Convolutional Neural Network-based Method Research Articles

Lost data reconstruction for structural health monitoring by parallel mixed Transformer-CNN network

Transformer-based and convolutional neural network-based deep learning methods have been extensively utilized to reconstruct lost data for structural health monitoring. However, the lack of inductive bias in Transformer and the fixed receptive fields of convolutional neural network (CNN) limit their local and global modeling capabilities, respectively. The traditional method of combining the two in series creates a sequential relationship and interdependence, negatively impacting reconstruction accuracy. To address this problem, this paper proposes a novel parallel mixed Transformer-CNN network. By parallel connecting the shifted window transformer and densely connected convolutional block, both can process structural vibration responses simultaneously and independently, leveraging the locality of convolution to address the inductive bias of Transformer. Experiments on real acceleration data from the Canton Tower validate its effectiveness. Compared with models using only Transformer or CNN, the reconstruction errors are reduced by 56% and 17%, respectively. The modal parameters extracted from the reconstructed data are highly consistent with those from the true data, and our model has good robustness to lost rates and noise.

A Convolutional Neural Network-Based Method for Distinguishing the Flow Patterns of Gas-Liquid Two-Phase Flow in the Annulus

In order to improve the accuracy and efficiency of flow pattern recognition and to solve the problem of the real-time monitoring of flow patterns, which is difficult to achieve with traditional visual recognition methods, this study introduced a flow pattern recognition method based on a convolutional neural network (CNN), which can recognize the flow pattern under different pressure and flow conditions. Firstly, the complex gas–liquid distribution and its velocity field in the annulus were investigated using a computational fluid dynamics (CFDs) simulation, and the gas–liquid distribution and velocity vectors in the annulus were obtained to clarify the complexity of the flow patterns in the annulus. Subsequently, a sequence model containing three convolutional layers and two fully connected layers was developed, which employed a CNN architecture, and the model was compiled using the Adam optimizer and the sparse classification cross entropy as a loss function. A total of 450 images of different flow patterns were utilized for training, and the trained model recognized slug and annular flows with probabilities of 0.93 and 0.99, respectively, confirming the high accuracy of the model in recognizing annulus flow patterns, and providing an effective method for flow pattern recognition.

Convolutional Neural Network-Based Deep Learning Methods for Skeletal Growth Prediction in Dental Patients.

This study aimed to predict the skeletal growth maturation using convolutional neural network-based deep learning methods using cervical vertebral maturation and the lower 2nd molar calcification level so that skeletal maturation can be detected from orthopantomography using multiclass classification. About 1200 cephalometric radiographs and 1200 OPGs were selected from patients seeking treatment in dental centers. The level of skeletal maturation was detected by CNN using the multiclass classification method, and each image was identified as a cervical vertebral maturation index (CVMI); meanwhile, the chronological age was estimated from the level of the 2nd molar calcification. The model's final result demonstrates a high degree of accuracy with which each stage and gender can be predicted. Cervical vertebral maturation reported high accuracy in males (98%), while females showed high accuracy of 2nd molar calcification. CNN multiclass classification is an accurate method to detect the level of maturation, whether from cervical maturation or the calcification of the lower 2nd molar, and the calcification level of the lower 2nd molar is a reliable method to trust in the growth level, so the traditional OPG is enough for this purpose.

Temporomandibular joint CBCT image segmentation via multi-view ensemble learning network.

Accurate segmentation of the temporomandibular joint (TMJ) from cone beam CT (CBCT) images holds significant clinical value for diagnosing temporomandibular joint osteoarthrosis (TMJOA) and related conditions. Convolutional neural network-based medical image segmentation methods have achieved state-of-the-art performance in various segmentation tasks. However, 3D medical images segmentation requires substantial global context and rich spatial semantic information, demanding much more GPU memory and computational resources. To address these challenges in 3D medical image segmentation, we propose a novel network- the MVEL-Net (Multi-view Ensemble Learning Network) for TMJ CBCT image segmentation. By resampling images along three dimensions, we generate multiple weak learners with different spatial semantic information. A subsequent strong learning network effectively integrates the outputs from these weak learners to achieve more accurate segmentation results. We evaluated our network model using a clinical dataset comprising 88 subjects with TMJ CBCT images. The average Dice similarity coefficient (DSC) was 0.9817 ± 0.0049, the average surface distance was 0.0540 ± 0.0179mm, and the 95% Hausdorff distance was 0.1743 ± 0.0550mm. Our proposed MVEL-Net demonstrates excellent segmentation performance on TMJ from CBCT images, while using fewer GPU memory resources compared to other 3D networks. The effectiveness of this method in capturing spatial context could be leveraged for tasks like organ segmentation from volumetric scans. This may facilitate wider adoption of AI-based solutions for automated analysis of 3D medical images.

