Search Results (541)

In industries spanning manufacturing to software development, defect segmentation is essential for maintaining high standards of product quality and reliability. However, traditional segmentation methods often struggle to accurately identify defects due to challenges like noise interference, occlusion, and feature overlap. To solve these problems, we propose a cross-hierarchy feature fusion network based on a composite dual-channel encoder for surface defect segmentation, called CFF-Net. Specifically, in the encoder of CFF-Net, we design a composite dual-channel module (CDCM), which combines standard convolution with dilated convolution and adopts a dual-path parallel structure to enhance the model’s capability in feature extraction. Then, a dilated residual pyramid module (DRPM) is integrated at the junction of the encoder and decoder, which utilizes the expansion convolution of different expansion rates to effectively capture multi-scale context information. In the final output phase, we introduce a cross-hierarchy feature fusion strategy (CFFS) that combines outputs from different layers or stages, thereby improving the robustness and generalization of the network. Finally, we conducted comparative experiments to evaluate CFF-Net against several mainstream segmentation networks across three distinct datasets: a publicly available Crack500 dataset, a self-built Bearing dataset, and another publicly available SD-saliency-900 dataset. The results demonstrated that CFF-Net consistently outperformed competing methods in segmentation tasks. Specifically, in the Crack500 dataset, CFF-Net achieved notable performance metrics, including an Mcc of 73.36%, Dice coefficient of 74.34%, and Jaccard index of 59.53%. For the Bearing dataset, it recorded an Mcc of 76.97%, Dice coefficient of 77.04%, and Jaccard index of 63.28%. Similarly, in the SD-saliency-900 dataset, CFF-Net achieved an Mcc of 84.08%, Dice coefficient of 85.82%, and Jaccard index of 75.67%. These results underscore CFF-Net’s effectiveness and reliability in handling diverse segmentation challenges across different datasets. Full article

We propose a novel architecture, Transformer Dil-DenseUNet, designed to address the challenges of accurately segmenting stroke lesions in MRI images. Precise segmentation is essential for diagnosing and treating stroke patients, as it provides critical spatial insights into the affected brain regions and the extent of damage. Traditional manual segmentation is labor-intensive and error-prone, highlighting the need for automated solutions. Our Transformer Dil-DenseUNet combines DenseNet, dilated convolutions, and Transformer blocks, each contributing unique strengths to enhance segmentation accuracy. The DenseNet component captures fine-grained details and global features by leveraging dense connections, improving both precision and feature reuse. The dilated convolutional blocks, placed before each DenseNet module, expand the receptive field, capturing broader contextual information essential for accurate segmentation. Additionally, the Transformer blocks within our architecture address CNN limitations in capturing long-range dependencies by modeling complex spatial relationships through multi-head self-attention mechanisms. We assess our model’s performance on the Ischemic Stroke Lesion Segmentation Challenge 2015 (SISS 2015) and ISLES 2022 datasets. In the testing phase, the model achieves a Dice coefficient of 0.80 ± 0.30 on SISS 2015 and 0.81 ± 0.33 on ISLES 2022, surpassing the current state-of-the-art results on these datasets. Full article

Background: Lung cancer remains a significant health concern, and the effectiveness of early detection significantly enhances patient survival rates. Identifying lung tumors with high precision is a challenge due to the complex nature of tumor structures and the surrounding lung tissues. Methods: To address these hurdles, this paper presents an innovative three-step approach that leverages Generative Adversarial Networks (GAN), Long Short-Term Memory (LSTM), and VGG16 algorithms for the accurate reconstruction of three-dimensional (3D) lung tumor images. The first challenge we address is the accurate segmentation of lung tissues from CT images, a task complicated by the overwhelming presence of non-lung pixels, which can lead to classifier imbalance. Our solution employs a GAN model trained with a reinforcement learning (RL)-based algorithm to mitigate this imbalance and enhance segmentation accuracy. The second challenge involves precisely detecting tumors within the segmented lung regions. We introduce a second GAN model with a novel loss function that significantly improves tumor detection accuracy. Following successful segmentation and tumor detection, the VGG16 algorithm is utilized for feature extraction, preparing the data for the final 3D reconstruction. These features are then processed through an LSTM network and converted into a format suitable for the reconstructive GAN. This GAN, equipped with dilated convolution layers in its discriminator, captures extensive contextual information, enabling the accurate reconstruction of the tumor’s 3D structure. Results: The effectiveness of our method is demonstrated through rigorous evaluation against established techniques using the LIDC-IDRI dataset and standard performance metrics, showcasing its superior performance and potential for enhancing early lung cancer detection. Conclusions:This study highlights the benefits of combining GANs, LSTM, and VGG16 into a unified framework. This approach significantly improves the accuracy of detecting and reconstructing lung tumors, promising to enhance diagnostic methods and patient results in lung cancer treatment. Full article

