Search

Detecting structural cracks is critical for quality control and maintenance of industrial materials, ensuring their safety and extending service life. This study enhances the automation and accuracy of crack detection in microscopic images using advanced image processing and deep learning techniques, particularly the YOLOv8 model. A comprehensive review of relevant literature was carried out to compare traditional image-processing methods with modern machine-learning approaches. The YOLOv8 model was optimized by incorporating the Wise Intersection over Union (WIoU) loss function and the bidirectional feature pyramid network (BiFPN) technique, achieving precise detection results with mean average precision (mAP@0.5) of 0.895 and a precision rate of 0.859, demonstrating its superiority in detecting fine cracks even in complex and noisy backgrounds. Experimental findings confirmed the model's high accuracy in identifying cracks, even under challenging conditions. Despite these advancements, detecting very small or overlapping cracks in complex backgrounds remains challenging. Our future work will focus on optimizing and extending the model's generalisation capabilities. The findings of this study provide a solid foundation for automatic and rapid crack detection in industrial applications and indicate potential for broader applications across various fields. [ABSTRACT FROM AUTHOR]

In the field of machine learning and computer vision, the lack of annotated datasets is a major challenge for model development and accuracy improvement. Synthetic data generation addresses this issue by providing large, diverse, and accurately annotated datasets, thereby enhancing model training and validation. This study presents a Unity-based virtual environment that utilises the Unity Perception package to generate high-quality datasets. First, high-precision 3D (Three-Dimensional) models are created using a 3D structured light scanner, with textures processed to remove specular reflections. These models are then imported into Unity to generate diverse and accurately annotated synthetic datasets. The experimental results indicate that object recognition models trained with synthetic data achieve a high rate of performance on real images, validating the effectiveness of synthetic data in improving model generalisation and application performance. Monocular distance measurement verification shows that the synthetic data closely matches real-world physical scales, confirming its visual realism and physical accuracy. [ABSTRACT FROM AUTHOR]

To address the challenge of rapid geometric model development in the digital twin industry, this paper presents a comprehensive pipeline for constructing 3D models from images using monocular vision imaging principles. Firstly, a structure-from-motion (SFM) algorithm generates a 3D point cloud from photographs. The feature detection methods scale-invariant feature transform (SIFT), speeded-up robust features (SURF), and KAZE are compared across six datasets, with SIFT proving the most effective (matching rate higher than 0.12). Using K-nearest-neighbor matching and random sample consensus (RANSAC), refined feature point matching and 3D spatial representation are achieved via antipodal geometry. Then, the Poisson surface reconstruction algorithm converts the point cloud into a mesh model. Additionally, texture images are enhanced by leveraging a visual geometry group (VGG) network-based deep learning approach. Content images from a dataset provide geometric contours via higher-level VGG layers, while textures from style images are extracted using the lower-level layers. These are fused to create texture-transferred images, where the image quality assessment (IQA) metrics SSIM and PSNR are used to evaluate texture-enhanced images. Finally, texture mapping integrates the enhanced textures with the mesh model, improving the scene representation with enhanced texture. The method presented in this paper surpassed a LiDAR-based reconstruction approach by 20 % in terms of point cloud density and number of model facets, while the hardware cost was only 1 % of that associated with LiDAR. [ABSTRACT FROM AUTHOR]

Breast cancer is the most common type of cancer in women and poses a significant health risk to women globally. Developments in computer-aided diagnosis (CAD) systems are focused on specific tasks of classification and segmentation, but few studies involve a completely integrated system. In this study, a comprehensive CAD system was proposed to screen ultrasound, mammograms and magnetic resonance imaging (MRI) of breast cancer, including image preprocessing, breast cancer classification, and tumour segmentation. First, the total variation filter was used for image denoising. Second, an optimised XGBoost machine learning model using EfficicnetB0 as feature extraction was proposed to classify breast images into normal and tumour. Third, after classifying the tumour images, a hybrid CNN deep learning model integrating the strengths of MobileNet and InceptionV3 was proposed to categorise tumour images into benign and malignant. Finally, Attention U-Net was used to segment tumours in annotated datasets while classical image segmentation methods were used for the others. The proposed models in the designed CAD system achieved an accuracy of 96.14% on the abnormal classification and 94.81% on tumour classification on the BUSI dataset, improving the effectiveness of automatic breast cancer diagnosis. [ABSTRACT FROM AUTHOR]

