☆ 4.6 Article

A Methodology to Automatically Segment 3D Ultrasonic Data Using X-ray Computed Tomography and a Convolutional Neural Network

APPLIED SCIENCES-BASEL (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Engineering, Electrical & Electronic

Multi-Purpose Oriented Single Nighttime Image Haze Removal Based on Unified Variational Retinex Model

Yun Liu et al.

Summary: In this paper, a multi-purpose oriented haze removal framework for nighttime hazy images is proposed. The framework can simultaneously estimate illumination and reflectance components and predict noise map. Experiments show that the proposed framework outperforms other nighttime image dehazing methods in terms of visual effects and objective comparisons, and it is also applicable to other types of degraded images.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2023)

添加到收藏夹

Article Engineering, Electrical & Electronic

Deep Learning-Based Defect Detection From Sequences of Ultrasonic B-Scans

Duje Medak et al.

Summary: Ultrasonic testing (UT) is a commonly used non-destructive testing technique for material evaluation and defect detection. Most previous automated defect detection methods from UT data analyze individual A-scans, neglecting valuable information from surrounding A-scans. In this paper, two approaches based on high-dimensional feature maps merging are proposed to effectively utilize information from neighboring B-scans and improve the precision.

IEEE SENSORS JOURNAL (2022)

添加到收藏夹

Article Materials Science, Characterization & Testing

A deep learning based methodology for artefact identification and suppression with application to ultrasonic images

Sergio Cantero-Chinchilla et al.

Summary: This paper presents a deep learning framework for artefact identification and suppression in nondestructive evaluation, which is based on the concept of autoencoders. Through experimental case study, it proves to be effective in accurately suppressing artefacts in complex scenarios and provides the physical parameters needed for imaging as well. Comparisons with state-of-the-art methodology based on image analysis are also made for artefact identification and suppression.

NDT & E INTERNATIONAL (2022)

添加到收藏夹

Article Engineering, Mechanical

Sizing limitations of ultrasonic array images for non-sharp defects and their impact on structural integrity assessments

Shivaprasad Shridhara Bhat et al.

Summary: Existing structural integrity assessment procedures usually assume flaws to be infinitely sharp, which is often overly conservative. This study examines the sizing limitation and accuracy of ultrasonic array image-based techniques for non-sharp defects and highlights their influence on structural integrity assessments.

THEORETICAL AND APPLIED FRACTURE MECHANICS (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Toward Fast, Flexible, and Robust Low-Light Image Enhancement

Long Ma et al.

Summary: This paper proposes a new Self-Calibrated Illumination (SCI) learning framework for enhancing image brightness in real-world low-light scenarios. The framework achieves a balance between computational efficiency and visual quality through cascaded illumination learning, weight sharing, and a self-calibrated module.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

添加到收藏夹

Article Materials Science, Characterization & Testing

Augmented Ultrasonic Data for Machine Learning

Iikka Virkkunen et al.

Summary: Flaw detection in non-destructive testing has traditionally relied on trained human inspectors, but recent advances in machine learning algorithms offer potential solutions. In this study, modern deep convolutional networks and data augmentation techniques were used to achieve flaw detection from ultrasonic data at human-level performance.

JOURNAL OF NONDESTRUCTIVE EVALUATION (2021)

添加到收藏夹

Article Acoustics

Automated Defect Detection From Ultrasonic Images Using Deep Learning

Duje Medak et al.

Summary: Nondestructive evaluation (NDE) techniques are used for material inspection without causing damage. Ultrasonic inspection is a common method, but data analysis is still manual and inefficient. Deep learning methods show promise in improving analysis efficiency, but face challenges with limited training data.

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL (2021)

添加到收藏夹

Article Acoustics

Deconvolution of ultrasonic signals using a convolutional neural network

Arthur Chapon et al.

