Region-based Fully Convolutional Network Research Articles

Research on a Bearing Fault Diagnosis Method Based on an Improved Wasserstein Generative Adversarial Network

In this paper, an advanced Wasserstein generative adversarial network (WGAN)-based bearing fault diagnosis approach is proposed to bolster the diagnostic efficacy of conventional WGANs and tackle the challenge of selecting optimal hyperparameters while reducing the reliance on sample labeling. Raw vibration signals undergo continuous wavelet transform (CWT) processing to generate time–frequency images that align with the model’s input dimensions. Subsequently, these images are incorporated into a region-based fully convolutional network (R-FCN), substituting the traditional discriminator for feature capturing. The WGAN model is refined through the utilization of the Bayesian optimization algorithm (BOA) to optimize the generator and discriminator’s semi-supervised learning loss function. This approach is verified using the Case Western Reserve University (CWRU) dataset and a centrifugal pump failure experimental dataset. The results showed improvements in data input generalization and fault feature extraction capabilities. By avoiding the need to label large quantities of sample data, the diagnostic accuracy was improved to 98.9% and 97.4%.

Proposal-Free Fully Convolutional Network: Object Detection Based on a Box Map.

Region proposal-based detectors, such as Region-Convolutional Neural Networks (R-CNNs), Fast R-CNNs, Faster R-CNNs, and Region-Based Fully Convolutional Networks (R-FCNs), employ a two-stage process involving region proposal generation followed by classification. This approach is effective but computationally intensive and typically slower than proposal-free methods. Therefore, region proposal-free detectors are becoming popular to balance accuracy and speed. This paper proposes a proposal-free, fully convolutional network (PF-FCN) that outperforms other state-of-the-art, proposal-free methods. Unlike traditional region proposal-free methods, PF-FCN can generate a "box map" based on regression training techniques. This box map comprises a set of vectors, each designed to produce bounding boxes corresponding to the positions of objects in the input image. The channel and spatial contextualized sub-network are further designed to learn a "box map". In comparison to renowned proposal-free detectors such as CornerNet, CenterNet, and You Look Only Once (YOLO), PF-FCN utilizes a fully convolutional, single-pass method. By reducing the need for fully connected layers and filtering center points, the method considerably reduces the number of trained parameters and optimizes the scalability across varying input sizes. Evaluations of benchmark datasets suggest the effectiveness of PF-FCN: the proposed model achieved an mAP of 89.6% on PASCAL VOC 2012 and 71.7% on MS COCO, which are higher than those of the baseline Fully Convolutional One-Stage Detector (FCOS) and other classical proposal-free detectors. The results prove the significance of proposal-free detectors in both practical applications and future research.

An adaptive ensemble deep learning framework for reliable detection of pandemic patients

Nurses, often considered the backbone of global health services, are disproportionately vulnerable to COVID-19 due to their front-line roles. They conduct essential patient tests, including blood pressure, temperature, and complete blood counts. The pandemic-induced loss of nursing staff has resulted in critical shortages. To address this, robotic solutions offer promising avenues. To solve this problem, we developed an ensemble deep learning (DL) model that uses seven different models to detect patients. Detected images are then used as input for the soft robot, which performs basic assessment tests. In this study, we introduce a deep learning-based approach for nursing soft robots, and propose a novel deep learning model named Deep Ensemble of Adaptive Architectures. Our method is twofold: firstly, an ensemble deep learning technique detects COVID-19 patients; secondly, a soft robot performs basic assessment tests on the identified patients. We evaluate the performance of various deep learning-based object detectors for patient detection, examining implementations of You Only Look Once (YOLO), Single Shot MultiBox Detector (SSD), Region-Based Convolutional Neural Network (RCNN), and Region-Based Fully Convolutional Network (R-FCN) on a proprietary dataset comprising 32,668 hospital surveillance images. Our results indicate that while YOLO and VGG facilitate rapid detection, Faster-RCNN (Inception ResNet-v2) and our proposed Ensemble-DL achieve the highest accuracy. Ensemble-DL offers accurate results in a reasonable timeframe, making it apt for patient detection on embedded platforms. Through real-world experiments, our method outperforms baseline approaches (including Faster-RCNN, R-FCN variants, CNN+LSTM, etc.) in terms of both precision and recall. Achieving an impressive accuracy of 98.32%, our deep learning-based model for nursing soft robots presents a significant advancement in the identification and assessment of COVID-19 patients, ultimately enhancing healthcare efficiency and patient care.