Clubbing finger is a significant clinical indicator, and its early detection is essential for the diagnosis and treatment of associated diseases. However, traditional diagnostic methods rely heavily on the clinician’s subjective assessment, which can be prone to biases and may lack standardized tools. Unlike other diagnostic challenges, the characteristic changes of clubbing finger are subtle and localized, necessitating high-precision feature extraction. Existing models often fail to capture these delicate changes accurately, potentially missing crucial diagnostic features or generating false positives. Furthermore, these models are often not suited for accurate clinical diagnosis in resource-constrained settings. To address these challenges, we propose MSG-YOLO, a lightweight clubbing finger detection model based on YOLOv8n, designed to enhance both detection accuracy and efficiency. The model first employs a multi-scale dilated residual module, which expands the receptive field using dilated convolutions and residual connections, thereby improving the model’s ability to capture features across various scales. Additionally, we introduce a Selective Feature Fusion Pyramid Network (SFFPN) that dynamically selects and enhances critical features, optimizing the flow of information while minimizing redundancy. To further refine the architecture, we reconstruct the YOLOv8 detection head with group normalization and shared-parameter convolutions, significantly reducing the model’s parameter count and increasing computational efficiency. Experimental results indicate that the model maintains high detection accuracy with reduced parameter and computational requirements. Compared to YOLOv8n, MSG-YOLO achieves a 48.74% reduction in parameter count and a 24.17% reduction in computational load, while improving the mAP0.5 score by 2.86%, reaching 93.64%. This algorithm strikes a balance between accuracy and lightweight design, offering efficient and reliable clubbing finger detection even in resource-constrained environments. Full article

Land-based sources of marine outfalls are a major source of marine pollution. The monitoring of land-based sources of marine outfalls is an important means for marine environmental protection and governance. Traditional on-site manual monitoring methods are inefficient, expensive, and constrained by geographic conditions. Satellite remote sensing spectral analysis methods can only identify pollutant plumes and are affected by discharge timing and cloud/fog interference. Therefore, we propose a smart monitoring method for land-based sources of marine outfalls based on an improved YOLOv8 model, using unmanned aerial vehicles (UAVs). This method can accurately identify and classify marine outfalls, offering high practical application value. Inspired by the sparse sampling method in compressed sensing, we incorporated a multi-scale dilated attention mechanism into the model and integrated dynamic snake convolutions into the C2f module. This approach enhanced the model’s detection capability for occluded and complex-feature targets while constraining the increase in computational load. Additionally, we proposed a new loss calculation method by combining Inner-IoU (Intersection over Union) and MPDIoU (IoU with Minimum Points Distance), which further improved the model’s regression speed and its ability to predict multi-scale targets. The final experimental results show that the improved model achieved an mAP50 (mean Average Precision at 50) of 87.0%, representing a 3.4% increase from the original model, effectively enabling the smart monitoring of land-based marine discharge outlets. Full article