Summary: This research aims to improve the compromise between penetration depth and axial resolution in ultrasonic testing by using a convolutional neural network to separate overlapping echoes in time traces to estimate time-of-flight and amplitude. The framework is trained using data generated in simulations and validated experimentally to detect flat bottom holes with a minimum depth corresponding to lambda/4 in an aluminum block.

ULTRASONICS (2021)

添加到收藏夹

Article Nanoscience & Nanotechnology

Intelligent damage recognition of composite materials based on deep learning and ultrasonic testing

Caizhi Li et al.

Summary: This paper proposes a 1D-YOLO network for intelligent recognition of aircraft composite material damage, which achieved higher accuracy and precision through training and testing of composite material damage data on aircraft skin.

AIP ADVANCES (2021)

添加到收藏夹

Article Acoustics

Towards using convolutional neural network to locate, identify and size defects in phased array ultrasonic testing

Thibault Latete et al.

Summary: In this study, Faster R-CNN was used to identify, locate, and size flat bottom holes (FBH) and side-drilled holes (SDH) in an immersed test specimen using a single plane wave insonification. The trained neural network performed well in finite element simulations, showing promise for real-world applications. Additional experiments also demonstrated the effectiveness of the method in correctly identifying defects within the test specimen.

ULTRASONICS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Benchmarking Deep Learning Models for Automatic Ultrasonic Imaging Inspection

Jiaxing Ye et al.

Summary: The study introduces a new annotated dataset USimgAIST and focuses on validating existing AI models for ultrasonic image understanding. It provides detailed benchmarking comparisons for defect detection accuracy, model complexity, memory usage, and inference time.

IEEE ACCESS (2021)

添加到收藏夹

Article Materials Science, Characterization & Testing

Defects identification using the improved ultrasonic measurement model and support vector machines

Huifang Xiao et al.

NDT & E INTERNATIONAL (2020)

添加到收藏夹

Review Materials Science, Composites

Voids in fiber-reinforced polymer composites: A review on their formation, characteristics, and effects on mechanical performance

Mahoor Mehdikhani et al.

JOURNAL OF COMPOSITE MATERIALS (2019)

添加到收藏夹

Proceedings Paper Materials Science, Characterization & Testing

A Supervised Learning Approach for Prediction of X-ray Computed Tomography Data from Ultrasonic Testing Data

Daniel Sparkman et al.

45TH ANNUAL REVIEW OF PROGRESS IN QUANTITATIVE NONDESTRUCTIVE EVALUATION, VOL 38 (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Shaoqing Ren et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks

Min Meng et al.

NEUROCOMPUTING (2017)

添加到收藏夹

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Mask R-CNN

Kaiming He et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

添加到收藏夹

Proceedings Paper Physics, Applied

Ultrasonic Tracking of Ply Drops in Composite Laminates

Robert A. Smith et al.

42ND ANNUAL REVIEW OF PROGRESS IN QUANTITATIVE NONDESTRUCTIVE EVALUATION: INCORPORATING THE 6TH EUROPEAN-AMERICAN WORKSHOP ON RELIABILITY OF NDE (2016)

添加到收藏夹

Article Multidisciplinary Sciences

scikit-image: image processing in Python

Stefan van der Walt et al.

PEERJ (2014)

添加到收藏夹

Article Materials Science, Composites

Determination of damage micromechanisms and fracture resistance of glass fiber/epoxy cross-ply laminate by means of X-ray computed microtomography

F. Sket et al.

COMPOSITES SCIENCE AND TECHNOLOGY (2012)

添加到收藏夹

Article Biochemical Research Methods

Fiji: an open-source platform for biological-image analysis

Johannes Schindelin et al.

NATURE METHODS (2012)

添加到收藏夹

Article Materials Science, Composites

Effect of curing cycle on void distribution and interlaminar shear strength in polymer-matrix composites

S. Hernandez et al.

COMPOSITES SCIENCE AND TECHNOLOGY (2011)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.