm. Moreover, the AGSO-based DCNN technique achieved better accuracy, TPR and TNR with the values of 97.90%, 98.00%, and 98.30%, respectively.

Tuning the parameters of a free-space optical channel using machine learning

The present work uses artificial intelligence (AI) methodology to simulate the data transmission process through free-space optical (FSO) technology. With machine learning procedures, the data are obtained by multiparametric simulation using Optisystem software. For the first simulation set, the input parameters were distance, attenuation, gain in the input signal amplifier, and gain in the output signal amplifier. For the second set, the effects of beam divergence and the receiver diameter were also evaluated. Additional sets were added to increase the data and characterize the underfitting and overfitting processes. With the data generated, artificial intelligence models were trained using decision tree regression (DTR), random forest regression (RFR), gradient boosting regressor (GBR), histogram gradient boosting regression (HGBR), and AdaBoost + deciston tree regression (ADDTR). The results showed that for the first scenario the models (DTR) and (RFR) showed an excellent estimate for the maximum quality factor (MaxQFactor), with a value of the coefficient of determination R2 above 95.00%, and, for the second scenario, the algorithms (DTR) and (RFR) also have shown excellent results, with R2 above 94.00%. The results obtained from the artificial intelligence procedures were compared graphically with the values obtained by multiparametric numerical simulation, confirming the effectiveness of the methodology used to predict the output values of the FSO channel.

Using the Support Vector Machine method with the HOG feature for classification of orchid types

Orchids are the most species-rich flowering plants, with approximately 750 genera and 43,000 types of orchids in the world, of which about 5,000 species have been recorded in several provinces in Indonesia. Orchids have beautiful flowers with attractive colors, making them ornamental plants that many people like. From plant morphology, orchid plants can be differentiated based on the morphology of flowers, leaves, fruit, stems, and roots. The leaves of orchid plants have their characteristics for each type of orchid, such as long, round, or lanceolate. All orchids have veins that run parallel to their leaves. The individual shapes of orchid leaves can be classified using a Support Vector Machine (SVM) and Histogram of Gradient (HOG). In this research, five types of orchids that are popular among orchid lovers were used, namely Dendrobium, Cattleya, Oncidium, Phalaenopsis, and Vanda orchids, which were taken from public data. The accuracy of this method in classifying orchid species based on leaf morphology can be measured using a confusion matrix that measures precision, recall, and accuracy. From five tests, the Oncidium orchid had the highest average accuracy with a value of 98%, the Vanda orchid had the highest average precision of 99.80%, and the Cattleya orchid had the highest average recall of 100%.

Two-stage HOG/SVM for license plate detection and recognition

Automatic license plate recognition (ALPR) is one of the technologies used in intelligent transport systems (ITS) to read vehicle license plates automatically. The extracted information has various potential applications, including but not limited to an electronic payment gateway, a system for paying parking fees, road surveillance, and managing traffic flow. In this paper, we propose an efficient method to detect and identify the Algerian license plate (LP). This method consists of a two-stage algorithm that combines the histogram of oriented gradients (HOG) with the support vector machine (SVM) classifier. The purpose of the first stage of HOG/SVM is the detection of the LP, while the recognition of the digits is accomplished by the second stage of HOG/SVM. As first contribution, a dataset of standard Algerian LP not available elsewhere is built (DZLP dataset), The second is a proposal of a very efficient pre-processing step for LP detection and digit recognition. Experimental results show that the proposed approach yields very high license plate and average digits recognition rates, which of 97.5% and 99.46%, respectively.

