Face Detection Method Research Articles

Defect intelligent recognition of membrane product based on deep learning

Defect detection plays a crucial role in the manufacturing industry, ensuring the quality of industrial products. Despite advancements in this field, current defect detection methods face two primary challenges: (1) extracting visually similar features from the background poses difficult and (2) these methods struggle to identify tiny defects in the target objects. We present a feature enhancement module called the SE-CAR, which aims to handle the identified problems effectively. This module is designed to efficiently capture tiny defects in images, prioritize defect information features, and ultimately enhance the model’s predictive performance and accuracy in defect recognition tasks. In addition, Distance-IoU Non-Maximum Suppression is employed as a substitution for the original Non-Maximum Suppression. This enhances the recognition accuracy of bounding boxes, ensuring that the model maintains high detection accuracy even after complex scenarios. Moreover, the proposed methodology exhibits broad applicability across a wide spectrum of prevalent defect detection paradigms. In empirical experiments, we employ the YOLOv7 architecture as the foundation framework, integrating the proposed methodologies for the purpose of detecting defects in the membrane. The empirical evidence demonstrates a notable improvement in the performance of detecting defects in membrane products using the SE-CAR feature enhancement module and Distance-IoU Non-Maximum Suppression algorithm. In comparison to baseline networks, an increase in mAp by 6.29%, precision by 1.63%, and recall by 8.76%.

Precision agriculture with YOLO-Leaf: advanced methods for detecting apple leaf diseases.

The detection of apple leaf diseases plays a crucial role in ensuring crop health and yield. However, due to variations in lighting and shadow, as well as the complex relationships between perceptual fields and target scales, current detection methods face significant challenges. To address these issues, we propose a new model called YOLO-Leaf. Specifically, YOLO-Leaf utilizes Dynamic Snake Convolution (DSConv) for robust feature extraction, employs BiFormer to enhance the attention mechanism, and introduces IF-CIoU to improve bounding box regression for increased detection accuracy and generalization ability. Experimental results on the FGVC7 and FGVC8 datasets show that YOLO-Leaf significantly outperforms existing models in terms of detection accuracy, achieving mAP50 scores of 93.88% and 95.69%, respectively. This advancement not only validates the effectiveness of our approach but also highlights its practical application potential in agricultural disease detection.

RP-Net: A Robust Polar Transformation Network for rotation-invariant face detection

Face detection is challenging in unconstrained environments, where it encounters various challenges such as orientation, pose, and occlusion. Deep convolutional neural networks, particularly cascaded ones, have greatly improved detection performance but still struggle with rotating objects due to limitations in the Cartesian coordinate system. Although data augmentation can mitigate this issue, it also increases computational demands. This paper introduces the Robust Polar Transformation Network (RP-Net) for rotation-invariant face detection. RP-Net converts the complex rotational problem into a simpler translational one to enhance feature extraction and computational efficiency. Additionally, the Advanced Spatial-Channel Restoration (ASCR) module optimizes facial landmark detection within polar domains and restores critical details lost during transformation. Experimental results on benchmark datasets show that RP-Net significantly improves rotation invariance over traditional CNNs and surpasses several state-of-the-art rotation-invariant face detection methods.

The novel methods of insulation detection based on Adaptive Levenberg–Marquardt algorithm and Third-Order Variable Forgetting Factor Recursive Least Squares-Decouple algorithm

Electric vehicles (EVs) are central to the future of automotive development, with high-voltage insulation performance critical for operational safety. Existing insulation detection methods face challenges such as limited scope, low accuracy, poor interference resistance, and slow response. This study introduces two insulation detection models based on the unbalanced bridge method and low-frequency signal injection, analyzing their theoretical effectiveness and confirming superior detection capability in the unbalanced bridge method. Furthermore, to address feedback voltage waveform issues in this method, an adaptive Levenberg–Marquardt (ALM) algorithm is proposed to prevent the divergence typically seen in traditional approaches. Additionally, a decoupling algorithm utilizing a Third-order Variable Forgetting Factor Recursive Least Squares (TVFF-Decouple) simplifies algorithm complexity significantly while enabling anomaly detection. Finally, AEKF and SRCKF algorithms were used for observation, identifying an optimal combination that reduces noise interference effectively. Simulations and bench tests demonstrate that the proposed methods swiftly and accurately detect positive and negative insulation resistances and equivalent Y capacitance under various conditions.

Exploration of Volatileomics and Optical Properties of Fusarium graminearum-Contaminated Maize: An Application Basis for Low-Cost and Non-Destructive Detection.