Tree Sequences as a General-Purpose Tool for Population Genetic Inference.

As population genetic data increase in size, new methods have been developed to store genetic information in efficient ways, such as tree sequences. These data structures are computationally and storage efficient but are not interchangeable with existing data structures used for many population genetic inference methodologies such as the use of convolutional neural networks applied to population genetic alignments. To better utilize these new data structures, we propose and implement a graph convolutional network to directly learn from tree sequence topology and node data, allowing for the use of neural network applications without an intermediate step of converting tree sequences to population genetic alignment format. We then compare our approach to standard convolutional neural network approaches on a set of previously defined benchmarking tasks including recombination rate estimation, positive selection detection, introgression detection, and demographic model parameter inference. We show that tree sequences can be directly learned from using a graph convolutional network approach and can be used to perform well on these common population genetic inference tasks with accuracies roughly matching or even exceeding that of a convolutional neural network-based method. As tree sequences become more widely used in population genetic research, we foresee developments and optimizations of this work to provide a foundation for population genetic inference moving forward.

A dual encoder LDCT image denoising model based on cross-scale skip connections

LDCT image denoising is crucial in medical imaging as it aims to minimize patient radiation exposure while maintaining diagnostic image quality. However, current convolutional neural network-based denoising methods struggle to incorporate global contexts, often focusing solely on local features. This limitation poses a significant challenge. To address this, a dual encoder denoising model is introduced that utilizes the Transformer model’s proficiency in capturing long-range dependencies and global context. This model integrates the Transformer branch and the convolutional branch in the encoder. By concatenating the features of these two different branches, the model can capture both global and local image features, substantially enhancing denoising efficacy. A cross-scale skip connection mechanism is introduced to integrate the encoder’ s low-level features with the decoder’ s high-level features, enriching contextual information and preserving image details. In addition, to meet the requirements of multi-scale feature fusion, the decoder is equipped with different multi-scale convolution modules to optimize feature processing. The number of layers in these modules gradually decreases as the depth of the decoder increases. In order to enhance the discriminative ability of the model, a multi-scale discriminator is also introduced, which effectively improves the recognition ability of the image by extracting features from four different scales. Consequently, our approach demonstrates remarkable performance in reducing noise and improving LDCT image quality, as evidenced by the substantial improvements in PSNR (17.75%) and SSIM (7.31%) values.

ThyFusion: A lightweight attribute enhancement module for thyroid nodule diagnosis using gradient and frequency-domain awareness

Accurate classification of thyroid nodules is a critical step in clinical diagnosis and plays a crucial role in guiding subsequent treatment planning. However, current deep learning methods lack the ability to effectively perceive the attributes of thyroid nodules. Specifically, convolutional neural network-based methods struggle to capture fine-grained attributes, such as echogenic foci, due to repeated downsampling operations. On the other hand, Transformer-based methods partition the image into blocks, which hinders the capture of continuous attributes such as margins, and require a large number of parameters. To overcome these limitations, this paper proposes a novel lightweight attribute enhancement module called ThyFusion. Firstly, a multi-scale Gaussian filtering attention module is developed to accurately capture fine-grained information. Secondly, a frequency-domain global regulation module is proposed to regulate global features and capture coarse-grained attributes. Finally, a cross domain mutual learning module is presented to fuse fine-grained and coarse-grained attributes. Extensive experiments were conducted to demonstrate the effectiveness of ThyFusion, and it was compared against 15 benchmark methods. ThyFusion achieves higher accuracy, F1 score, recall, and precision (87.18%, 87.12%, 87.36% and 87.10%). ThyFusion is a plug-and-play lightweight module that can be embedded behind any layer of a backbone network to enhance the accuracy of thyroid nodule classification. The advantages of ThyFusion in thyroid nodule classification can greatly streamline the process of automated diagnosis and improve the accuracy of thyroid diagnosis.