755 Pathology in the Digital Era of Neuro-oncology: A Pathomics-Based Approach to Modeling Outcomes in Medulloblastoma

INTRODUCTION: Pathomics is an emerging data science technique that may be used to extract intricate, sub-visual histopathologic features using high-throughput digital image analysis. METHODS: Using the Children’s Brain Tumor Network database, pediatric medulloblastoma patients were evaluated for inclusion in the study. After tumor segmentation, 49 quantitative pathomic features were extracted using a digital pathology software package (Qupath). LASSO cox proportional hazard model with stratified 5-fold cross-validation was used to identify high-performing features and create a predictive survival model by identifying low-, medium- and high-risk OS cohorts. A classification model was developed using histogram gradient boosting classifier to perform binary classification of Group3/4 vs. SHH/WNT with leave-one-subject-out cross validation. RESULTS: 84 patients with median age at diagnosis of 8.61 years (range 0.31-21.72), and median OS of 45.6 months (range 0.76-195.87) were included in the study. A survival model built using only clinical features yielded a concordance index (c-index) of 0.76 compared to actual outcomes (stratification: p < 0.001). However, a survival model built by combining clinical and high-performing pathomic features yielded the best performance, showing disparate outcomes between low-, medium- and high-risk groups (p < 0.001) with resultant c-index of 0.85. Furthermore, pathomic features classified subjects into Group 3/4 or SHH/WNT with classification accuracy of 71% (SEM = 0.06), and t-test against stratified chance accuracy (57%) showed significantly above-chance performance (p = .019). CONCLUSIONS: This study represents the largest pathomic-based machine learning analysis for predicting survival and molecular subtypes in medulloblastoma. The results demonstrate success in pathomic analysis using machine learning-based modeling to predict survival and molecular subtypes for patients with medulloblastoma. Further work will aim to perform our analysis on an external validation dataset to enhance model performance and improve its clinical applicability.

Advancing Attendance: A Facial Recognition System Empowered by Deep Learning Techniques

Many studies during the last decade tried to provide an automatic technique for facial recognition and identification challenge especially in security systems. In this study, we suggested two methods for student attendance problem based on image processing and machine learning algorithms. The first method uses Haar cascade classifier with the Local Binary Patterns Histograms (LBPH) model and the second method composed from Histograms of Oriented Gradient (HoG) followed by the Convolutional Neural Network (CNN) model. Both methods take a collection of random student images taken from low quality sources as input. A set of image processing filters are first applied on images to enhance the method of extracting the face boundary. Then, each model will be trained using random images from student dataset. The trained model is tested using testing set. The results showed that the method that employ CNN model with HoG provides high accuracy value of 98.44%. While, the accuracy of LBPH model with Haar Cascade classifier is 95.63%.

Stroke Prediction with Enhanced Gradient Boosting Classifier and Strategic Hyperparameter

A stroke is a medical condition that occurs when the blood supply to the brain is interrupted. Stroke can cause damage to the brain that can potentially affect a person's function and ability to move, speak, think, and feel normally. The effect of stroke on health emphasizes the importance of stroke detection, so an effective model is needed in predicting stroke. This research aimed to find a new approach that can improve the performance of stroke prediction by comparing four derivative algorithms from Gradient Boosting by adding hyperparameters tuning. The addition of hyperparameters was used to find the best combination of parameter values that can improve the model accuracy. The methods used in this research were Categorical Boosting, Histogram Gradient Boosting, Light Gradient Boosting, and Extreme Gradient Boosting. The research involved retrieving, cleaning, and analyzing data and then the model performance was evaluated with a confusion matrix and execution time. The results obtained were Light Gradient Boosting with Hyperparameter RandomSearchCV achieved the highest accuracy at 95% among the algorithms tested, while also being the fastest in execution. The contribution of this research to the medical field can help doctors and patients predict the occurrence of stroke early and reduce serious consequences.

A Comparative Study of Machine Learning Classifiers for Enhancing Knee Osteoarthritis Diagnosis

