Direction Histogram Research Articles

Machine Learning in Agriculture: KNN-Based Classification of Fruits and Vegetables

In modern agriculture and the food industry, it is essential to classify fruits and vegetables accurately and efficiently to meet growing consumer demand and reduce post-harvest losses. Traditional manual methods are often labor-intensive and error prone, highlighting the need for automated solutions. This paper discusses the application of the k Nearest Neighbor (KNN) algorithm to fruit and vegetable recognition using image processing technology. In this study, image data sets are used for feature extraction using Directional Gradient Histogram (HOG) and dimensionality reduction using Principal Component Analysis (PCA). The accuracy of KNN model on verification set and test set reaches 97%, which proves its validity. Confusion matrix analysis and F1 score evaluation further revealed the strengths and areas of improvement of the model, particularly in distinguishing visually similar categories. The results show that the integration of artificial intelligence (especially KNN) offers great potential for the automation of agricultural classification tasks. Future studies could combine more advanced models, such as CNNS, with larger datasets to improve accuracy and robustness.

Anti-Occlusion Visual Tracking Algorithm for UAVs with Multi-Feature Adaptive Fusion

Most of the existing trackers based on discriminative correlation filters use only one feature or a simple linear fusion of multiple features for object tracking, and most of them lack a mechanism to handle occlusions. This leads to poor tracking performance in rapidly changing and easily occluded scenarios, especially on unmanned aerial vehicle (UAV) platforms. To address this issue, this paper proposes an anti-occlusion visual tracking algorithm for UAVs with multi-feature adaptive fusion named multi-feature adaptive fusion and anti-occlusion tracker (MAFAOT). It introduces a novel approach for implementing an adaptive fusion of multiple features. This method transforms the multi-feature fusion problem into a maximization issue by designing a tracking quality evaluation index. It successfully achieves an adaptive fusion of gradient direction histogram and color histogram feature responses. MAFAOT also introduces an anti-occlusion update pool strategy, enabling the tracker to adapt dynamically to various complex scenarios, including occlusion and motion blur. The experimental results on the OTB100 and UAV123 datasets confirm the significant advantages of MAFAOT in terms of precision and success rate compared to other correlation filter-based algorithms. The proposed methods further enhance the expressiveness of the features and effectively avoid the problem of tracker contamination caused by occlusion. Furthermore, this paper applies the proposed methods to the kernelized correlation filters (KCF) algorithm. On the OTB100 dataset, the improved KCF algorithm shows an improvement of 10.94% in precision and 11.11% in success rate. On the UAV123 dataset, it shows an improvement of 14.53% in precision and 16.62% in success rate, further verifying the effectiveness and versatility of the proposed methods.

Influence of VR-Assisted College Dance on College Students' Physical and Mental Health and Comprehensive Quality

With the development and the popularization of sports dance, sports dance teaching has become a required elective course in universities. Sports dance can not only improve students' comprehensive quality, but also affect college students' healthy psychology. The use of VR (Virtual Reality) technology in dance education will definitely develop and promote dance education. This paper studies an effective feature extraction method for the characteristics of dance movements based on VR. The edge features of all video images in each segment are accumulated into one image, and the directional gradient histogram features are extracted from it. The results show that compared with the current robust regression method and cascade regression method, our method has higher positioning accuracy on the pollution test set, and more than 75% of the sample errors in this method are within 0.1. This also verifies the effectiveness of this motion recognition algorithm for dance motion recognition. Dance can effectively resist the psychological barriers of college students and improve their comprehensive quality.

Research on Visual Inspection Method of Tree Whitening Quality based on Multi-level Feature Fusion

Background: At present, the traditional manual whitewashing method is used in tree whitewashing in China. The quality of tree whitening can only be judged by the naked eye. Objective: Up to now, the quality of tree whitewashing is still judged manually. In order to improve work efficiency, an automatic evaluation method of tree whitewashing quality based on multi-level feature fusion is proposed. Methods: The images extract texture features from white-washed trees (gray-level co-occurrence matrix) and shape features (gradient direction histogram) from pixel-level fusion to obtain a global characteristic matrix. Using a support vector machine (SVM), random forests, and clustering algorithm (KNN), three classifiers were selected to identify the integration characteristics of the training test. In order to reduce the correlation of feature information and improve the execution efficiency of the classifier, the global feature matrix was optimized by combining principal component analysis (PCA) with pixel-level fusion and feature-level fusion. Results: The experiment results showed that the classification accuracy of the support vector machine is 94.00%, which is higher than that of the random forest classifier (92.67) and KNN classifier (92.67%). Meanwhile, the support vector machine is superior to the other two classification algorithms in recall rate, accuracy rate, and algorithm execution efficiency. The results showed that the execution efficiency of each classification algorithm was improved after the optimization of the feature data. The support vector machine classification algorithm is more stable than the other two algorithms. Conclusion: The feature fusion method combined with PCA can improve the execution efficiency and recognition precision of classifiers to a certain extent. For the feature matrix obtained by different data processing methods, the SVM classifier performs more stably and reliably than the random forest classifier and KNN in the inspection of tree whitening quality.

