2014
DOI: 10.1007/978-3-319-12568-8_5
|View full text |Cite
|
Sign up to set email alerts
|

Estimation of Bubble Size Distribution Based on Power Spectrum

Abstract: A bubble size distribution gives relevant insight into mixing processes where gas-liquid phases are present. The distribution estimation is challenging since accurate bubble detection from images captured from industrial processes is a complicated task due to varying lighting conditions which change the appearance of bubbles considerably. In this paper, we propose a new method for estimating the bubble size distribution based on the image power spectrum. The method works by calculating the power spectrum for a… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
4
3

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 13 publications
0
3
0
Order By: Relevance
“…3) (Fu et al 2019). As mentioned in the introduction, BubGAN generates more realistic synthetic bubble images for machine learning training (Hass et al 2020) compared to conventional method by applying modelled pixel intensity variation on simple shapes such as circles and ellipses (Ilonen et al 2014 andKarn et al 2015b). The machine learning model used for bubble image analysis in this section is trained on a 2000 synthetic images and their corresponding labels.…”
Section: Assessment Of Proposed Methodsmentioning
confidence: 99%
“…3) (Fu et al 2019). As mentioned in the introduction, BubGAN generates more realistic synthetic bubble images for machine learning training (Hass et al 2020) compared to conventional method by applying modelled pixel intensity variation on simple shapes such as circles and ellipses (Ilonen et al 2014 andKarn et al 2015b). The machine learning model used for bubble image analysis in this section is trained on a 2000 synthetic images and their corresponding labels.…”
Section: Assessment Of Proposed Methodsmentioning
confidence: 99%
“…For example, Poletaev's CNN takes ∼8 seconds to achieve 94%-96% accuracy. One method that merits further investigation is direct estimation of the volume distribution from the power spectrum of the image [8].…”
Section: Related Workmentioning
confidence: 99%
“…LBP descriptor transforms an image to an array of integer labels, which can represent the small-scale appearance of the image [132]. The Fourier power spectrum of an image or a region is the square of the magnitude of its Fourier transform [70]. Gabor filters [77] can extract image information in different scales and orientations, so they are one of the most powerful local appearance descriptors.…”
Section: Terminal Setmentioning
confidence: 99%