Text CAPTCHAs are crucial security measures deployed on global websites to deter unauthorized intrusions. The presence of anti-attack features incorporated into text CAPTCHAs limits the effectiveness of evaluating them, despite CAPTCHA recognition being an effective method for assessing their security. This study introduces a novel color augmentation technique called Variational Color Shift (VCS) to boost the recognition accuracy of different networks. VCS generates a color shift of every input image and then resamples the image within that range to generate a new image, thus expanding the number of samples of the original dataset to improve training effectiveness. In contrast to Random Color Shift (RCS), which treats the color offsets as hyperparameters, VCS estimates color shifts by reparametrizing the points sampled from the uniform distribution using predicted offsets according to every image, which makes the color shifts learnable. To better balance the computation and performance, we also propose two variants of VCS: Sim-VCS and Dilated-VCS. In addition, to solve the overfitting problem caused by disturbances in text CAPTCHAs, we propose an Auto-Encoder (AE) based on Large Separable Kernel Attention (AE-LSKA) to replace the convolutional module with large kernels in the text CAPTCHA recognizer. This new module employs an AE to compress the interference while expanding the receptive field using Large Separable Kernel Attention (LSKA), reducing the impact of local interference on the model training and improving the overall perception of characters. The experimental results show that the recognition accuracy of the model after integrating the AE-LSKA module is improved by at least 15 percentage points on both M-CAPTCHA and P-CAPTCHA datasets. In addition, experimental results demonstrate that color augmentation using VCS is more effective in enhancing recognition, which has higher accuracy compared to RCS and PCA Color Shift (PCA-CS). Full article

To address the issue of efficiently reusing the massive amount of unstructured knowledge generated during the handling of track circuit equipment faults and to automate the construction of knowledge graphs in the railway maintenance domain, it is crucial to leverage knowledge extraction techniques to efficiently extract relational triplets from fault maintenance text data. Given the current lag in joint extraction technology within the railway domain and the inefficiency in resource utilization, this paper proposes a joint extraction model for track circuit entities and relations, integrating Global Pointer and tensor learning. Taking into account the associative characteristics of semantic relations, the nesting of domain-specific terms in the railway sector, and semantic diversity, this research views the relation extraction task as a tensor learning process and the entity recognition task as a span-based Global Pointer search process. First, a multi-layer dilate gated convolutional neural network with residual connections is used to extract key features and fuse the weighted information from the 12 different semantic layers of the RoBERTa-wwm-ext model, fully exploiting the performance of each encoding layer. Next, the Tucker decomposition method is utilized to capture the semantic correlations between relations, and an Efficient Global Pointer is employed to globally predict the start and end positions of subject and object entities, incorporating relative position information through rotary position embedding (RoPE). Finally, comparative experiments with existing mainstream joint extraction models were conducted, and the proposed model’s excellent performance was validated on the English public datasets NYT and WebNLG, the Chinese public dataset DuIE, and a private track circuit dataset. The F1 scores on the NYT, WebNLG, and DuIE public datasets reached 92.1%, 92.7%, and 78.2%, respectively. Full article

The rotating parts of large and complex equipment are key components that ensure the normal operation of the equipment. Accurate fault diagnosis is crucial for the safe operation of these systems. To simultaneously extract both local and global valuable fault feature information from key components of complex equipment, this study proposes a fault diagnosis network model, named MultiDilatedFormer, which is based on the fusion of transformer and multi-head dilated convolution. The newly designed multi-head dilated convolution module is sequentially integrated into the transformer-encoder architecture, constructing a feature extraction module where the complementary advantages of both components enhance overall performance. Firstly, the sample is expanded into a two-dimensional feature map and then input into the newly designed feature extraction module. Finally, the diagnostic output is performed by the designed patch feature fusion module and classifier module. Additionally, interpretability research is conducted on the proposed model, aiming to understand the decision-making mechanism of the model through visual analysis of the entire decision process. The experimental results on three different datasets indicate that the proposed model achieved high accuracy in fault diagnosis with relatively short data windows. The highest accuracy reached 97.95%, which was up to 10.97% higher than other models. Furthermore, the feasibility of the model is also verified in the actual dataset of the rotating parts of the injection molding machine. The excellent performance of the model on different datasets demonstrates its effectiveness in extracting comprehensive fault feature information and also proves its great potential in practical industrial applications. Full article