Measurement method of flexible component pose based on discrete motion actuators

Abstract In order to address the limitations of traditional large discrete motion actuator mechanisms in realizing high-precision inter-axis relationship calibration in manufacturing environments, this paper proposes a new convolutional neural network-based attitude mapping estimation method, component pose using convolutional neural network (CPCNN). The method implicitly encodes the inter-axis relation matrix into the weight parameters of the training neural network, which results in a high degree of integration with existing large discrete motion actuator mechanisms. The CPCNN-based method directly obtains the attitude change of the adjustment cabin by reading the change of each axis of the current motion actuator mechanism in its own coordinate system. This method can overcome the limitations of the experimental process in the traditional calibration methods and improve the accuracy of attitude mapping under the influence of self-weight by selecting better motion parameters through redundant degrees of freedom. The application of this new method will provide an effective solution for the high-precision inter-axis relationship calibration of large discrete motion actuator mechanisms in manufacturing environments, offering new possibilities for improving production efficiency and product quality.

A Convolutional Neural Network-Based Defect Recognition Method for Power Insulator

As the scale of the power grid rapidly expands, its operation becomes increasingly complex, with higher demands on personnel proficiency, grid stability, equipment safety, and operational efficiency. In this study, a novel power insulator defect detection method based on convolutional neural networks (CNNs) is proposed. This method innovatively combines the feature extraction advantages of deep learning to build an efficient binary classification model capable of accurately detecting defects in power insulators in complex backgrounds. To avoid the impact of a small dataset on model performance, transfer learning was employed during model training to enhance the model’s generalization ability. A combination of Grid Search and Random Search was used for hyperparameter tuning, and the Early Stopping strategy was introduced to effectively prevent the model from overfitting to the training set, ensuring generalization performance on the validation set. Experimental results show that the proposed method achieves an average accuracy of 98.6%, a recall of 96.8%, and an F1 score of 97.7% on the test set. Compared to traditional Faster RCNN and PCA-SVM methods, the proposed CNN model significantly improves detection accuracy and computational efficiency in complex backgrounds, exhibiting superior recognition precision and model generalization ability for efficiently and accurately identifying defective insulators.

Self-Supervised 3D Semantic Occupancy Prediction from Multi-View 2D Surround Images

An accurate 3D representation of the geometry and semantics of an environment builds the basis for a large variety of downstream tasks and is essential for autonomous driving related tasks such as path planning and obstacle avoidance. The focus of this work is put on 3D semantic occupancy prediction, i.e., the reconstruction of a scene as a voxel grid where each voxel is assigned both an occupancy and a semantic label. We present a Convolutional Neural Network-based method that utilizes multiple color images from a surround-view setup with minimal overlap, together with the associated interior and exterior camera parameters as input, to reconstruct the observed environment as a 3D semantic occupancy map. To account for the ill-posed nature of reconstructing a 3D representation from monocular 2D images, the image information is integrated over time: Under the assumption that the camera setup is moving, images from consecutive time steps are used to form a multi-view stereo setup. In exhaustive experiments, we investigate the challenges presented by dynamic objects and the possibilities of training the proposed method with either 3D or 2D reference data. Latter being motivated by the comparably higher costs of generating and annotating 3D ground truth data. Moreover, we present and investigate a novel self-supervised training scheme that does not require any geometric reference data, but only relies on sparse semantic ground truth. An evaluation on the Occ3D dataset, including a comparison against current state-of-the-art self-supervised methods from the literature, demonstrates the potential of our self-supervised variant.