Research on 3D point cloud alignment algorithm based on SHOT features.

To overcome the problem of the high initial position of the point cloud required by the traditional Iterative Closest Point (ICP) algorithm, in this paper, we propose a point cloud registration method based on normal vector and directional histogram features (SHOT). Firstly, a hybrid filtering method based on the voxel idea is proposed and verified using the measured point cloud data, and the noise removal rates of 97.5%, 97.8%, and 93.8% are obtained. Secondly, in terms of feature point extraction, the original algorithm is optimized, and the optimized algorithm can better extract the missing part of the point cloud. Finally, a fine alignment method based on normal vector and directional histogram features (SHOT) is proposed, and the improved algorithm is compared with the existing algorithm. Taking the Stanford University point cloud data and the self-measured point cloud data as examples, the plotted iteration-error plots can be concluded that the improved method can reduce the number of iterations by 40.23% and 37.62%, respectively.

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine.

In this paper, the directional gradient histogram technology is employed to extract the features of concrete image samples captured under different vibration states. The support vector machine (SVM) is utilized to learn the relationship between image features and vibration state. The machine learning results are subsequently used to assess the feasibility of the concrete vibration state. Simultaneously, the influence mechanism of the calculation parameters of the directional gradient histogram on the recognition accuracy is analyzed. The results demonstrate the feasibility of using the directional gradient histogram-SVM technology to identify the vibration state of concrete. The recognition accuracy initially increases and then decreases as the block size of the directional gradient, or the number of statistical intervals increases. The recognition accuracy also decreases linearly with the increase of the binarization threshold. By using sample images with a resolution of 1024 pixels x 1024 pixels and optimizing the feature extraction parameters, a recognition accuracy of 100% can be attained.

Feature extraction and classification of dance movements based on data mining

Abstract In recent years, the expansive utilization of data mining techniques has revolutionized various fields, including the analysis of dance videos. This study leverages data mining to meticulously capture and analyze dance movements, thereby facilitating the enhancement and correction of dancers’ techniques. Within the scope of this research, images of dance movements extracted from videos are subjected to preprocessing, which involves grayscaling and thresholding, to prepare them for further analysis. Building on these processed images, this paper introduces a novel multi-feature dance action recognition approach. This method integrates several distinct features—directional gradient histogram features, optical flow directional histogram features, and audio features—employing a linear weighting scheme within a multi-core learning framework. The efficacy of the proposed approach is demonstrated through its performance on the FolkDance dance dataset, where it achieves a 3.5% increase in fusion accuracy over the traditional Dance Style Identification (DSI) method. Additionally, when compared with the Multi-Feature Learning-Combined (MFL-C) method, our approach shows an improvement of 0.6% in fusion accuracy. This research establishes a viable method for the recognition and classification of dance movements, laying a robust foundation for further inquiry and practical applications in this domain.

The Value and Use of Chinese Traditional Music in Dance Performance in the Internet Era

Abstract In this study, Gaussian mixture model preprocessing and histogram of orientation gradient (HOG) and histogram of optical flow direction (HOF) action feature extraction techniques are used to significantly optimize the accuracy of dance performance action recognition. In addition, the VNect pose estimation algorithm and dual-stream 3D-CNN-based skeleton action recognition are used to improve significantly the accuracy and efficiency of recognition. In terms of music feature recognition, this study utilizes short-time time domain and frequency domain analysis techniques and BP neural networks to effectively achieve accurate recognition and sentiment classification of music features. Analyzing a dataset containing 6000 training videos, 800 validation videos, and 1200 test videos, the study reveals that musical elements, melody, rhythm, emotional tone, and song style significantly impact the stage performance effect. The study not only highlights the importance of traditional Chinese music in dance performance to enhance the artistic effect and deepen the emotional expression, but also opens up new perspectives and methods for disseminating and developing traditional culture.