Knee osteoarthritis (KOA) is a leading cause of disability, particularly affecting older adults due to the deterioration of articular cartilage within the knee joint. This condition is characterized by pain, stiffness, and impaired movement, posing a significant challenge in medical diagnostics and treatment planning, especially due to the current inability for early and accurate detection or monitoring of disease progression. This research introduces a multifaceted approach employing feature extraction and machine learning (ML) to improve the accuracy of diagnosing and classifying KOA stages from radiographic images. Utilizing a dataset of 3154 knee X-ray images, this study implemented feature extraction methods such as Histogram of Oriented Gradients (HOG) with Linear Discriminant Analysis (LDA) and Min–Max scaling to prepare the data for classification. The study evaluates six ML classifiers—K Nearest Neighbors classifier, Support Vector Machine (SVM), Gaussian Naive Bayes, Decision Tree, Random Forest, and XGBoost—optimized via GridSearchCV for hyperparameter tuning within a 10-fold Stratified K-Fold cross-validation framework. An ensemble model has also been made for the already high-accuracy models to explore the possibility of enhancing the accuracy and reducing the risk of overfitting. The XGBoost classifier and the ensemble model emerged as the most efficient for multiclass classification, with an accuracy of 98.90%, distinguishing between healthy and unhealthy knees. These results underscore the potential of integrating advanced ML methodologies for the nuanced and accurate diagnosis and classification of KOA, offering new avenues for clinical application and future research in medical imaging diagnostics.

A Novel Transfer Learning Approach to Improve Breast Cancer Diagnosing on Screening Mammography

Segmentation is a technique for separating an image into discrete areas in order to separate objects of interest from their surroundings. In image analysis, segmentation—which encompasses detection, feature extraction, classification, and treatment—is crucial. In order to plan treatments, segmentation aids doctors in measuring the amount of tissue in the breast. Categorizing the input data into two groups that are mutually exclusive is the aim of a binary classification problem. In this case, the training data is labeled in a binary format based on the problem being solved. Identifying breast lumps accurately in mammography pictures is essential for the purpose of prenatal testing for breast cancer. The proposed TLA (Transfer Learning Approach) based CNN (Convolution Neural Network) –TLA based CNN aims to offer binary classification for rapid and precise breast cancer diagnosis (benign and malignant). In order to predict the sub-type of cancer, this exploration as used Deep Learning techniques on the Histogram of Oriented Gradient (HOG) - Feature extraction technique that creates a local histogram of the image to extract features from each place in the image with CNN classifier. This research work employs two well-known pre-trained models, ResNet-50 and VGG16, to extract characteristics from mammography images. The high-level features from the Mammogram dataset are extracted using a transfer learning model based on Visual Geometry Group (VGG) with 16-layer and Residual Neural Network with 50-layers deep model architecture (ResNet-50). The proposed model TLA based CNN has achieved 96.49% and 95.48% accuracy as compared to ResNet50 and VGG16 in the breast cancer classification and segmentation.

Zanthoxylum infructescence detection based on adaptive density clustering

Infructescence detection during the early fruiting stage is a necessary preliminary work to estimate the yield of Zanthoxylum. The purpose of this research is to detect and quantify the infructescences on the images of early fruit-bearing branches of Zanthoxylum which are collected in the natural environment. Thus, a machine vision-based algorithm for detecting Zanthoxylum infructescences is proposed, which contains of two phases. The first is to segment fruit-like and non-fruit region from Zanthoxylum branch image by extracting the Histogram of Oriented Gradient (HOG) feature map and Excess Green minus Excess Red (ExGR) index to obtain the fruits of Zanthoxylum infructescences. The second is to identify fruits adaptively and roughly in accordance with the density of their position distribution, then an optimization model is established to merge rough clusters and the optimal clustering result is obtained. Experiments with normal samples demonstrate that the proposed approach receives a Precision of 96.67%, a Recall of 91.07%, and an F1-score of 0.93. Compared with ADPC-kNN, DBSCAN and OPTICS, the results reveal that the proposed algorithm has an improved robustness and achieves higher Recall and F1-score. Meanwhile, its competitiveness is displayed in the experiments with deep learning-based methods. It can adaptively detect the infructescences of Zanthoxylum branch images, and the experiments prove that it is effective.

Deep Learning-Based Small Face Detection from Hard Image

Facial detection usually comes first in face recognition and face analysis systems. Previously, techniques such as directed gradient histograms and cascades relied on manually-engineered features from particular photos. Nevertheless, the precision with which these techniques could identify faces in uncontrolled environments was restricted. Numerous deep learning-based face recognition frameworks have recently been developed, many of which have significantly increased accuracy, as a result of the rapid progress of deep learning in computer vision. Despite these advancements, detecting small, scaled, positioned, occluded, blurred, and faces that are partially occluded in uncontrolled conditions remains a challenge in face identification. This problem has been studied for many years but has not been completely resolved.