Fusarium graminearum (F. graminearum) in maize poses a threat to grain security. Current non-destructive detection methods face limited practical applications in grain quality detection. This study aims to understand the optical properties and volatileomics of F. graminearum-contaminated maize. Specifically, the transmission and reflection spectra (wavelength range of 200-1100 nm) were used to explore the optical properties of F. graminearum-contaminated maize. Volatile organic compounds (VOCs) of F. graminearum-contaminated maize were determined by headspace solid phase micro-extraction with gas chromatography-tandem mass spectrometry. The VOCs of normal maize were mainly alcohols and ketones, while the VOCs of severely contaminated maize became organic acids and alcohols. The ultraviolet excitation spectrum of maize showed a peak redshift as fungi grew, and the intensity decreased in the 400-600 nm band. Peak redshift and intensity changes were observed in the visible/near-infrared reflectance and transmission spectra of F. graminearum-contaminated maize. Remarkably, optical imaging platforms based on optical properties were developed to ensure high-throughput detection for single-kernel maize. The developed imaging platform could achieve more than 80% classification accuracy, whereas asymmetric polarization imaging achieved more than 93% prediction accuracy. Overall, these results can provide theoretical support for the cost-effective preparation of low-cost gas sensors and high-prediction sorting equipment for maize quality detection.

Comprehensive Mapping of Cyclotides from Viola philippica by Using Mass Spectrometry-Based Strategy.

Cyclotides are plant cyclic peptides with exceptional stability and diverse bioactivity, making them promising candidates for biomedical applications. Therefore, the study of cyclotides has attracted increasing attention in recent years. However, the existing cyclotide detection methods face limitations in sensitivity, accuracy, and reliability. To address these challenges, we developed an integrated strategy using a combination of strong cation exchange chromatography techniques for removing interfering small molecules, Orbitrap Exploris 480 mass spectrometry (OEMS); this is a detection and database searching-based method for cyclotide verification, which greatly improved the sensitivity, accuracy, and reliability of cyclotide identification. This strategy was subsequently employed for cyclotide mapping in Viola with a minute amount of starting tissue, resulting the identification of 65 known and 18 potentially novel cyclotides, which is the largest dataset of cyclotides for Viola philippica. This strategy provided valuable insights into the cyclotide diversity and distribution in V. philippica, with potential applications in drug discovery and other biomedical fields.

Ensembled methodology for the comtrade analysis regarding medium voltage side in wind park

This research proposes a methodology for automated COMTRADE analysis using ensembled algorithms for fault analysis in medium voltage circuits, specifically for wind park feeders. Traditional fault detection methods face significant limitations, such as CT saturation and DC offset, underscoring the need for improved approaches. The proposed methodology integrates Random Committee, XGBoost (XGB), and Light XGB algorithms, optimized through grid search, achieving an accuracy of 99.397 %. This ensemble approach significantly reduces classification errors, false positives, and false negatives compared to single algorithm methods. This research has the analysis of 3929 events for training and 829 fault events for test, it revealed a high correlation between current and fault spectra; the methodology demonstrated superior performance in fault location analysis, with terminal faults showing the most severe transient recovery voltage (TRV) peak values, while kilometer faults exhibited higher transient recovery restoration voltage growth rates. The fault location analysis was conducted by comparing simulation-derived overvoltage with standard TRV graphs, aligned with IEC 62271-100 standards. Circuit breakers exhibited higher TRV tolerance with lower fault currents. Terminal faults, particularly symmetrical three-phase faults, were identified as the most severe, typically occurring at peak TRV values. Its findings reduced classification errors, from 41 to 5 events, and decreased the false negative rate from 1.81 % to 0.24 % compared to Random Forest. Validation with virtual relays showed a reduction in RCE from 5.3 % to 0.63 %.

Rapid identification method for on-road high-emission vehicle based on deep semi-supervised anomaly detection

This study aims to identify high-emission vehicles in urban traffic management. Existing high-emission vehicle identification models typically overlook the dispersed anomaly data distribution, and machine learning anomaly detection methods face difficulties in learning decision boundaries, leading to reduced detection performance. To address these issues, this study proposes a semi-supervised learning method based on data fusion and deep anomaly detection. This method integrates the chassis and engine dynamometer test data with on-road remote sensing system data to obtain more comprehensive vehicle emission information. Experimental results demonstrate that the proposed method introduces a penalty mechanism for anomaly samples, encouraging the model to increase the dissimilarity in similarity between normal and abnormal data at the latent data distribution level. In vehicle emission datasets from different regions, this method achieves over 95% AUC, demonstrating strong applicability and accuracy.

