Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A convolutional neural network-based joint detection and localization spatiotemporal scheme for process control through speckle pattern imaging

Sabahno, Hamed LU orcid and Khodadad, Davood (2025) In Computers & Industrial Engineering 210. p.1-17
Abstract
This paper presents a novel convolutional neural network (CNN)-based control chart for detecting localized and subtle speckle shifts (displacements) in the images. To enhance detection accuracy, especially in detecting localized and simultaneous shifts, we design a custom CNN architecture and utilize a training methodology. Moreover, instead of inputting the entire images, we divide them into equal-sized grids and process them as two-channel inputs: one containing the shifted grids and the other capturing the difference between shifted and reference grids. A maximum probability-based control scheme is developed to concurrently detect shifted images and localize shifted regions within an image. To the best of our knowledge, this is also the... (More)
This paper presents a novel convolutional neural network (CNN)-based control chart for detecting localized and subtle speckle shifts (displacements) in the images. To enhance detection accuracy, especially in detecting localized and simultaneous shifts, we design a custom CNN architecture and utilize a training methodology. Moreover, instead of inputting the entire images, we divide them into equal-sized grids and process them as two-channel inputs: one containing the shifted grids and the other capturing the difference between shifted and reference grids. A maximum probability-based control scheme is developed to concurrently detect shifted images and localize shifted regions within an image. To the best of our knowledge, this is also the first spatiotemporal scheme that simultaneously performs detection and localization, while conducting image-based process control. We perform simulation studies under two main scenarios: (i) spatial domain analysis and (ii) frequency domain analysis. The control chart's performance is evaluated across various grid sizes, shift magnitudes, and shifted areas. Additionally, we demonstrate our scheme's capability through several real-time monitoring examples. Comparative analysis with the existing methods showed that our CNN-based control chart significantly out-performed the existing approach, particularly in detecting small global shifts, localized shifts, and simultaneous shifts. (Less)
Please use this url to cite or link to this publication:
author
and
publishing date
type
Contribution to journal
publication status
published
subject
keywords
convolutional neural network, process control, Control charts, Image data, Speckle pattern analysis, Monte Carlo simulation
in
Computers & Industrial Engineering
volume
210
article number
111538
pages
1 - 17
publisher
Elsevier
ISSN
0360-8352
DOI
10.1016/j.cie.2025.111538
language
English
LU publication?
no
id
aa8b397c-89cb-4a7e-8ca2-7b7f2a3db40a
date added to LUP
2025-09-25 11:30:08
date last changed
2025-09-25 11:48:45
@article{aa8b397c-89cb-4a7e-8ca2-7b7f2a3db40a,
  abstract     = {{This paper presents a novel convolutional neural network (CNN)-based control chart for detecting localized and subtle speckle shifts (displacements) in the images. To enhance detection accuracy, especially in detecting localized and simultaneous shifts, we design a custom CNN architecture and utilize a training methodology. Moreover, instead of inputting the entire images, we divide them into equal-sized grids and process them as two-channel inputs: one containing the shifted grids and the other capturing the difference between shifted and reference grids. A maximum probability-based control scheme is developed to concurrently detect shifted images and localize shifted regions within an image. To the best of our knowledge, this is also the first spatiotemporal scheme that simultaneously performs detection and localization, while conducting image-based process control. We perform simulation studies under two main scenarios: (i) spatial domain analysis and (ii) frequency domain analysis. The control chart's performance is evaluated across various grid sizes, shift magnitudes, and shifted areas. Additionally, we demonstrate our scheme's capability through several real-time monitoring examples. Comparative analysis with the existing methods showed that our CNN-based control chart significantly out-performed the existing approach, particularly in detecting small global shifts, localized shifts, and simultaneous shifts.}},
  author       = {{Sabahno, Hamed and Khodadad, Davood}},
  issn         = {{0360-8352}},
  keywords     = {{convolutional neural network; process control; Control charts; Image data; Speckle pattern analysis; Monte Carlo simulation}},
  language     = {{eng}},
  pages        = {{1--17}},
  publisher    = {{Elsevier}},
  series       = {{Computers & Industrial Engineering}},
  title        = {{A convolutional neural network-based joint detection and localization spatiotemporal scheme for process control through speckle pattern imaging}},
  url          = {{https://lup.lub.lu.se/search/files/228440216/CAIE.pdf}},
  doi          = {{10.1016/j.cie.2025.111538}},
  volume       = {{210}},
  year         = {{2025}},
}