DVFNet: A deep feature fusion-based model for the multiclassification of skin cancer utilizing dermoscopy images.

Skin cancer is a common cancer affecting millions of people annually. Skin cells inside the body that grow in unusual patterns are a sign of this invasive disease. The cells then spread to other organs and tissues through the lymph nodes and destroy them. Lifestyle changes and increased solar exposure contribute to the rise in the incidence of skin cancer. Early identification and staging are essential due to the high mortality rate associated with skin cancer. In this study, we presented a deep learning-based method named DVFNet for the detection of skin cancer from dermoscopy images. To detect skin cancer images are pre-processed using anisotropic diffusion methods to remove artifacts and noise which enhances the quality of images. A combination of the VGG19 architecture and the Histogram of Oriented Gradients (HOG) is used in this research for discriminative feature extraction. SMOTE Tomek is used to resolve the problem of imbalanced images in the multiple classes of the publicly available ISIC 2019 dataset. This study utilizes segmentation to pinpoint areas of significantly damaged skin cells. A feature vector map is created by combining the features of HOG and VGG19. Multiclassification is accomplished by CNN using feature vector maps. DVFNet achieves an accuracy of 98.32% on the ISIC 2019 dataset. Analysis of variance (ANOVA) statistical test is used to validate the model's accuracy. Healthcare experts utilize the DVFNet model to detect skin cancer at an early clinical stage.

Subcutaneous fat predicts bone metastasis in breast cancer: A novel multimodality-based deep learning model.

This study explores a deep learning (DL) approach to predicting bone metastases in breast cancer (BC) patients using clinical information, such as the fat index, and features like Computed Tomography (CT) images. CT imaging data and clinical information were collected from 431 BC patients who underwent radical surgical resection at Harbin Medical University Cancer Hospital. The area of muscle and adipose tissue was obtained from CT images at the level of the eleventh thoracic vertebra. The corresponding histograms of oriented gradients (HOG) and local binary pattern (LBP) features were extracted from the CT images, and the network features were derived from the LBP and HOG features as well as the CT images through deep learning (DL). The combination of network features with clinical information was utilized to predict bone metastases in BC patients using the Gradient Boosting Decision Tree (GBDT) algorithm. Regularized Cox regression models were employed to identify independent prognostic factors for bone metastasis. The combination of clinical information and network features extracted from LBP features, HOG features, and CT images using a convolutional neural network (CNN) yielded the best performance, achieving an AUC of 0.922 (95% confidence interval [CI]: 0.843-0.964, P< 0.01). Regularized Cox regression results indicated that the subcutaneous fat index was an independent prognostic factor for bone metastasis in breast cancer (BC). Subcutaneous fat index could predict bone metastasis in BC patients. Deep learning multimodal algorithm demonstrates superior performance in assessing bone metastases in BC patients.

Wasserstein HOG: Local Directionality Extraction via Optimal Transport.

Directionally sensitive radiomic features including the histogram of oriented gradient (HOG) have been shown to provide objective and quantitative measures for predicting disease outcomes in multiple cancers. However, radiomic features are sensitive to imaging variabilities including acquisition differences, imaging artifacts and noise, making them impractical for using in the clinic to inform patient care. We treat the problem of extracting robust local directionality features by mapping via optimal transport a given local image patch to an iso-intense patch of its mean. We decompose the transport map into sub-work costs each transporting in different directions. To test our approach, we evaluated the ability of the proposed approach to quantify tumor heterogeneity from magnetic resonance imaging (MRI) scans of brain glioblastoma multiforme, computed tomography (CT) scans of head and neck squamous cell carcinoma as well as longitudinal CT scans in lung cancer patients treated with immunotherapy. By considering the entropy difference of the extracted local directionality within tumor regions, we found that patients with higher entropy in their images, had significantly worse overall survival for all three datasets, which indicates that tumors that have images exhibiting flows in many directions may be more malignant. This may seem to reflect high tumor histologic grade or disorganization. Furthermore, by comparing the changes in entropy longitudinally using two imaging time points, we found patients with reduction in entropy from baseline CT are associated with longer overall survival (hazard ratio = 1.95, 95% confidence interval of 1.4-2.8, p = 1.65e-5). The proposed method provides a robust, training free approach to quantify the local directionality contained in images.