МОДЕЛИ РАСПОЗНАВАНИЯ ЭЛЕМЕНТОВ ДОРОЖНОЙ ИНФРАСТРУКТУРЫ

The paper considers the problem of recognising road infrastructure elements (temporary signs, guardrail tapes, traffic cones). To solve it, we propose to use the following types of models: Deep Learning model, Random Forest model, Support Vector Machines model, Directional Gradient Histogram model. The principles of operation of the models presented in the article are considered. Recognizing road infrastructure elements in three of the four models studied requires a significant amount of time. The factors influencing the implementation of road works and object recognition are analyzed. The need for road work often depends on weather conditions (rain, snowfall, blizzard, fog, etc.). Recognition of road infrastructure elements includes the following stages: data capture, data preprocessing, model selection, model training, model testing. The article proposes the choice of a recognition model for road infrastructure elements (temporary barriers, temporary signs, traffic cones) based on the YOLO neural network, which has high detection speed and accuracy. The use of the YOLO neural network model allows for timely recognition of objects in images or video streams, which will further reduce the risks of road accidents. Based on the analysis of recognition models for road infrastructure elements, the use of the YOLO neural network model, which does not require significant financial costs, is proposed. The model was trained in the Google Colab development environment in the Python programming language. The neural network model was trained for 100 epochs in 15 minutes. The accuracy of recognition of road infrastructure elements on the training data set was 90%, and on the test set - 79%. In the future, it is planned to expand new data in the form of images of road infrastructure elements and develop a software package for automatically recognizing these elements and reducing the number of road accidents.

Application of big data technology in traditional dance video movement recognition research

Abstract This paper proposes a multi-feature fusion approach for action recognition under big data technology with the goal of improving traditional dance video action recognition. By analyzing the basic method of dance action, the extraction process of dance action features is analyzed using both single-layer and hierarchical methods. Multi-feature fusion action recognition is chosen as the main method for action recognition. The image and audio features of the dance video are combined to improve the accuracy of recognizing dance actions. Use the optical flow algorithm to construct a histogram of the optical flow direction. The method’s feasibility is explored by applying the multi-feature fusion recognition method to traditional dance movement recognition. The results show that in traditional dance movement recognition performance, the performance of the method of multi-feature fusion recognition is improved by 7.6% compared to other traditional methods. The multi-feature fusion recognition method has more than 50% accuracy in recognizing different traditional dance movements and similar movements in terms of movement recognition accuracy. To a certain degree, this study enhances the efficiency of traditional dance movement recognition and conserves human and financial resources in dance movement recognition.

Automated Deep Learning Model with Optimization Mechanism for Segmenting Leukemia from Blood Smear Images

The advancement of digital microscopic scanning has made the study of image processing as well as categorization an exciting field of diagnostic studies. The literature describes a number of methods for detecting acute lymphocytic leukemia (ALL) using blood smear pictures. The goal of this research is to create an efficient approach for segmenting and detecting leukemia. This research has created a leukemia diagnosis module predicated on deep learning (DL) using blood smear pictures. Pre-processing, segmentation, extraction of features, and classification are performed here by the identification scheme. The presented hybrid model of African Buffalo and African Vulture Optimization (AB-AVO) performs the segmentation process, in which cytoplasm and nucleus regions are segmented. The Local Directional Pattern (LDP) and color histogram characteristics have been then retrieved from the segmented pictures and given into the presented Recurrent Neural Network (RNN) for categorization. The ALL-IDB1 and ALL-IDB2 databases’ blood smear pictures are taken into account for the investigation and assessed using metrics including F1-score, sensitivity, dice coefficient, precision, specificity, recall, and accuracy. The presented AB-AVO-RNN approach exhibits 100% accuracy, according to simulation data. Modern methodologies are used to compare the effectiveness of the suggested AB-AVO-RNN methodology. The investigation demonstrates that the suggested classifier performs comparably better and can identify leukemia from blood smear pictures.

Efficient bat-inspired block matching algorithm with novel motion energy directional histograms for dynamic texture fast recognition

Efficient bat-inspired block matching algorithm with novel motion energy directional histograms for dynamic texture fast recognition

Integration of Deep Direction Distribution Feature Extraction and Optimized Attention Based Double Hidden Layer GRNN Models for Robust Cursive Handwriting Recognition

Cursive handwriting recognition (CHWR) is an interesting area of research as it has a wide range of applications but lacks an accurate approach to provide better results due to its character shapes, the non-uniform spacing between words and within a word, diverse placements of dots, and diacritics, and very low inter-class variation among individual classes. A novel CHWR model is proposed to enhance the recognition accuracy with high global stability. The proposed model introduces three major phases: pre-processing, feature extraction and classification. In the pre-processing stage, the noise removal and binarization are adapted with the intrusion of improved adaptive wiener filtering (IAWF) and structural symmetric pixels. A hybrid deep direction distribution feature extraction (HDDDFE) approach is proposed to extract directional Local gradient histogram (LGH), column gradient histogram (CGH) features and a wavelet convolutional neural network with Block Attention Module (WCNN-BAM) is proposed to extract deep global features (GF), profile features (PF) and dynamic features (DF). A novel double hidden layer gated recurrent neural network with a feature attention mechanism (ODHL-GRNN-FAM) is proposed to offer handwritten classification results. The developed model is evaluated with the IAM database and attains an overall recognition accuracy of 98%, precision of 97%, f-measure of 97.99%, character error rate (CER) of 1.23%, word error rate (WER) of 4.8%, respectively.