A Novel Approach for Human Face Extraction and Detection using SAE-AFB-RFCN Framework

Research into Facial Recognition Technology (FRT), which uses a person's face to identify them, has become a hot topic among scientists. Face recognition relies heavily on feature extraction and classifiers. Occlusion, illuminations, and a complicated background provide the most difficult problems for face recognition systems to overcome. With the advent of Artificial Intelligence and Deep Learning techniques now it became easy to identify different features of an Image and to detect a face. In this paper, Stacked Auto Encoder (SAE), Artificial Feeding Bird (AFB), Region Based Fully Convolutional Network (RFCN), novel approach is developed for human face feature extraction and detection. Initially, the dataset is normalized using rescaling method. Then the Stacked Auto Encoder with Artificial Feeding Birds (SAE-AFB) optimization algorithm is used for facial feature extraction and Region based Fully Convolutional Networks (R-FCN) algorithm is used for detection and classification. The WIDER Face dataset is used for training and testing. Experimental results demonstrate that the proposed SAE-AFB-RFCN framework outperforms the existing algorithms in terms of accuracy, precision, recall and F1-score.

Human Detection and Action Recognition for Search and Rescue in Disasters Using YOLOv3 Algorithm

Drone examination has been overall quickly embraced by NDMM (natural disaster mitigation and management) division to survey the state of impacted regions. Manual video analysis by human observers takes time and is subject to mistakes. The human identification examination of pictures caught by drones will give a practical method for saving lives who are being trapped under debris during quakes or in floods and so on. Drone investigation for research and security and search and rescue (SAR) should involve the drone to filter the impacted area using a camera and a model of unmanned area vehicles (UAVs) to identify specific locations where assistance is required. The existing methods (Balmukund et al. 2020) used were faster-region based convolutional neural networks (F-RCNNs), single shot detector (SSD), and region-based fully convolutional network (R-FCN) for the detection of human and recognition of action. Some of the existing methods used 700 images with six classes only, whereas the proposed model uses 1996 images with eight classes. The proposed model is used YOLOv3 (you only look once) algorithm for the detection and recognition of actions. In this study, we provide the fundamental ideas underlying an object detection model. To find the most effective model for human recognition and detection, we trained the YOLOv3 algorithm on the image dataset and evaluated its performance. We compared the outcomes with the existing algorithms like F-RCNN, SSD, and R-FCN. The accuracies of F-RCNN, SSD, R-FCN (existing algorithms), and YOLOv3 (proposed algorithm) are 53%, 73%, 93%, and 94.9%, respectively. Among these algorithms, the YOLOv3 algorithm gives the highest accuracy of 94.9%. The proposed work shows that existing models are inadequate for critical applications like search and rescue, which convinces us to propose a model raised by a pyramidal component extracting SSD in human localization and action recognition. The suggested model is 94.9% accurate when applied to the proposed dataset, which is an important contribution. Likewise, the suggested model succeeds in helping time for expectation in examination with the cutting-edge identification models with existing strategies. The average time taken by our proposed technique to distinguish a picture is 0.40 milisec which is a lot better than the existing method. The proposed model can likewise distinguish video and can be utilized for real-time recognition. The SSD model can likewise use to anticipate messages if present in the picture.

Classification and identification of garment images based on deep learning

The clothing images on the Internet is growing rapidly, and there is an increasing demand for the clothing images’ intelligent classification. In this paper, Region-Based Fully Convolutional Networks (R-FCN) is introduced into the clothing image recognition. In the clothing image classification, because the network training time is long and the recognition rate of deformed clothing images is low, an improved framework HSR-FCN is proposed. The regional suggestion network and HyperNet network in R-FCN are integrated in the new framework, the learning approach of image features is changed in HSR-FCN, the higher accuracy can be achieved in a shorter training time. A spatial transformation network is introduced into the model, the input clothing image and feature map are spatially transformed and aligned, the feature learning is strengthened for multi-angle clothing and deformed clothing. The experimental results show that the improved HSR-FCN model is used to strengthen effectively the learning of deformed clothing images, and with a shorter training time, the average accuracy rate of the original network model R-FCN is increased by about 3%, it reachs 96.69%.