Automatic detection of knee osteoarthritis grading using artificial intelligence‐based methods

AbstractOsteoarthritis (OA) means that the slippery cartilage tissue that covers the bone surfaces in the joints and allows the joint to move easily loses its properties and wears out. Knee OA is the wear and tear of the cartilage in the knee joint. Knee OA is a disease whose incidence increases especially after a certain age. Knee OA is difficult and costly to be detected by specialists using traditional methods and may lead to misdiagnosis. In this study, computer‐aided systems were used to prevent errors in traditional methods of detecting knee OA, shorten the diagnosis time, and accelerate the treatment process. In this study, a hybrid model was developed by using Darknet53, Histogram of Directional Gradients (HOG), Local Binary Model (LBP) methods for feature extraction, and Neighborhood Component Analysis (NCA) for feature selection. Our dataset used in experiments contains 1650 knee joint images and consists of five classes: Normal, Doubtful, Mild, Moderate, and Severe. In the experimental studies performed, the performance of the proposed method was compared with eight different Convolutional Neural Networks (CNN) Models. The developed model achieved better performance metrics than the eight different models used in the study and similar studies in the literature. The accuracy value of the developed model is 83.6%.

Vision-Based On-Road Nighttime Vehicle Detection and Tracking Using Improved HOG Features.

The lack of discernible vehicle contour features in low-light conditions poses a formidable challenge for nighttime vehicle detection under hardware cost constraints. Addressing this issue, an enhanced histogram of oriented gradients (HOGs) approach is introduced to extract relevant vehicle features. Initially, vehicle lights are extracted using a combination of background illumination removal and a saliency model. Subsequently, these lights are integrated with a template-based approach to delineate regions containing potential vehicles. In the next step, the fusion of superpixel and HOG (S-HOG) features within these regions is performed, and the support vector machine (SVM) is employed for classification. A non-maximum suppression (NMS) method is applied to eliminate overlapping areas, incorporating the fusion of vertical histograms of symmetrical features of oriented gradients (V-HOGs). Finally, the Kalman filter is utilized for tracking candidate vehicles over time. Experimental results demonstrate a significant improvement in the accuracy of vehicle recognition in nighttime scenarios with the proposed method.

Covid-19 Detection by Machine Learning Using Chest Radiographs

The recent pandemic caused by Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) has highlighted the importance of early detection of infections, especially when RT-PCR testing equipment is scarce. This study introduces a machine learning algorithm using CT scan imaging for rapid COVID-19 identification. The algorithm, designed as a computer-aided detection model, analyzed 536 CT images (32x32 pixels) categorized into COVID-19 infected and non-infected groups. The model preprocesses images using the Prewitt filter and discrete cosine transform, then extracts features through various statistical methods and the histogram of oriented gradients (HOG). Out of 32 analyzed features, 29 showed high significance (p-value &lt; 0.05), effectively distinguishing normal and abnormal cases. These features were classified using support vector machine (SVM) and k-nearest neighbor (KNN) methods. Performance metrics like sensitivity, specificity, and accuracy were used to evaluate the classifiers. The results of metrics showed that the classifiers of KNN-1, KNN-3, KNN-5, and SVM-Linear could distinguish between normal and abnormal images perfectly (100%) when it was applied to the proposed model on the tested ROIs images. Also, the SVM-RBF had less performance than other classifiers with 98.38% of accuracy but was still at a high-performance level. These results indicate that physicians can utilize the proposed model as an assisted tool for detecting COVID-19.