PorosityAnalyzer: Visual analysis and evaluation of segmentation pipelines to determine the porosity in fiber-reinforced polymers

Weissenböck, Johannes; Amirkhanov, A.N.; Gröller, Eduard; Kastner, Johann; Heinzl, Christoph

doi:10.1109/vast.2016.7883516

Cited by 14 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• GEMSe (Fröhler, Möller, & Heinzl, 2016) supports users in finding optimal parameters for their volume segmentation tasks without requiring a ground truth. • The PorosityAnalyzer (Weissenböck, Amirkhanov, Gröller, Kastner, & Heinzl, 2016) similarly supports users in finding the ideal segmentation algorithm and parameterization when they are determining porosity values, e.g., in fiber-reinforced polymers. • InSpectr (A.…”

Section: Discussionmentioning

confidence: 92%

open_iA: A tool for processing and visual analysis of industrial computed tomography datasets

Fröhler¹,

Weissenböck²,

Schiwarth³

et al. 2019

JOSS

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 92%

open_iA: A tool for processing and visual analysis of industrial computed tomography datasets

Fröhler¹,

Weissenböck²,

Schiwarth³

et al. 2019

JOSS

Self Cite

View full text Add to dashboard Cite

show abstract

“…Human in the loop means here that the network makes a prediction, which is then corrected by a human expert, until the quality of the prediction reaches a predefined threshold. Another important point is the use of additional measures to quantify the results of the prediction better, in similar directions as Yosifov et al [12] or Weissenböck et al [13]. Especially the shape and volume of the pores are important for aerospace components.…”

Section: Discussionmentioning

confidence: 99%

Usage of 3D U-net Convolutional Neural Network for the inspection of aerospace components

Yosifov¹,

Weinberger²,

Fröhler³

et al. 2023

eJNDT

View full text Add to dashboard Cite

This work illustrates the use of deep learning methods applied on X-ray computed tomography (XCT) datasets to segment pores and fibres in reinforced composite components from the aeronautic industry by binary semantic segmentation. We first apply data pre-processing, and then employ a modified 3D U-Net, representing a convolutional neural network. Tweaking hyper-parameters, we have reached an optimal model for our datasets. One of the models has reached 99% segmentation accuracy when testing using a Dice function. In our experiments, pores and fibres in XCT datasets of aerospace components, more specifically of glass and carbon fibre reinforced composites, were segmented and analysed. In order to compare this modified 3D U-Net architecture with segmentation methods currently used in the industry, the datasets were also input to conventional Otsu thresholding. Our results shows that modified 3D U-Net performs better than Otsu thresholding, especially on the segmentation of small pores. Modified 3D U-Net also showed reasonable prediction accuracy when testing with an optimised model which was trained with a low number of dataset both for fibre and pore segmentation.

show abstract

“…In addition, the inclusion of more complex image quality metrics such as the structural similarity index measure (SSIM) (Wang et al 2004) or peak signal-to-noise ratio (PSNR) would result in a more robust framework. A final image analysis framework, PorosityAnalyzer (Weissenböck et al 2016), compares results from various algorithms, e.g., different blob detection algorithms, to determine which is most useful for a particular application. We expect this sort of comparison to be useful in future work once scientists are more comfortable with image proxy analysis techniques.…”

Section: Related Workmentioning

confidence: 99%

An Image-Based Framework for Ocean Feature Detection and Analysis

et al. 2021

View full text Add to dashboard Cite

Today's supercomputing capabilities allow ocean scientists to generate simulation data at increasingly higher spatial and temporal resolutions. However, I/O bandwidth and data storage costs limit the amount of data saved to disk. In situ methods are one solution to generate reduced data extracts, with the potential to reduce disk storage requirement even for high spatial and temporal resolutions, a major advantage to storing raw output. Image proxies have become an efficient and accepted in situ reduced data extract. These extracts require innovative automated techniques to identify and analyze features. We present a framework of computer vision and image processing techniques to detect and analyze important features from in situ image proxies of large ocean simulations. We constrain the analysis framework in support of techniques that emulate ocean-specific tasks as accurately as possible. The framework maximizes feature analysis capabilities while minimizing computational requirements. We demonstrate its use for image proxies extracted from the ocean component of Model for Prediction Across Scales (MPAS) simulations to analyze ocean-specific features such as eddies and western boundary currents. The results obtained for specific data sets are compared to those of traditional methods, documenting the efficacy and advantages of our framework.

show abstract

PorosityAnalyzer: Visual analysis and evaluation of segmentation pipelines to determine the porosity in fiber-reinforced polymers

Cited by 14 publications

References 21 publications

open_iA: A tool for processing and visual analysis of industrial computed tomography datasets

open_iA: A tool for processing and visual analysis of industrial computed tomography datasets

Usage of 3D U-net Convolutional Neural Network for the inspection of aerospace components

An Image-Based Framework for Ocean Feature Detection and Analysis

Contact Info

Product

Resources

About