Monocular Pose and Shape Reconstruction of Vehicles in UAV imagery using a Multi-task CNN

Estimating the pose and shape of vehicles from aerial images is an important, yet challenging task. While there are many existing approaches that use stereo images from street-level perspectives to reconstruct objects in 3D, the majority of aerial configurations used for purposes like traffic surveillance are limited to monocular images. Addressing this challenge, a Convolutional Neural Network-based method is presented in this paper, which jointly performs detection, pose, type and 3D shape estimation for vehicles observed in monocular UAV imagery. For this purpose, a robust 3D object model is used following the concept of an Active Shape Model. In addition, different variants of loss functions for learning 3D shape estimation are presented, focusing on the height component, which is particularly challenging to estimate from monocular near-nadir images. We also introduce a UAV-based dataset to evaluate our model in addition to an augmented version of the publicly available Hessigheim benchmark dataset. Our method yields promising results in pose and shape estimation: utilising images with a ground sampling distance (GSD) of 3 cm, it achieves median errors of up to 4 cm in position and 3° in orientation. Additionally, it achieves root mean square (RMS) errors of \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm 6$$\\end{document} cm in planimetry and \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm 18$$\\end{document} cm in height for keypoints defining the car shape.

A Texture-Considerate Convolutional Neural Network Approach for Color Consistency in Remote Sensing Imagery

Remote sensing allows us to conduct large-scale scientific studies that require extensive mapping and the amalgamation of numerous images. However, owing to variations in radiation, atmospheric conditions, sensor perspectives, and land cover, significant color discrepancies often arise between different images, necessitating color consistency adjustments for effective image mosaicking and applications. Existing methods for color consistency adjustment in remote sensing images struggle with complex one-to-many nonlinear color-mapping relationships, often resulting in texture distortions. To address these challenges, this study proposes a convolutional neural network-based color consistency method for remote sensing cartography that considers both global and local color mapping and texture mapping constrained by the source domain. This method effectively handles complex color-mapping relationships while minimizing texture distortions in the target image. Comparative experiments on remote sensing images from different times, sensors, and resolutions demonstrated that our method achieved superior color consistency, preserved fine texture details, and provided visually appealing outcomes, assisting in generating large-area data products.

Investigating the use of signal detection information in supervised learning-based image denoising with consideration of task-shift.

Recently, learning-based denoising methods that incorporate task-relevant information into the training procedure have been developed to enhance the utility of the denoised images. However, this line of research is relatively new and underdeveloped, and some fundamental issues remain unexplored. Our purpose is to yield insights into general issues related to these task-informed methods. This includes understanding the impact of denoising on objective measures of image quality (IQ) when the specified task at inference time is different from that employed for model training, a phenomenon we refer to as "task-shift." A virtual imaging test bed comprising a stylized computational model of a chest X-ray computed tomography imaging system was employed to enable a controlled and tractable study design. A canonical, fully supervised, convolutional neural network-based denoising method was purposely adopted to understand the underlying issues that may be relevant to a variety of applications and more advanced denoising or image reconstruction methods. Signal detection and signal detection-localization tasks under signal-known-statistically with background-known-statistically conditions were considered, and several distinct types of numerical observers were employed to compute estimates of the task performance. Studies were designed to reveal how a task-informed transfer-learning approach can influence the tradeoff between conventional and task-based measures of image quality within the context of the considered tasks. In addition, the impact of task-shift on these image quality measures was assessed. The results indicated that certain tradeoffs can be achieved such that the resulting AUC value was significantly improved and the degradation of physical IQ measures was statistically insignificant. It was also observed that introducing task-shift degrades the task performance as expected. The degradation was significant when a relatively simple task was considered for network training and observer performance on a more complex one was assessed at inference time. The presented results indicate that the task-informed training method can improve the observer performance while providing control over the tradeoff between traditional and task-based measures of image quality. The behavior of a task-informed model fine-tuning procedure was demonstrated, and the impact of task-shift on task-based image quality measures was investigated.

A comparative experimental research on the diagnosis of tooth root cracks in asymmetric spur gear pairs with a one-dimensional convolutional neural network

Gearboxes transfer rotational motion and handle precision functionalities in many fields, including aviation, wind turbines, and industrial services. Their health management is essential to minimize workforce risks, increase the level of safety, and avoid machine breakdowns. From this standpoint, the present experimental research work developed a convolutional neural network-based method for diagnosing different levels of tooth root cracks (25 %-50 %-75 %-100 %) for symmetric (20°/20°) and asymmetric (20°/30°) profiled gear pairs. A series of vibration experiments were performed on a one-stage spur gearbox to achieve this by using a tri-axial accelerometer under variable working loads. The main purpose of this experimental research study is to explore the influence of the tooth profile on spur gears’ vibration responses and whether utilizing an asymmetric tooth profile would positively impact a deep learning algorithm's classification accuracy to add to the enhancements it provides in terms of fatigue life, mesh stiffness, and impact strength. Experimental results revealed that the overall classification accuracy could be increased by 7.712 % by feeding the proposed deep learning model with vibration data measured using test samples with asymmetric teeth.