Hybrid Convolutional Neural Network for Plant Diseases Prediction

Plant diseases prediction is the essential technique to prevent the yield loss and gain high production of agricultural products. The monitoring of plant health continuously and detecting the diseases is a significant for sustainable agriculture. Manual system to monitor the diseases in plant is time consuming and report a lot of errors. There is high demand for technology to detect the plant diseases automatically. Recently image processing approach and deep learning approach are highly invited in detection of plant diseases. The diseases like late blight, bacterial spots, spots on Septoria leaf and yellow leaf curved are widely found in plants. These are the main reasons to affects the plants life and yield. To identify the diseases earliest, our research presents the hybrid method by combining the region based convolutional neural network (RCNN) and region based fully convolutional networks (RFCN) for classifying the diseases. First the leaf images of plants are collected and preprocessed to remove noisy data in image. Further data normalization, augmentation and removal of background noises are done. The images are divided as testing and training, training images are fed as input to deep learning architecture. First, we identify the region of interest (RoI) by using selective search. In every region, feature of convolutional neural network (CNN) is extracted independently for further classification. The plants such as tomato, potato and bell pepper are taken for this experiment. The plant input image is analyzed and classify as healthy plant or unhealthy plant. If the image is detected as unhealthy, then type of diseases the plant is affected will be displayed. Our proposed technique achieves 98.5% of accuracy in predicting the plant diseases.

A weight optimization-based transfer learning approach for plant disease detection of New Zealand vegetables.

Deep learning (DL) is an effective approach to identifying plant diseases. Among several DL-based techniques, transfer learning (TL) produces significant results in terms of improved accuracy. However, the usefulness of TL has not yet been explored using weights optimized from agricultural datasets. Furthermore, the detection of plant diseases in different organs of various vegetables has not yet been performed using a trained/optimized DL model. Moreover, the presence/detection of multiple diseases in vegetable organs has not yet been investigated. To address these research gaps, a new dataset named NZDLPlantDisease-v2 has been collected for New Zealand vegetables. The dataset includes 28 healthy and defective organs of beans, broccoli, cabbage, cauliflower, kumara, peas, potato, and tomato. This paper presents a transfer learning method that optimizes weights obtained through agricultural datasets for better outcomes in plant disease identification. First, several DL architectures are compared to obtain the best-suited model, and then, data augmentation techniques are applied. The Faster Region-based Convolutional Neural Network (RCNN) Inception ResNet-v2 attained the highest mean average precision (mAP) compared to the other DL models including different versions of Faster RCNN, Single-Shot Multibox Detector (SSD), Region-based Fully Convolutional Networks (RFCN), RetinaNet, and EfficientDet. Next, weight optimization is performed on datasets including PlantVillage, NZDLPlantDisease-v1, and DeepWeeds using image resizers, interpolators, initializers, batch normalization, and DL optimizers. Updated/optimized weights are then used to retrain the Faster RCNN Inception ResNet-v2 model on the proposed dataset. Finally, the results are compared with the model trained/optimized using a large dataset, such as Common Objects in Context (COCO). The final mAP improves by 9.25% and is found to be 91.33%. Moreover, the robustness of the methodology is demonstrated by testing the final model on an external dataset and using the stratified k-fold cross-validation method.

Non-intrusive load identification method based on color encoding and improve R-FCN

In the non-invasive load identification task, feature overlap exists when only a single load feature is used to identify equipment, which cannot meet the requirements of fine-grained equipment classification. Therefore, this paper proposes a non-invasive fine-grained load identification method based on color coding. Firstly, the Fryze power theory is used to decompose the high-frequency sampling current into active and reactive current, and the high-frequency sampling voltage and trace image are obtained. Then, the trajectory image is processed by color coding technology, and the active current, trajectory change information and instantaneous power are fused in R, G and B channels respectively to obtain the color V-I trajectory image. Finally, the Region-based fully Convolutional Networks (R-FCN) model is constructed to extract features from color V-I track images and realize device classification. On this basis, an autonomous learning method is proposed to update the load identification model autonomously. The recognition effect of the algorithm and the autonomous learning method were tested using PLAID data set. The results show that the proposed method increases the amount of information carried by V-I trajectory and enhances the uniqueness of load characteristics, thus realizing fine-grained identification of equipment. The self-learning method can learn new electrical appliances and update the model, which improves the adaptability of load identification model.