Acousto-optic Multi-source Information Fusion Algorithm for Outdoor Pedestrian Detection

The inefficiency of traditional rescue methods is a serious threat to the life and health of outdoor people in distress, so the research on pedestrian identification for outdoor rescue has important theoretical significance and application value. In order to solve the problem of low probability of recognition based on signal information in traditional methods, an outdoor pedestrian recognition model based on acousto-optic information fusion is constructed. Considering the characteristics of the information source, the directional gradient histogram of the infrared image and the Mel Cepstral Coefficients of the acoustic signal are selected as the factors affecting the recognition probability, and the pedestrian recognition probability correlation equation is deduced; Based on the improved D-S evidence theory of fuzzy system, a pedestrian recognition method based on infrared image and sound signal is proposed, and the mapping relationship between two kinds of information sources and detection probability is established to improve the pedestrian recognition probability. The hardware-in-the-loop simulation results show that the pedestrian recognition probability of fusion of infrared image and sound signal is higher than that of single information, which provides an efficient and reliable method for outdoor rescue.

Multi – oil droplet recognition of oil-water two-phase flow based on integrated features

Multi-oil droplet target recognition is one of the applications of machine vision in the measurement of oil-water two-phase flow parameters, which could combine other algorithms to obtain the oil droplet velocity and the water holdup of oil water two-phase flow. Appropriate target representation features can improve the recognition effect of multiple oil droplets. However, due to shooting environment differences and quality differences of oil-water two-phase flow images, existing target representation features do not perform well in low-quality oil-water two-phase flow images. To improve the precision of multi-oil droplet target recognition in oil-water two-phase flow and reduce the miss rate, this paper constructs an integrated feature on the basis of aggregate channel features (ACF). The integrated feature named aggregate channel features with histogram of local gravitational feature（ACFHG） contains the color feature channels reflecting the overall color features of the oil droplet sample, the gradient amplitude channel reflecting the overall gradient of the oil droplet sample image, the gradient direction histogram feature channels reflecting the local gradient of the oil droplet sample image, and the local gravitational feature channels that ensure oil droplet target recognition in low quality photos and photos taken in complex shooting environments. Moreover, the rotation invariance is obtained by taking the oriented gradient histogram of the local gravitational feature to further improve the multi-oil droplet target recognition effect. Experiment results show that the average precision of multi-oil droplet target recognition using the integrated features is 83.38%, which is 9.93% higher than that with using ACF, and the miss rate is 9.13%, which is 57.18% lower than that with using ACF. Compared with other existing target detection methods, the method proposed in this paper still has an advantage in the rate of missed detection.

An improved SIFT algorithm for registration between SAR and optical images

Aiming at improving the performance of scale invariant feature transform (SIFT) algorithm during the registration of optical and synthetic aperture radar (SAR) images, a new SIFT algorithm is proposed. Firstly, the nonlinear diffusion scale space of optical and SAR images is constructed by using nonlinear diffusion filtering, the uniform gradient information is calculated by using multi-scale Sobel operator and multi-scale exponential weighted mean ratio operator respectively. Then, after removing the first layer of the scale space with the image blocking strategy, the scale space is partitioned, and Harris feature points are extracted on the basis of consistent gradient information to obtain stable and uniform point features. Descriptors are constructed based on gradient position and direction histogram templates and normalized to overcome nonlinear radiation differences between images. Finally, the correct matching point pairs are obtained by using bilateral fast approximate nearest neighbor (FLANN) search matching method and random sampling consistent (RANSAC) method, and the affine transformation model parameters are obtained. Compared with the other two algorithms, the CMR of this algorithm is improved by 80.53%, 75.61% and 81.74% respectively in the three groups of images, and the RMSE is reduced by 0.6491, 1.0287 and 0.6306 respectively.