REDef-DETR: real-time and efficient DETR for industrial surface defect detection

Abstract Industrial surface defect detection is an important part of industrial production, which aims to identify and detecting various defects on the surface of product to ensure quality and meet customer requirements. With the development of deep learning and image processing technologies, the surface defect detection methods based on computer vision has become the mainstream method. However, the prevalent convolutional neural network-based defect detection methods also have many problems. For example, these methods rely on post-processing of Non-Maximum Suppression and have poor detection ability for small targets, which affects the speed and accuracy of surface defect detection in industrial scenarios. Therefore, we propose a novel DEtection TRansformer-based surface defect detection method. Firstly, we propose a Multi-scale Contextual Information Dilated module and fuse it into the backbone. The module is mainly composed of large kernel convolutions, which aims to expand the receptive field of the model, thus reducing the leakage rate of the model. Moreover, we design an efficient encoder which mainly contains two important modules, namely feature enhancement based on cascaded group attention module and efficient feature fusion module based on content-aware. The former module effectively enhances the high-level semantic information extracted by the backbone, thus enabling the model to better interpret features, and it can improve the problem of high computational cost of transformer encoder, thus increasing the detection speed. The latter module performs multi-scale feature fusion across the feature information of various scales, thus improving the detection accuracy of the model for small-size defects. Experimental results show that the proposed method achieves 80.6%mAP and 80.3FPS on NEU-DET, and 98.0%mAP and 79.4FPS on PCB-DET. Our proposed method exhibits excellent detection performance and achieves real-time and efficient surface defect detection capability to meet the needs of industrial surface defect detection.

DSnet: a new dual-branch network for hippocampus subfield segmentation

The hippocampus is a critical component of the brain and is associated with many neurological disorders. It can be further subdivided into several subfields, and accurate segmentation of these subfields is of great significance for diagnosis and research. However, the structures of hippocampal subfields are irregular and have complex boundaries, and their voxel values are close to surrounding brain tissues, making the segmentation task highly challenging. Currently, many automatic segmentation tools exist for hippocampal subfield segmentation, but they suffer from high time costs and low segmentation accuracy. In this paper, we propose a new dual-branch segmentation network structure (DSnet) based on deep learning for hippocampal subfield segmentation. While traditional convolutional neural network-based methods are effective in capturing hierarchical structures, they struggle to establish long-term dependencies. The DSnet integrates the Transformer architecture and a hybrid attention mechanism, enhancing the network’s global perceptual capabilities. Moreover, the dual-branch structure of DSnet leverages the segmentation results of the hippocampal region to facilitate the segmentation of its subfields. We validate the efficacy of our algorithm on the public Kulaga-Yoskovitz dataset. Experimental results indicate that our method is more effective in segmenting hippocampal subfields than conventional single-branch network structures. Compared to the classic 3D U-Net, our proposed DSnet improves the average Dice accuracy of hippocampal subfield segmentation by 0.57%.

Vision transformer-based robust learning for cloth-changing person re-identification

The domain of Cloth-Changing Person Re-identification has garnered substantial attention recently owing to its pivotal role in security applications. The essence of Cloth-Changing Person Re-identification lies in acquiring information unaffected by clothing variations, such as gait and silhouette. Most studies focus on the Convolutional Neural Network models. However, main drawback of Convolutional Neural Network is the limitation of receptive field. Methods based on Convolutional Neural Network primarily focus on modeling local information, making it complex to extract the discriminative part of multiple spatial contexts. Therefore, we proposed a Vision Transformer-based Cloth-Changing Person Re-identification framework called TransRL-ReID. Specifically, we encoded an image as a sequence of patches and constructed a Vision Transformer-based framework. In addition, a module named DropAll was designed to reduce local bias by adaptive adjustment of attention weights for each patch. We conducted extensive experiments on the real-world benchmark PRCC dataset. TransRL-ReID achieves 66.7% on Rank-1 and 60.0% on mean Average Precision, outperforming previous Convolutional Neural Network-based methods. After visual analysis of the results, we found that TransReID could extract information unrelated to clothing, such as gait and silhouette, and paid less attention to clothing information. DropAll improves the model’s ability to fit pedestrian distributions.