Enhanced Multi-Task Learning Architecture for Detecting Pedestrian at Far Distance

Existing pedestrian detection methods suffer from performance degradation in the presence of small-scale pedestrians who are positioned at far distance from the camera. We present a pedestrian detection framework that is not only robust to small- and large-scale pedestrians, but is also significantly faster than state-of-the-art methods. The proposed framework incorporates semantic segmentation to confidence modules for RPN (Region Proposal Network) head and R-FCN (Region-based Fully Convolutional Networks) head, and a cascaded R-FCN head. The semantic segmentation confidence is extracted and utilized as auxiliary classification prior knowledge for RPN proposal selection and R-FCN head prediction. Finally, the cascaded R-FCN head progressively refine the pedestrian prediction accuracy with negligible computation overhead. The proposed framework is also capable of maintaining high detection performance on down-sampled input images, which leads to further reduction in overall computational complexity. Experiment results on CityPersons and MOT17Det datasets show that the proposed framework achieves competitive detection performance with about <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$3\times $ </tex-math></inline-formula> speedup over state-of-the-art methods.

Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms.

The accurate identification of weeds is an essential step for a site-specific weed management system. In recent years, deep learning (DL) has got rapid advancements to perform complex agricultural tasks. The previous studies emphasized the evaluation of advanced training techniques or modifying the well-known DL models to improve the overall accuracy. In contrast, this research attempted to improve the mean average precision (mAP) for the detection and classification of eight classes of weeds by proposing a novel DL-based methodology. First, a comprehensive analysis of single-stage and two-stage neural networks including Single-shot MultiBox Detector (SSD), You look only Once (YOLO-v4), EfficientDet, CenterNet, RetinaNet, Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Network (RFCN), has been performed. Next, the effects of image resizing techniques along with four image interpolation methods have been studied. It led to the final stage of the research through optimization of the weights of the best-acquired model by initialization techniques, batch normalization, and DL optimization algorithms. The effectiveness of the proposed work is proven due to a high mAP of 93.44% and validated by the stratified k-fold cross-validation technique. It was 5.8% improved as compared to the results obtained by the default settings of the best-suited DL architecture (Faster RCNN ResNet-101). The presented pipeline would be a baseline study for the research community to explore several tasks such as real-time detection and reducing the computation/training time. All the relevant data including the annotated dataset, configuration files, and inference graph of the final model are provided with this article. Furthermore, the selection of the DeepWeeds dataset shows the robustness/practicality of the study because it contains images collected in a real/complex agricultural environment. Therefore, this research would be a considerable step toward an efficient and automatic weed control system.

Fault Diagnosis Method of Distribution Equipment Based on Hybrid Model of Robot and Deep Learning

In view of the poor effect of most fault diagnosis methods on the intelligent recognition of equipment images, a fault diagnosis method of distribution equipment based on the hybrid model of robot and deep learning is proposed to reduce the dependence on manpower and realize efficient intelligent diagnosis. Firstly, the robot is used to collect the on-site state images of distribution equipment to build the image information database of distribution equipment. At the same time, the robot background is used as the comprehensive database data analysis platform to optimize the sample quality of the database. Then, the massive infrared images are segmented based on chroma saturation brightness space to distinguish the defective equipment images, and the defective equipment areas are extracted from the images by OTSU method. Finally, the residual network is used to improve the region-based fully convolutional networks (R-FCN) algorithm, and the improved R-FCN algorithm trained by the online hard example mining method is used for fault feature learning. The fault type, grade, and location of distribution equipment are obtained through fault criterion analysis. The experimental analysis of the proposed method based on PyTorch platform shows that the fault diagnosis time and accuracy are about 5.5 s and 92.06%, respectively, which are better than other comparison methods and provide a certain theoretical basis for the automatic diagnosis of power grid equipment.

A Performance-Optimized Deep Learning-Based Plant Disease Detection Approach for Horticultural Crops of New Zealand

Deep learning-based plant disease detection has gained significant attention from the scientific community. However, various aspects of real horticultural conditions have not yet been explored. For example, the disease should be considered not only on leaves, but also on other parts of plants, including stems, canes, and fruits. Furthermore, the detection of multiple diseases in a single plant organ at a time has not been performed. Similarly, plant disease has not been identified in various crops in the complex horticultural environment with the same optimized/modified model. To address these research gaps, this research presents a dataset named NZDLPlantDisease-v1, consisting of diseases in five of the most important horticultural crops in New Zealand: kiwifruit, apple, pear, avocado, and grapevine. An optimized version of the best obtained deep learning (DL) model named region-based fully convolutional network (RFCN) has been proposed to detect plant disease using the newly generated dataset. After final the most suitable DL model, data augmentation techniques were successively evaluated. Subsequently, the effects of image resizers with interpolators, weight initializers, batch normalization, and DL optimizers were studied. Finally, performance was enhanced by empirical observation of position-sensitive score maps and anchor box specifications. Furthermore, the robustness/practicality of the proposed approach was demonstrated using a stratified k-fold cross-validation technique and testing on an external dataset. The final mean average precision of the RFCN model was found to be 93.80%, which was 19.33% better than the default settings. Therefore, this research could be a benchmark step for any follow-up research on automatic control of disease in several plant species.