Heterogeneous Views and Spatial Structure Enhancement for triple error detection

Knowledge graph error detection is to identify erroneous triples in knowledge graphs that are inconsistent with objective facts in the real world. In practice, the quality of knowledge graphs is an indispensable foundation for the widespread and accurate knowledge application services such as intelligent retrieval and human machine dialogue. Technically, the existing knowledge graph error detection methods face the following two problems: few available negative samples of triples, and an uneven data distribution. That distribution is caused by the large disparity in the number of head and tail entities belonging to the same relationship and the disparity in the number of triples with different relationships. To alleviate these problems, this paper proposes an approach based on the Heterogeneous Views and Spatial Structure Enhancement (HVSSE) in a contrastive learning framework for triple error detection task. Specifically, the heterogeneous views are constructed to include four kinds of triple views, i.e., positive and negative triple views based on head or tail entity co-occurrence. Moreover, Graph-Spatial-Transformer with an explicit spatial structure encoding is designed to fully capture the contextual information of triple nodes. Thereby, driven by the framework of contrastive learning, our HVSSE model can not only learn more discriminative embedding of triples, but also capture the local structure of triples and global contextual information of knowledge graphs. Experimental results on five public datasets indicate that our proposed approach is superior to the state-of-the-art methods, showing its the effectiveness on triple error detection.

Face detection method based on improved YOLO-v4 network and attention mechanism

Abstract Due to insufficient information and feature extraction in existing face-detection methods, as well as limited computing power, designing high-precision and efficient face-detection algorithms is an open challenge. Based on this, we propose an improved face detection algorithm. First, through 1 × 1’s common convolution block (CBL) expands the channel for feature extraction, introduces a depthwise separable residual network into the YOLO-v4 network to further reduce the amount of model computation, and uses CBL to reduce the dimension, so as to improve the efficiency of the subsequent network. Second, the improved attention mechanism is used to splice the high-level features, and the high-level features and the shallow features are fused to obtain the feature vectors containing more information, so as to improve the richness and representativeness of the feature vectors. Finally, the experimental results show that compared with other comparative methods, our method achieves the best results on public face datasets, and our performance in personal face detection is significantly better than other methods.

Colorectal Polyp Detection Model by Using Super-Resolution Reconstruction and YOLO

Colorectal cancer (CRC) is the second leading cause of cancer-related deaths worldwide. Colonoscopy is the primary method to prevent CRC. However, traditional polyp detection methods face problems such as low image resolution and the possibility of missing polyps. In recent years, deep learning techniques have been extensively employed in the detection of colorectal polyps. However, these algorithms have not yet addressed the issue of detection in low-resolution images. In this study, we propose a novel YOLO-SRPD model by integrating SRGAN and YOLO to address the issue of low-resolution colonoscopy images. Firstly, the SRGAN with integrated ACmix is used to convert low-resolution images to high-resolution images. The generated high-resolution images are then used as the training set for polyp detection. Then, the C3_Res2Net is integrated into the YOLOv5 backbone to enhance multiscale feature extraction. Finally, CBAM modules are added before the prediction head to enhance attention to polyp information. The experimental results indicate that YOLO-SRPD achieves a mean average precision (mAP) of 94.2% and a precision of 95.2%. Compared to the original model (YOLOv5), the average accuracy increased by 1.8% and the recall rate increased by 5.6%. These experimental results confirm that YOLO-SRPD can address the low-resolution problem during colorectal polyp detection and exhibit exceptional robustness.

Evaluation of the passive mast cell activation test for identifying allergens in perioperative anaphylaxis: a study protocol for a prospective diagnostic accuracy study

IntroductionPerioperative anaphylaxis (POA) can lead to significant complications. Therefore, accurate identification of allergens for POA patients is critical to ensure the safety of future surgical and anaesthetic procedures. Existing perioperative...

A Real Time Facial Recognition and Tracking System for Personnel Presence

Abstract: Our project aims to revolutionize the conventional attendance system by implementing a facial recognition-based solution. The existing manual methods are prone to human error and require significant maintenance. By leveraging facial recognition technology, our system will offer improved precision and efficiency, reducing the need for manual work. The system will maintain a database of students' images, matching them during class to mark attendance accurately. Utilizing machine learning techniques, specially the Haar-Cascade classifier and local binary pattern histogram method for face detection and recognition, respectively, our system will ensure reliable attendance tracking. The attendance data will be stored in a MySQL database and Microsoft Excel file, providing a streamlined and secure alternative to the traditional attendance process.

