Design of a deep learning visual system for the thickness measurement of each coating layer of TRISO-coated fuel particles

Zhang, Hang; Liu, Jian; Hu, Zhaochuan; Chen, Ning; Yang, Zhiyuan; Shen, Junhua

doi:10.1016/j.measurement.2022.110806

Cited by 6 publications

(2 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To calibrate cameras more effectively, Song et al [7] relocated the subpixel edge of the feature points detected by the Canny operator, with the aid of Zernike. Zhang et al [8] Combined ceramic slicing with deep learning to measure the thickness of fuel coating automatically and accurately. In general, pixellevel size detection is much more common than subpixel size detection.…”

Section: Introductionmentioning

confidence: 99%

An Improved BM3D-Canny-Zernike Algorithm for Micro-Size Detection of Electronic Connectors

Wang¹,

Yang²,

Ren³

et al. 2022

View full text Add to dashboard Cite

To detect the micro-size injection molded parts of electronic connectors, this paper establishes a complete size detection system based on machine vision, and measures the size through image acquisition and processing, according to the features of the injection molded parts. The proposed system is called the improved BM3D-Canny-Zernike algorithm. Specifically, the traditional block matching and three-dimensional filtering (BM3D) image denoising algorithm was improved to optimize the peak signal-to-noise ratio (PSNR) and reduce the mean squared error (MSE). Then, the Canny algorithm was improved for pixel-level edge detection, and the Zernike moment is improved for detecting edges on the subpixel-level more effectively and reducing the calculation amount. Finally, the least squares method was employed to fit the edge to be measured. The exact pixel length was obtained by solving the function of different edges, thereby realizing size measurement. Experimental results show that the mean error percentage of our algorithm was 8.73%, which meets the needs of industrial detection.

show abstract

Section: Introductionmentioning

confidence: 99%

An Improved BM3D-Canny-Zernike Algorithm for Micro-Size Detection of Electronic Connectors

Wang¹,

Yang²,

Ren³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Not to say the least, machine learning algorithms have played a significant role in the applicability of NDE techniques in material surface characterization. Several researchers have used machine learning algorithms to successfully characterize the material surfaces and the characteristics of coatings and thin films [13][14][15]. Reviews by Mao et al [16] and Fu et al [17] highlight the applicability and advantages of using these techniques to support nondestructive techniques.…”

mentioning

confidence: 99%

Special Issue: Nondestructive Evaluation of Material Surfaces: Theory, Techniques, and Applications

Kannan

Barile

2022

Coatings

View full text Add to dashboard Cite

show abstract

FLSSnet: Few labeled samples segmentation network for coated fuel particle segmentation

Yang,

Zhang,

Liu

et al. 2024

Advanced Engineering Informatics

View full text Add to dashboard Cite

Design of a deep learning visual system for the thickness measurement of each coating layer of TRISO-coated fuel particles

Cited by 6 publications

References 52 publications

An Improved BM3D-Canny-Zernike Algorithm for Micro-Size Detection of Electronic Connectors

An Improved BM3D-Canny-Zernike Algorithm for Micro-Size Detection of Electronic Connectors

Special Issue: Nondestructive Evaluation of Material Surfaces: Theory, Techniques, and Applications

FLSSnet: Few labeled samples segmentation network for coated fuel particle segmentation

Contact Info

Product

Resources

About