Beet seedling and weed recognition based on convolutional neural network and multi-modality images

Difficulties in the recognition of beet seedlings and weeds can arise from a complex background in the natural environment and a lack of light at night. In the current study, a novel depth fusion algorithm was proposed based on visible and near-infrared imagery. In particular, visible (RGB) and near-infrared images were superimposed at the pixel-level via a depth fusion algorithm and were subsequently fused into three-channel multi-modality images in order to characterize the edge details of beets and weeds. Moreover, an improved region-based fully convolutional network (R-FCN) model was applied in order to overcome the geometric modeling restriction of traditional convolutional kernels. More specifically, for the convolutional feature extraction layers, deformable convolution was adopted to replace the traditional convolutional kernel, allowing for the entire network to extract more precise features. In addition, online hard example mining was introduced to excavate the hard negative samples in the detection process for the retraining of misidentified samples. A total of four models were established via the aforementioned improved methods. Results demonstrate that the average precision of the improved optimal model for beets and weeds were 84.8% and 93.2%, respectively, while the mean average precision was improved to 89.0%. Compared with the classical R-FCN model, the performance of the optimal model was not only greatly improved, but the parameters were also not significantly expanded. Our study can provide a theoretical basis for the subsequent development of intelligent weed control robots under weak light conditions.

Sugar Beet Damage Detection during Harvesting Using Different Convolutional Neural Network Models

Mechanical damages of sugar beet during harvesting affects the quality of the final products and sugar yield. The mechanical damage of sugar beet is assessed randomly by operators of harvesters and can depend on the subjective opinion and experience of the operator due to the complexity of the harvester machines. Thus, the main aim of this study was to determine whether a digital two-dimensional imaging system coupled with convolutional neural network (CNN) techniques could be utilized to detect visible mechanical damage in sugar beet during harvesting in a harvester machine. In this research, various detector models based on the CNN, including You Only Look Once (YOLO) v4, region-based fully convolutional network (R-FCN) and faster regions with convolutional neural network features (Faster R-CNN) were developed. Sugar beet image data during harvesting from a harvester in different farming conditions were used for training and validation of the proposed models. The experimental results showed that the YOLO v4 CSPDarknet53 method was able to detect damage in sugar beet with better performance (recall, precision and F1-score of about 92, 94 and 93%, respectively) and higher speed (around 29 frames per second) compared to the other developed CNNs. By means of a CNN-based vision system, it was possible to automatically detect sugar beet damage within the sugar beet harvester machine.

Research on Recognition and Location Method of Insulator in Infrared Image Based on Deep Learning

Infrared thermography technology is widely used in the thermal condition detection of insulators due to its advantages of non-contact, sensitive, online detection. To realize the automatic detection of the operating condition of insulators in complex environments, this paper proposes a method for the recognition and location of the insulator based on Region-based Fully Convolutional Networks (R-FCN). The model was trained and tested on the constructed insulator infrared data set, compared with the SSD model. The results showed that the R-FCN detecting insulators can not only accurately locate insulators, but have an AP (average precision) value as high as 89.2%. Therefore, the findings in this paper have verified that R-FCN has great advantages in the recognition and location of infrared images of insulators and has practical application value.

Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image.