Real-time precision detection algorithm for jellyfish stings in neural computing, featuring adaptive deep learning enhanced by an advanced YOLOv4 framework

IntroductionSea jellyfish stings pose a threat to human health, and traditional detection methods face challenges in terms of accuracy and real-time capabilities.MethodsTo address this, we propose a novel algorithm that integrates YOLOv4 object detection, an attention mechanism, and PID control. We enhance YOLOv4 to improve the accuracy and real-time performance of detection. Additionally, we introduce an attention mechanism to automatically focus on critical areas of sea jellyfish stings, enhancing detection precision. Ultimately, utilizing the PID control algorithm, we achieve adaptive adjustments in the robot's movements and posture based on the detection results. Extensive experimental evaluations using a real sea jellyfish sting image dataset demonstrate significant improvements in accuracy and real-time performance using our proposed algorithm. Compared to traditional methods, our algorithm more accurately detects sea jellyfish stings and dynamically adjusts the robot's actions in real-time, maximizing protection for human health.Results and discussionThe significance of this research lies in providing an efficient and accurate sea jellyfish sting detection algorithm for intelligent robot systems. The algorithm exhibits notable improvements in real-time capabilities and precision, aiding robot systems in better identifying and addressing sea jellyfish stings, thereby safeguarding human health. Moreover, the algorithm possesses a certain level of generality and can be applied to other applications in target detection and adaptive control, offering broad prospects for diverse applications.

Detection of the Pine Wilt Disease Using a Joint Deep Object Detection Model Based on Drone Remote Sensing Data

Disease and detection is crucial for the protection of forest growth, reproduction, and biodiversity. Traditional detection methods face challenges such as limited coverage, excessive time and resource consumption, and poor accuracy, diminishing the effectiveness of forest disease prevention and control. By addressing these challenges, this study leverages drone remote sensing data combined with deep object detection models, specifically employing the YOLO-v3 algorithm based on loss function optimization, for the efficient and accurate detection of tree diseases and pests. Utilizing drone-mounted cameras, the study captures insect pest image information in pine forest areas, followed by segmentation, merging, and feature extraction processing. The computing system of airborne embedded devices is designed to ensure detection efficiency and accuracy. The improved YOLO-v3 algorithm combined with the CIoU loss function was used to detect forest pests and diseases. Compared to the traditional IoU loss function, CIoU takes into account the overlap area, the distance between the center of the predicted frame and the actual frame, and the consistency of the aspect ratio. The experimental results demonstrate the proposed model’s capability to process pest and disease images at a slightly faster speed, with an average processing time of less than 0.5 s per image, while achieving an accuracy surpassing 95%. The model’s effectiveness in identifying tree pests and diseases with high accuracy and comprehensiveness offers significant potential for developing forest inspection protection and prevention plans. However, limitations exist in the model’s performance in complex forest environments, necessitating further research to improve model universality and adaptability across diverse forest regions. Future directions include exploring advanced deep object detection models to minimize computing resource demands and enhance practical application support for forest protection and pest control.

Detecting Line Segments in Motion-Blurred Images With Events.

Making line segment detectors more reliable under motion blurs is one of the most important challenges for practical applications, such as visual SLAM and 3D line mapping. Existing line segment detection methods face severe performance degradation for accurately detecting and locating line segments when motion blur occurs. While event data shows strong complementary characteristics to images for minimal blur and edge awareness at high-temporal resolution, potentially beneficial for reliable line segment recognition. To robustly detect line segments over motion blurs, we propose to leverage the complementary information of images and events. Specifically, we first design a general frame-event feature fusion network to extract and fuse the detailed image textures and low-latency event edges, which consists of a channel-attention-based shallow fusion module and a self-attention-based dual hourglass module. We then utilize the state-of-the-art wireframe parsing networks to detect line segments on the fused feature map. Moreover, due to the lack of line segment detection datasets with pairwise motion-blurred images and events, we contribute two datasets, i.e., synthetic FE-Wireframe and realistic FE-Blurframe, for network training and evaluation. Extensive analyses on the component configurations demonstrate the design effectiveness of our fusion network. When compared to the state-of-the-arts, the proposed approach achieves the highest detection accuracy while maintaining comparable real-time performance. In addition to being robust to motion blur, our method also exhibits superior performance for line detection under high dynamic range scenes.

