EUVIMEDEUVIMED entdecken
Crossref

Three-stage training strategy phase unwrapping method for high speckle noises

Kejia Li, Zixin Zhao, Hong Zhao, Menghang Zhou, Luo Jin, Wang Danyun, Wang Zhiyu, Lu Zhang

Optics Express · 30.12.2024 · 32 (27) · 48895

DOI: 10.1364/oe.544968 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 23.12.2024. Verfasst von Kejia Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 76-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Program of Xi'an, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning has been widely used in phase unwrapping. However, owing to the noise of the wrapped phase, errors in wrap count prediction and phase calculation can occur, making it challenging to achieve high measurement accuracy under high-noise conditions. To address this issue, a three-stage multi-task phase unwrapping method was proposed. The phase retrieval was divided into three training stages: wrapped phase denoising, wrap count prediction, and unwrapped phase error compensation. In the first stage, a noise preprocessing module was trained to reduce noise interference, thereby improving the accuracy of the wrap count prediction and phase calculation. The second stage involved training the wrap count prediction module. A residual compensation module was added to correct the errors from the denoising results generated in the first stage. Finally, in the third stage, the phase error compensation module was trained to correct errors in the unwrapped phase calculated in the second stage. Additionally, a convolution-based multi-scale spatial attention module was proposed, which effectively reduces the interference of spatially inconsistent noise and can be applied to a convolutional neural network. The principles of the multi-task phase unwrapping method based on a three-stage training strategy were first introduced. Subsequently, the framework and training strategies for each stage were presented. Finally, the method was tested using simulated data with varying noise levels. It was compared with TIE, iterative TIE, the least squares phase unwrapping method, UNet, phaseNet2.0, and DeepLabV3 + with a phase correction operation, demonstrating the noise robustness and phase retrieval accuracy of the proposed method.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Program of Xi'an, China

Zitieren

APA

Li, K., Zhao, Z., Zhao, H., Zhou, M., Jin, L., Danyun, W., Zhiyu, W., & Zhang, L. (2024). Three-stage training strategy phase unwrapping method for high speckle noises. Optics Express, 32(27), 48895. https://doi.org/10.1364/oe.544968

Vancouver

Li K, Zhao Z, Zhao H, Zhou M, Jin L, Danyun W, et al. Three-stage training strategy phase unwrapping method for high speckle noises. Optics Express. 2024;32(27):48895. doi:10.1364/oe.544968

BibTeX
@article{Li2024,
  author = {Li, Kejia and Zhao, Zixin and Zhao, Hong and Zhou, Menghang and Jin, Luo and Danyun, Wang and Zhiyu, Wang and Zhang, Lu},
  title = {Three-stage training strategy phase unwrapping method for high speckle noises},
  journal = {Optics Express},
  year = {2024},
  volume = {32},
  number = {27},
  pages = {48895},
  doi = {10.1364/oe.544968}
}
Kostenlos starten →