Research on Background Learning Correlation Filtering Algorithm With Multi-Feature Fusion

Aiming at the problems of occlusion, drift, and background change in target tracking, a background learning correlation filtering algorithm based on multi-feature fusion is proposed. In the framework of correlation filtering, multi-feature fusion, multi-template update, and background learning regularization are used to improve the performance of the filter in the problem of template contamination and object occlusion. The fast directional gradient histogram (FHOG), color feature (CN), and texture feature (ULBP) were extracted, and the feature channels were connected in series. Then the depth features of Conv4-4 and Conv5-4 layers were extracted through the VGG-19 network, and the appearance model of the target was constructed. To reduce the sensitivity of the filter to the sudden change of background, a background learning filter is constructed, and the alternate direction multiplier method (ADMM) is used to speed up the calculation of the filter. In the model update stage, aiming at the problem of pollution of the original template caused by target occlusion, a high-confidence multi-template fusion update strategy is proposed by fusing the template with the highest confidence in the current frame, the previous frame, and the history frame. Finally, the proposed algorithm is tested on OTB50, OTB100, UAV123, and TC128 experimental data sets, and some classical and latest algorithms. The experimental results show that the tracking accuracy and robustness of the correlation filtering algorithm are improved.

An Early Warning Model for Intelligent Operation of Power Engineering based on Kalman Filter Algorithm

The accurate early warning of intelligent operation of power engineering can find the abnormal operation of substation equipment in time and ensure the safe operation of substation equipment. Thus, an early warning model for intelligent operation of power engineering based on Kalman filter algorithm is constructed. In this model, the noise elimination method of substation equipment inspection image based on particle resampling filter algorithm is introduced. After removing the noise information of operation situation inspection image of substation equipment, the gradient direction histogram feature, lab color space feature and edge contour feature in the image are extracted by the multi-feature extraction method for intelligent operation of power engineering based on multi-feature fusion. These features are combined to form the feature description set of equipment operation situation. The feature description set is used as the identification attribute set of the anomaly identification and early warning model for intelligent operation of electric power engineering based on Kalman filter algorithm to complete the anomaly identification and early warning of equipment operation situation. The test shows that when the model is used to observe the temperature change trend of the top layer of the transformer, the temperature error is very small, and the early warning accuracy for the abnormal temperature of the top layer of the transformer is very high, so the abnormal operation of the substation equipment can be found in time.

An “optical flow” method based on pressure sensors data for quantification of Parkinson's disease characteristics

Most patients with Parkinson's disease (PD) have different degrees of movement disorders, and effective gait analysis is beneficial to find the abnormal gait of patients to achieve the diagnosis of patients with Parkinson's disease. In this paper, an “optical flow” method based on Vertical Ground Reaction Force (VGRF) timeseries data is proposed, the algorithm takes the force point as the detection target, regards the transfer of the force point on the sole as the optical flow, and combines the optical flow of the multi-level force points to form optic flow field. To quantify the optical flow direction, the direction histogram is used to extract the direction information, and the symmetry information is further extracted according to the optical flow difference between the left and right foot, which not only realizes the fusion of multi-sensors but also extracts highly interpretable motion information. Finally, the model is trained by combining optical flow features and spatial-temporal features. The results show that the proposed model has better performance in gait detection of Parkinson's disease patients than several other state-of-the-art methods previously studied. Among them, the accuracy of Parkinson's disease diagnosis reached 93.3%, and the accuracy of severity assessment of Parkinson's disease reached 91.4%.

Head Orientation Influences Saccade Directions during Free Viewing.

When looking around a visual scene, humans make saccadic eye movements to fixate objects of interest. While the extraocular muscles can execute saccades in any direction, not all saccade directions are equally likely: saccades in horizontal and vertical directions are most prevalent. Here, we asked whether head orientation plays a role in determining saccade direction biases. Study participants (n = 14) viewed natural scenes and abstract fractals (radially symmetric patterns) through a virtual reality headset equipped with eye tracking. Participants' heads were stabilized and tilted at -30°, 0°, or 30° while viewing the images, which could also be tilted by -30°, 0°, and 30° relative to the head. To determine whether the biases in saccade direction changed with head tilt, we calculated polar histograms of saccade directions and cross-correlated pairs of histograms to find the angular displacement resulting in the maximum correlation. During free viewing of fractals, saccade biases largely followed the orientation of the head with an average displacement value of 24° when comparing head upright to head tilt in world-referenced coordinates (t (13) = 17.63, p < 0.001). There was a systematic offset of 2.6° in saccade directions, likely reflecting ocular counter roll (OCR; t (13) = 3.13, p = 0.008). When participants viewed an Earth upright natural scene during head tilt, we found that the orientation of the head still influenced saccade directions (t (13) = 3.7, p = 0.001). These results suggest that nonvisual information about head orientation, such as that acquired by vestibular sensors, likely plays a role in saccade generation.