Vibration-based structural health monitoring (SHM) is essential for evaluating structural integrity. Traditional methods using contact vibration sensors like accelerometers have limitations in accessibility, coverage, and impact on structural dynamics. Recent digital advancements offer new solutions through high-speed camera-based measurements. This study explores how camera settings (speed and resolution) influence the accuracy of dynamic response measurements for detecting small cracks in damped cantilever beams. Different beam thicknesses affect damping, altering dynamic response parameters such as frequency and amplitude, which are crucial for damage quantification. Experiments were conducted on 3D-printed Acrylonitrile Butadiene Styrene (ABS) cantilever beams with varying crack depth ratios from 0% to 60% of the beam thickness. The study utilised the Canny edge detection technique and Fast Fourier Transform to analyse vibration behaviour captured by cameras at different settings. The results show an optimal set of camera resolutions and frame rates for accurately capturing dynamic responses. Empirical models based on four image resolutions were validated against experimental data, achieving over 98% accuracy for predicting the natural frequency and around 90% for resonance amplitude. The optimal frame rate for measuring natural frequency and amplitude was found to be 2.4 times the beam's natural frequency. The findings provide a method for damage assessment by establishing a relationship between crack depth, beam thickness, and damping ratio. [ABSTRACT FROM AUTHOR]

The early detection of breast cancer is essential for improving treatment outcomes, and recent advancements in artificial intelligence (AI), combined with image processing techniques, have shown great potential in enhancing diagnostic accuracy. This study explores the effects of various image processing methods and AI models on the performance of early breast cancer diagnostic systems. By focusing on techniques such as Wiener filtering and total variation filtering, we aim to improve image quality and diagnostic precision. The novelty of this study lies in the comprehensive evaluation of these techniques across multiple medical imaging datasets, including a DCE-MRI dataset for breast-tumor image segmentation and classification (BreastDM) and the Breast Ultrasound Image (BUSI), Mammographic Image Analysis Society (MIAS), Breast Cancer Histopathological Image (BreakHis), and Digital Database for Screening Mammography (DDSM) datasets. The integration of advanced AI models, such as the vision transformer (ViT) and the U-KAN model—a U-Net structure combined with Kolmogorov–Arnold Networks (KANs)—is another key aspect, offering new insights into the efficacy of these approaches in different imaging contexts. Experiments revealed that Wiener filtering significantly improved image quality, achieving a peak signal-to-noise ratio (PSNR) of 23.06 dB and a structural similarity index measure (SSIM) of 0.79 using the BreastDM dataset and a PSNR of 20.09 dB with an SSIM of 0.35 using the BUSI dataset. When combined filtering techniques were applied, the results varied, with the MIAS dataset showing a decrease in SSIM and an increase in the mean squared error (MSE), while the BUSI dataset exhibited enhanced perceptual quality and structural preservation. The vision transformer (ViT) framework excelled in processing complex image data, particularly with the BreastDM and BUSI datasets. Notably, the Wiener filter using the BreastDM dataset resulted in an accuracy of 96.9% and a recall of 96.7%, while the combined filtering approach further enhanced these metrics to 99.3% accuracy and 98.3% recall. In the BUSI dataset, the Wiener filter achieved an accuracy of 98.0% and a specificity of 98.5%. Additionally, the U-KAN model demonstrated superior performance in breast cancer lesion segmentation, outperforming traditional models like U-Net and U-Net++ across datasets, with an accuracy of 93.3% and a sensitivity of 97.4% in the BUSI dataset. These findings highlight the importance of dataset-specific preprocessing techniques and the potential of advanced AI models like ViT and U-KAN to significantly improve the accuracy of early breast cancer diagnostics. [ABSTRACT FROM AUTHOR]

This study primarily investigates advanced object detection and time series prediction methods in image-based visual servoing systems, aiming to capture targets better and predict the motion trajectory of robotic arms in advance, thereby enhancing the system's performance and reliability. The research first implements object detection on the VOC2007 dataset using the Detection Transformer (DETR) and achieves ideal detection scores. The particle swarm optimization algorithm and 3-5-3 polynomial interpolation methods were utilized for trajectory planning, creating a unique dataset through simulation. This dataset contains randomly generated trajectories within the workspace, fully simulating actual working conditions. Significantly, the Bidirectional Long Short-Term Memory (BILSTM) model was improved by substituting its traditional Multilayer Perceptron (MLP) components with Kolmogorov–Arnold Networks (KANs). KANs, inspired by the K-A theorem, improve the network representation ability by placing learnable activation functions on fixed node activation functions. By implementing KANs, the model enhances parameter efficiency and interpretability, thus addressing the typical challenges of MLPs, such as the high parameter count and lack of transparency. The experiments achieved favorable predictive results, indicating that the KAN not only reduces the complexity of the model but also improves learning efficiency and prediction accuracy in dynamic visual servoing environments. Finally, Gazebo software was used in ROS to model and simulate the robotic arm, verify the effectiveness of the algorithm, and achieve visual servoing. [ABSTRACT FROM AUTHOR]