X-ray non-destructive testing (NDT) technology is extensively utilized in the welding industry for the detection of weld defects. This paper proposes a novel defect segmentation algorithm to address the challenges of X-ray defect detection images, including low contrast, blurred edges, significant noise, and pronounced background variations. Traditional detection methods often struggle to extract low-contrast defects from weld images, so this approach integrates both underlying and mid-level image information to enhance accuracy. The process begins with a visual saliency model that generates a rough saliency map from underlying details. Next, a Pulse Coupled Neural Network (PCNN) is used to compute the saliency map at the mid-level. Finally, these two saliency maps are combined using a pixel-minimum method to produce the final image saliency map. Experimental results show that this method is highly accurate, broadly applicable, and capable of rapid defect extraction within the welding area.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11532248 | PMC |
| http://dx.doi.org/10.1016/j.heliyon.2024.e39442 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Interpretable machine learning models for COPD ease of breathing estimation.
Med Biol Eng Comput
January 2025
IDLab, Ghent University-Imec, Technologiepark-Zwijnaarde 126, Zwijnaarde, Belgium.
Chronic obstructive pulmonary disease (COPD) is a leading cause of death worldwide and greatly reduces the quality of life. Utilizing remote monitoring has been shown to improve quality of life and reduce exacerbations, but remains an ongoing area of research. We introduce a novel method for estimating changes in ease of breathing for COPD patients, using obstructed breathing data collected via wearables.
View Article and Find Full Text PDFRad4XCNN: A new agnostic method for post-hoc global explanation of CNN-derived features by means of Radiomics.
Comput Methods Programs Biomed
January 2025
Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, 90127, Italy. Electronic address:
Article Synopsis
- Machine learning-based clinical decision support systems (CDSS) face challenges with transparency and reliability, as explainability often reduces predictive accuracy.
- A novel method called Rad4XCNN enhances the predictive power of CNN features while maintaining interpretability through Radiomics, moving beyond traditional saliency maps.
- In breast cancer classification tasks, Rad4XCNN demonstrates superior accuracy compared to other feature types and allows for global insights, effectively addressing the explainability-accuracy trade-off in AI models.
Salience maps for judgments of frontal plane distance, centroids, numerosity, and letter identity inferred from substance-invariant processing.
J Vis
January 2025
Department of Cognitive Sciences and Neurobiology and Behavior, University of California, Irvine, California, USA.
A salience map is a topographic map that has inputs at each x,y location from many different feature maps and summarizes the combined salience of all those inputs as a real number, salience, which is represented in the map. Of the more than 1 million Google references to salience maps, nearly all use the map for computing the relative priority of visual image components for subsequent processing. We observe that salience processing is an instance of substance-invariant processing, analogous to household measuring cups, weight scales, and measuring tapes, all of which make single-number substance-invariant measurements.
View Article and Find Full Text PDFEdge-guided feature fusion network for RGB-T salient object detection.
Front Neurorobot
December 2024
Department of Information Engineering, Shanghai Maritime University, Shanghai, China.
Introduction: RGB-T Salient Object Detection (SOD) aims to accurately segment salient regions in both visible light and thermal infrared images. However, many existing methods overlook the critical complementarity between these modalities, which can enhance detection accuracy.
Methods: We propose the Edge-Guided Feature Fusion Network (EGFF-Net), which consists of cross-modal feature extraction, edge-guided feature fusion, and salience map prediction.
TCBGY net for enhanced wear particle detection in ferrography using self attention and multi scale fusion.
Sci Rep
December 2024
Merchant Marine College, Shanghai Maritime University, Shanghai, 201306, China.
The intelligent identification of wear particles in ferrography is a critical bottleneck that hampers the development and widespread adoption of ferrography technology. To address challenges such as false detection, missed detection of small wear particles, difficulty in distinguishing overlapping and similar abrasions, and handling complex image backgrounds, this paper proposes an algorithm called TCBGY-Net for detecting wear particles in ferrography images. The proposed TCBGY-Net uses YOLOv5s as the backbone network, which is enhanced with several advanced modules to improve detection performance.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!