Bubble Image Segmentation Based on a Novel Watershed Algorithm With an Optimized Mark and Edge Constraint

Peng, Cheng; Liu, Yikun; Gui, Weihua; Tang, Zhaohui; Chen, Qing

doi:10.1109/tim.2021.3129873

Cited by 10 publications

(13 citation statements)

References 18 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, some researchers introduced transfer learning into different fields of study (Xu et al 2015;He et al 2022;Kuang et al 2022). In real application, researchers developed more deep neural network architecture for multiple scenarios (Zeng et al 2021;Fu et al 2022;Lin et al 2022;Peng et al 2022).…”

Section: Introductionmentioning

confidence: 99%

A Hierarchical Method for Locating the Interferometric Fringes of Celestial Sources in the Visibility Data

Ma,

Yan,

Cui

et al. 2024

Res. Astron. Astrophys.

View full text Add to dashboard Cite

In celestial source detection in Tianlai project, locating interferometric fringe in visibility data accurately will influence downstream tasks drastically, such as physical parameters estimation and weak celestial source exploration. Considering that traditional locating methods are time-consuming and supervised methods require a great quantity of expensive labeled data, in this paper, we firstly investigate characteristic of interferometric fringes in simulation and real scenario respectively, and integrate almost parameter-free unsupervised clustering method and seeding filling or eraser algorithm to propose a hierarchical plug and play method to improve locating accuracy. Then, we apply our method to locate single and multiple sources' interferometric fringes in simulation data. Next, we apply our method in real data taken from Tianlai radio telescope array. Finally, we do comparison with unsupervised methods of state of the art. These results show that our method has robustness in different scenarios and can improve locating measurement accuracy effectively.

show abstract

Section: Introductionmentioning

confidence: 99%

A Hierarchical Method for Locating the Interferometric Fringes of Celestial Sources in the Visibility Data

Ma,

Yan,

Cui

et al. 2024

Res. Astron. Astrophys.

View full text Add to dashboard Cite

show abstract

“…Liu et al [11] proposed an online bubble size distribution monitoring scheme through a fully convolutional network with multi-scale deblurring and multi-stage jumping feature fusion to identify the health status of the flotation froth process. Peng et al [12] proposed a watershed algorithm with an optimized mark and edge constraint for accurate segmentation of flotation froth images. Haas et al [13] proposed a faster regionbased convolutional neural network (CNN) detector to locate bubbles and a shape regression CNN to approximate bubble shapes in gas-liquid multi-phase flows.…”

Section: Introductionmentioning

confidence: 99%

Spirits quality classification based on machine vision technology and expert knowledge

Chen

Líu

Zhang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

By combining machine vision technology and expert knowledge, this paper proposes an online intelligent classification solution for Chinese spirits, which effectively improves the classification accuracy and production efficiency of spirits. Specifically, an intelligent spirits quality classification system is first designed, including spirits collectors, image sampling cameras, and computing devices. According to the principle that the size and shape of the bubbles in the spirits collector will change with the alcohol content in the spirits, a classification method of spirits quality based on the convolutional neural network and bubble region of interest selection is proposed. Furthermore, a post-processing method based on expert knowledge is proposed to improve the accuracy of the classification algorithm. A spirits quality classification dataset containing 139119 images is created, and 15 convolutional neural networks are tested. Test results show that the highest spirits quality classification accuracy is 98.62% after using the bubble region of interest selection method, and the highest classification accuracy reached 99.82% after adopting the post-processing method. Furthermore, practical application tests show that the solution proposed in this paper can improve spirits' production quality and efficiency.

show abstract

“…Bubbly flow is a common gas–liquid two-phase flow pattern which widely exists in water conservancy, petroleum, the chemical industry, the nuclear industry, and other fields. For example, the shape and size distributions of bubbles have a high correlation with the performance of mineral froth flotation [ 1 ]. The morphology of bubbles in Chinese spirits is closely related to alcohol concentration and quality [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

End-to-End Bubble Size Distribution Detection Technique in Dense Bubbly Flows Based on You Only Look Once Architecture

Chen

Zhang²,

Yang

et al. 2023

Sensors

View full text Add to dashboard Cite

Accurate measurements of the bubble size distribution (BSD) are crucial for investigating gas–liquid mass transfer mechanisms and describing the characteristics of chemical production. However, measuring the BSD in high-density bubbly flows remains challenging due to limited image algorithms and high data densities. Therefore, an end-to-end BSD detection method in dense bubbly flows based on deep learning is proposed in this paper. The bubble detector locates the positions of dense bubbles utilizing objection detection networks and simultaneously performs ellipse parameter fitting to measure the size of the bubbles. Different You Only Look Once (YOLO) architectures are compared, and YOLOv7 is selected as the backbone network. The complete intersection over union calculation method is modified by the circumferential horizontal rectangle of bubbles, and the loss function is optimized by adding L2 constraints of ellipse size parameters. The experimental results show that the proposed technique surpasses existing methods in terms of precision, recall, and mean square error, achieving values of 0.9871, 0.8725, and 3.8299, respectively. The proposed technique demonstrates high efficiency and accuracy when measuring BSDs in high-density bubbly flows and has the potential for practical applications.

show abstract

Bubble Image Segmentation Based on a Novel Watershed Algorithm With an Optimized Mark and Edge Constraint

Cited by 10 publications

References 18 publications

A Hierarchical Method for Locating the Interferometric Fringes of Celestial Sources in the Visibility Data

A Hierarchical Method for Locating the Interferometric Fringes of Celestial Sources in the Visibility Data

Spirits quality classification based on machine vision technology and expert knowledge

End-to-End Bubble Size Distribution Detection Technique in Dense Bubbly Flows Based on You Only Look Once Architecture

Contact Info

Product

Resources

About