Multi kernel cross sparse graph attention convolutional neural network for brain magnetic resonance imaging super-resolution

High-resolution Magnetic Resonance Imaging (MRI) is pivotal in both diagnosing and treating brain tumors, assisting physicians in diagnosis and treatment by displaying anatomical structures. Utilizing convolutional neural network-based super-resolution methods enables the efficient acquisition of high-resolution MRI images.However, Convolutional neural networks are limited by their kernel size, which restricts their ability to capture a wider field of view, potentially leading to feature omission and difficulties in establishing global and local feature relationships. To overcome these shortcomings, We have designed a novel network architecture that highlights three main modules: (i) Multiple Convolutional Feature (MCF)extraction module, which diversifies convolution operations for extracting image features, achieving comprehensive feature representation. (ii) Multiple Groupss of Cross-Iterative Feature(MGCIF) modules, promoting inter-channel feature interactions and emphasizing crucial features needed for subsequent learning. (iii) A Graph Neural Network Module based on a sparse attention mechanism, capable of connecting distant pixel features and identifying influential neighboring pixels for target pixel inpainting. To evaluate the accuracy of our proposed network, we conducted tests on four datasets, comprising two sets of brain tumor data and two sets of healthy head MRI data, all of which underwent varying degrees of degradation. We conducted experiments using nineteen super-resolution (SR) models. Our experiments were carried out on four datasets, and the results demonstrate that our method outperforms the current leading-edge methods. In the four datasets, our model showed improvements in Peak Signal-to-Noise Ratio (PSNR) scores compared to the second-place model,with increase of 1.16 %,1.08 %,0.19 % and 0.53 % for ×2,and 2.26 %,1.67 %,0.13 % and 0.45 % for × 4,respectively.

A Convolutional Neural Network-Based Quantization Method for Block Compressed Sensing of Images.

Block compressed sensing (BCS) is a promising method for resource-constrained image/video coding applications. However, the quantization of BCS measurements has posed a challenge, leading to significant quantization errors and encoding redundancy. In this paper, we propose a quantization method for BCS measurements using convolutional neural networks (CNN). The quantization process maps measurements to quantized data that follow a uniform distribution based on the measurements' distribution, which aims to maximize the amount of information carried by the quantized data. The dequantization process restores the quantized data to data that conform to the measurements' distribution. The restored data are then modified by the correlation information of the measurements drawn from the quantized data, with the goal of minimizing the quantization errors. The proposed method uses CNNs to construct quantization and dequantization processes, and the networks are trained jointly. The distribution parameters of each block are used as side information, which is quantized with 1 bit by the same method. Extensive experiments on four public datasets showed that, compared with uniform quantization and entropy coding, the proposed method can improve the PSNR by an average of 0.48 dB without using entropy coding when the compression bit rate is 0.1 bpp.

A fiber recognition framework based on multi-head attention mechanism

Convolutional neural networks have been extensively studied in textile fiber recognition. However, the down-sampling performed by the convolutional and pooling layers on the extracted features result in a significant loss of fine-grained fiber features. To address this issue, a multi-head attention framework for fiber recognition has been proposed. First, textile surface images are captured using optical magnifiers and smart devices such as smartphones. Second, fiber features and label embeddings are learned separately by multi-head self-attention. Finally, the label embeddings are used to query the presence of fiber types, and pool type-related features in the multi-head cross-attention module to classify fibers. The experimental results demonstrate that the proposed method performs exceptionally well on the textile surface image dataset, with a mean average precision accuracy improvement of 6% compared with the convolutional neural network-based fiber recognition method Cu-Net, and a 5% improvement compared with the fiber recognition method FiberCT combining convolutional neural networks and attention mechanisms. It is worth mentioning that the fiber images captured at 200× magnification in the collected dataset are most favorable for models to recognize fiber. The proposed method achieves a mean average precision fiber recognition accuracy of 80.2% on images at 200× magnification.