Non-contact heart rate monitoring from facial videos utilizing remote photoplethysmography (rPPG) has gained significant traction in remote health monitoring. Given that rPPG captures the dynamic blood flow within the human body and constitutes a time-series signal characterized by periodic properties, this study introduced a three-dimensional convolutional neural network (3D CNN) designed to simultaneously address long-term periodic and short-term temporal characteristics for effective rPPG signal extraction. Firstly, differential operations are employed to preprocess video data, enhancing the face’s dynamic features. Secondly, building upon the 3D CNN framework, multi-scale dilated convolutions and self-attention mechanisms were integrated to enhance the model’s temporal modeling capabilities further. Finally, interpolation techniques are applied to refine the heart rate calculation methodology. The experiments conducted on the UBFC-rPPG dataset indicate that, compared with the existing optimal algorithm, the average absolute error (MAE) and the root mean square error (RMSE) realized significant enhancements of approximately 28% and 35%. Additionally, through comprehensive analyses such as cross-dataset experiments and complexity analyses, the validity and stability of the proposed algorithm in the task of heart rate estimation were manifested. Full article

Neural networks have inductive biases owing to the assumptions associated with the selected learning algorithm, datasets, and network structure. Specifically, convolutional neural networks (CNNs) are known for their tendency to exhibit textural biases. This bias is closely related to image classification accuracy. Aligning the model’s bias with the dataset’s bias can significantly enhance performance in transfer learning, leading to more efficient learning. This study aims to quantitatively demonstrate that increasing shape bias within the network by varying kernel sizes and dilation rates improves accuracy on shape-dominant data and enables efficient learning with less data. Furthermore, we propose a novel method for quantitatively evaluating the balance between texture bias and shape bias. This method enables efficient learning by aligning the biases of the transfer learning dataset with those of the model. Systematically adjusting these biases allows CNNs to better fit data with specific biases. Compared to the original model, an accuracy improvement of up to 9.9% was observed. Our findings underscore the critical role of bias adjustment in CNN design, contributing to developing more efficient and effective image classification models. Full article

Image super-resolution (SR) algorithms based on deep learning yield good visual performances on visible images. Due to the blurred edges and low contrast of infrared (IR) images, methods transferred directly from visible images to IR images have a poor performance and ignore the demands of downstream detection tasks. Therefore, an Inception Dilated Super-Resolution (IDSR) network with multiple branches is proposed. A dilated convolutional branch captures high-frequency information to reconstruct edge details, while a non-local operation branch captures long-range dependencies between any two positions to maintain the global structure. Furthermore, deformable convolution is utilized to fuse features extracted from different branches, enabling adaptation to targets of various shapes. To enhance the detection performance of low-resolution (LR) images, we crop the images into patches based on target labels before feeding them to the network. This allows the network to focus on learning the reconstruction of the target areas only, reducing the interference of background areas in the target areas’ reconstruction. Additionally, a feature-driven module is cascaded at the end of the IDSR network to guide the high-resolution (HR) image reconstruction with feature prior information from a detection backbone. This method has been tested on the FLIR Thermal Dataset and the M3FD Dataset and compared with five mainstream SR algorithms. The final results demonstrate that our method effectively maintains image texture details. More importantly, our method achieves 80.55% mAP, outperforming other methods on FLIR Dataset detection accuracy, and with 74.7% mAP outperforms other methods on M3FD Dataset detection accuracy. Full article

Single-stage detectors have drawbacks of insufficient accuracy and poor coverage capability. YOLOF (You Only Look One-level Feature) has achieved better performance in this regard, but there is still room for improvement. To enhance the coverage capability for objects of different scales, we propose an improved single-stage object detector: Dq-YOLOF. We have designed an output encoder that employs a series of modules utilizing deformable convolution and SimAM (Simple Attention Module). This module replaces the dilated convolution in YOLOF. This design significantly improves the ability to express details. Simultaneously, we have redefined the sample selection strategy, which optimizes the quality of positive samples based on SimOTA. It can dynamically allocate positive samples according to their quality, reducing computational load and making it more suitable for small objects. Experiments conducted on the COCO 2017 dataset also verify the effectiveness of our method. Dq-YOLOF achieved 38.7 $AP$, 1.5 $AP$ higher than YOLOF. To confirm performance improvements on small objects, our method was tested on urinary sediment and aerial drone datasets for generalization. Notably, it enhances performance while also lowering computational costs. Full article