This exploration primarily aims to jointly apply the local FCN (fully convolution neural network) and YOLO-v5 (You Only Look Once-v5) to the detection of small targets in remote sensing images. Firstly, the application effects of R-CNN (Region-Convolutional Neural Network), FRCN (Fast Region-Convolutional Neural Network), and R-FCN (Region-Based-Fully Convolutional Network) in image feature extraction are analyzed after introducing the relevant region proposal network. Secondly, YOLO-v5 algorithm is established on the basis of YOLO algorithm. Besides, the multi-scale anchor mechanism of Faster R-CNN is utilized to improve the detection ability of YOLO-v5 algorithm for small targets in the image in the process of image detection, and realize the high adaptability of YOLO-v5 algorithm to different sizes of images. Finally, the proposed detection method YOLO-v5 algorithm + R-FCN is compared with other algorithms in NWPU VHR-10 data set and Vaihingen data set. The experimental results show that the YOLO-v5 + R-FCN detection method has the optimal detection ability among many algorithms, especially for small targets in remote sensing images such as tennis courts, vehicles, and storage tanks. Moreover, the YOLO-v5 + R-FCN detection method can achieve high recall rates for different types of small targets. Furthermore, due to the deeper network architecture, the YOL v5 + R-FCN detection method has a stronger ability to extract the characteristics of image targets in the detection of remote sensing images. Meanwhile, it can achieve more accurate feature recognition and detection performance for the densely arranged target images in remote sensing images. This research can provide reference for the application of remote sensing technology in China, and promote the application of satellites for target detection tasks in related fields.

A visual fingerprint update algorithm based on crowdsourced localization and deep learning for smart IoV

Recently, deep learning and vision-based technologies have shown their great significance for the prospective development of smart Internet of Vehicle (IoV). When the smart vehicle enters the indoor parking of a shopping mall, the vision-based localization technology can provide reliable parking service. As known, the vision-based technique relies on a visual map without a change in the position of the reference object. Although, some researchers have proposed a few automatic visual fingerprinting (AVF) methods, which are aiming at reducing the cost of building the visual map database. However, the AVF method still costs too much under such a situation, since it is impossible to determine the specific location of the displaced object. Given the smart IoV and the development of deep learning approach, we propose an algorithm for solving the problem based on crowdsourcing and deep learning in this paper. Firstly, we propose a Region-based Fully Convolutional Network (R-FCN) based method with the feedback of crowdsourced images to locate the specific displaced object in the visual map database. Secondly, we propose a method based on quadratic programming (QP) for solving the translation vector of the displaced objects, which finally solves the problem of updating the visual map database. The simulation results show that our method can provide a higher detection sensitivity and correction accuracy as well as the relocation results. It means that our proposed algorithm outperforms the compared one, which is verified by both synthetic and real data simulation.

RETRACTED: Road Object Detection: A Comparative Study of Deep Learning-Based Algorithms

Automated driving and vehicle safety systems need object detection. It is important that object detection be accurate overall and robust to weather and environmental conditions and run in real-time. As a consequence of this approach, they require image processing algorithms to inspect the contents of images. This article compares the accuracy of five major image processing algorithms: Region-based Fully Convolutional Network (R-FCN), Mask Region-based Convolutional Neural Networks (Mask R-CNN), Single Shot Multi-Box Detector (SSD), RetinaNet, and You Only Look Once v4 (YOLOv4). In this comparative analysis, we used a large-scale Berkeley Deep Drive (BDD100K) dataset. Their strengths and limitations are analyzed based on parameters such as accuracy (with/without occlusion and truncation), computation time, precision-recall curve. The comparison is given in this article helpful in understanding the pros and cons of standard deep learning-based algorithms while operating under real-time deployment restrictions. We conclude that the YOLOv4 outperforms accurately in detecting difficult road target objects under complex road scenarios and weather conditions in an identical testing environment.

An Efficient and Robust Target Detection Algorithm for Identifying Minor Defects of Printed Circuit Board Based on PHFE and FL-RFCN

For ensuring the safety and reliability of electronic equipment, it is a necessary task to detect the surface defects of the printed circuit board (PCB). Due to the smallness, complexity and diversity of minor defects of PCB, it is difficult to identify minor defects in PCB with traditional methods. And the target detection method based on deep learning faces the problem of imbalance between foreground and background when detecting minor defects. Therefore, this paper proposes a minor defect detection method on PCB based on FL-RFCN (focal loss and Region-based Fully Convolutional Network) and PHFE (parallel high-definition feature extraction). Firstly, this paper uses the Region-based Fully Convolutional Network(R-FCN) to identify minor defects on the PCB. Secondly, the focal loss is used to solve the problem of data imbalance in neural networks. Thirdly, the parallel high-definition feature extraction algorithm is used to improve the recognition rate of minor defects. In the detection of minor defects on PCB, the ablation experiment proves that the mean Average accuracy (mAP) of the proposed method is increased by 7.4. In comparative experiments, it is found that the mAP of the method proposed in this paper is 12.3 higher than YOLOv3 and 6.7 higher than Faster R-CNN.