An adaptive detection model for IPv6 extension header threats based on deterministic decision automaton

The IPv6 extension header mechanism, a new feature of the IPv6 protocol, enhances flexibility and scalability but introduces numerous security threats like firewall evasion and covert channels. Existing threat detection methods face limitations in detection types, universality, and speed. Hence, an adaptive detection model for IPv6 extension header threats (ADM-DDA6) is proposed. Firstly, standard rule sets are designed for common IPv6 extension headers, successfully detecting 70 types of threats from THC-IPv6 and ExtHdr tools using only 20 rules. Secondly, by parsing IPv6 extension headers, matching rules, establishing transition relationships, and deciding packet threat status based on final states (Normal or Abnormal), complex threats like header disorder and header repetition can be detected. Finally, an adaptive rule matching method is introduced, which dynamically selects rule sets based on IPv6 extension header types, effectively reducing rule matching time. Experimental results show that under different threat magnitudes, ADM-DDA6 is 32% faster than Suricata v6.0.12 and 21.2% faster than Snort v3.1.61.0 in detection speed. Additionally, as the number of threats increases, on commodity hardware, ADM-DDA6 incurs only a 0.7% increase in CPU overhead with no significant memory consumption increase, maintains maximum throughput, and exhibits minor performance changes under low and moderate network load conditions.

Wildlife Real-Time Detection in Complex Forest Scenes Based on YOLOv5s Deep Learning Network

With the progressively deteriorating global ecological environment and the gradual escalation of human activities, the survival of wildlife has been severely impacted. Hence, a rapid, precise, and reliable method for detecting wildlife holds immense significance in safeguarding their existence and monitoring their status. However, due to the rare and concealed nature of wildlife activities, the existing wildlife detection methods face limitations in efficiently extracting features during real-time monitoring in complex forest environments. These models exhibit drawbacks such as slow speed and low accuracy. Therefore, we propose a novel real-time monitoring model called WL-YOLO, which is designed for lightweight wildlife detection in complex forest environments. This model is built upon the deep learning model YOLOv5s. In WL-YOLO, we introduce a novel and lightweight feature extraction module. This module is comprised of a deeply separable convolutional neural network integrated with compression and excitation modules in the backbone network. This design is aimed at reducing the number of model parameters and computational requirements, while simultaneously enhancing the feature representation of the network. Additionally, we introduced a CBAM attention mechanism to enhance the extraction of local key features, resulting in improved performance of WL-YOLO in the natural environment where wildlife has high concealment and complexity. This model achieved a mean accuracy (mAP) value of 97.25%, an F1-score value of 95.65%, and an accuracy value of 95.14%. These results demonstrated that this model outperforms the current mainstream deep learning models. Additionally, compared to the YOLOv5m base model, WL-YOLO reduces the number of parameters by 44.73% and shortens the detection time by 58%. This study offers technical support for detecting and protecting wildlife in intricate environments by introducing a highly efficient and advanced wildlife detection model.

Intelligent Rapid Detection Techniques for Low-Content Components in Fruits and Vegetables: A Comprehensive Review.

Fruits and vegetables are an important part of our daily diet and contain low-content components that are crucial for our health. Detecting these components accurately is of paramount significance. However, traditional detection methods face challenges such as complex sample processing, slow detection speed, and the need for highly skilled operators. These limitations fail to meet the growing demand for intelligent and rapid detection of low-content components in fruits and vegetables. In recent years, significant progress has been made in intelligent rapid detection technology, particularly in detecting high-content components in fruits and vegetables. However, the accurate detection of low-content components remains a challenge and has gained considerable attention in current research. This review paper aims to explore and analyze several intelligent rapid detection techniques that have been extensively studied for this purpose. These techniques include near-infrared spectroscopy, Raman spectroscopy, laser-induced breakdown spectroscopy, and terahertz spectroscopy, among others. This paper provides detailed reports and analyses of the application of these methods in detecting low-content components. Furthermore, it offers a prospective exploration of their future development in this field. The goal is to contribute to the enhancement and widespread adoption of technology for detecting low-content components in fruits and vegetables. It is expected that this review will serve as a valuable reference for researchers and practitioners in this area.

SQL Injection Detection using Machine Learning: A Review

SQL injection attacks are critical security vulnerability exploitation in web applications, posing risks to data, if successfully executed, allowing attackers to gain unauthorised access to sensitive data. Due to the absence of a standardised structure, traditional signature-based detection methods face challenges in effectively detecting SQL injection attacks. To overcome this challenge, machine learning (ML) algorithms have emerged as a promising approach for detecting SQL injection attacks. This paper presents a comprehensive literature review on the utilisation of ML techniques for SQL injection detection. The review covers various aspects, including dataset collection, feature extraction, training, and testing, with different ML algorithms. The studies included in the review demonstrate high levels of accuracy in detecting attacks and reducing false positives.