This study presents a new image inpainting model based on U-Net and incorporating the Wasserstein Generative Adversarial Network (WGAN). The model uses skip connections to connect every encoder block to the corresponding decoder block, resulting in a strictly symmetrical architecture referred to as Symmetric Connected U-Net (SC-Unet). By combining SC-Unet with a GAN, the study aims to reconstruct images more effectively and seamlessly. The traditional discriminators only differentiate the entire image as true or false. In this study, the discriminator calculated the probability of each pixel belonging to the hole and non-hole regions, which provided the generator with more gradient loss information for image inpainting. Additionally, every block of SC-Unet incorporated a Dilated Convolutional Neural Network (DCNN) to increase the receptive field of the convolutional layers. Our model also integrated Multi-Head Self-Attention (MHSA) into selected blocks to enable it to efficiently search the entire image for suitable content to fill the missing areas. This study adopts the publicly available datasets CelebA-HQ and ImageNet for evaluation. Our proposed algorithm demonstrates a 10% improvement in PSNR and a 2.94% improvement in SSIM compared to existing representative image inpainting methods in the experiment. Full article

In recent years, research on Unmanned Aerial Vehicles (UAVs) has developed rapidly. Compared to traditional remote-sensing images, UAV images exhibit complex backgrounds, high resolution, and large differences in object scales. Therefore, UAV object detection is an essential yet challenging task. This paper proposes a multi-scale object detection network, namely YOLO-DroneMS (You Only Look Once for Drone Multi-Scale Object), for UAV images. Targeting the pivotal connection between the backbone and neck, the Large Separable Kernel Attention (LSKA) mechanism is adopted with the Spatial Pyramid Pooling Factor (SPPF), where weighted processing of multi-scale feature maps is performed to focus more on features. And Attentional Scale Sequence Fusion DySample (ASF-DySample) is introduced to perform attention scale sequence fusion and dynamic upsampling to conserve resources. Then, the faster cross-stage partial network bottleneck with two convolutions (named C2f) in the backbone is optimized using the Inverted Residual Mobile Block and Dilated Reparam Block (iRMB-DRB), which balances the advantages of dynamic global modeling and static local information fusion. This optimization effectively increases the model’s receptive field, enhancing its capability for downstream tasks. By replacing the original CIoU with WIoUv3, the model prioritizes anchoring boxes of superior quality, dynamically adjusting weights to enhance detection performance for small objects. Experimental findings on the VisDrone2019 dataset demonstrate that at an Intersection over Union (IoU) of 0.5, YOLO-DroneMS achieves a 3.6% increase in mAP@50 compared to the YOLOv8n model. Moreover, YOLO-DroneMS exhibits improved detection speed, increasing the number of frames per second (FPS) from 78.7 to 83.3. The enhanced model supports diverse target scales and achieves high recognition rates, making it well-suited for drone-based object detection tasks, particularly in scenarios involving multiple object clusters. Full article

This study introduces an improved YOLOv8 model tailored for detecting objects in road scenes. To overcome the limitations of standard convolution operations in adapting to varying targets, we introduce Adaptive Kernel Convolution (AKconv). AKconv dynamically adjusts the convolution kernel’s shape and size, enhancing the backbone network’s feature extraction capabilities and improving feature representation across different scales. Additionally, we employ a Multi-Scale Dilated Attention (MSDA) mechanism to focus on key target features, further enhancing feature representation. To address the challenge posed by YOLOv8’s large down sampling factor, which limits the learning of small target features in deeper feature maps, we add a small target detection layer. Finally, to improve model training efficiency, we introduce a regression loss function with a Wise-IoU dynamic non-monotonic focusing mechanism. With these enhancements, our improved YOLOv8 model excels in road scene object detection tasks, achieving a 5.6 percentage point improvement in average precision over the original YOLOv8n on real road datasets. Full article