EUVIMEDEUVIMED entdecken
Crossref

Feature engineering with neural networks in Shack–Hartmann wavefront sensing

Akash Kumar Tarai, Suman Sangiri, Likhith Kumar Pampana, Sambit Kumar Shukla, Vyas Akondi

Journal of the Optical Society of America A · 01.08.2026 · 43 (8) · D64

DOI: 10.1364/josaa.590445 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the Optical Society of America A, online erschienen am 14.05.2026. Verfasst von Akash Kumar Tarai und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Indian Institute of Science Education and Research Berhampur, Indian Council of Medical Research, Science and Engineering Research Board.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wavefront sensing in conventional Shack–Hartmann wavefront sensors (SHWSs) relies on sequential centroiding and wavefront slope fitting algorithms, which are computationally demanding and whose accuracy is limited by wavefront sampling. In this work, we propose hybrid machine learning (ML) strategies combining feature selection and extraction with artificial neural networks (ANNs) that enhance both the wavefront sensing accuracy and computational efficiency. The ML models proposed for use in a SHWS (8×8 lenslets) are compared against a robust traditional wavefront sensing algorithm. Using a numerically simulated dataset of 10000 SHWS images, we evaluated three approaches: (1) manual feature selection (MFS) with ANNs, (2) random forest (RF)–based feature selection with ANNs, and (3) principal component analysis (PCA)–based feature extraction with ANNs. These methods achieved an average wavefront root-mean-square (RMS) error lower than the traditional algorithm, while maintaining sub-millisecond wavefront sensing time. To evaluate the models’ performance under realistic conditions, we introduced a simulated Gaussian readout noise with a standard deviation of 15 ADU for a 12-bit camera. Evaluations using both noise-free models and those explicitly trained on noisy data confirmed that the proposed ML frameworks remain robust to readout noise. All the simulations and neural network training were performed on a personal laptop without a dedicated GPU or high-performance computing resources. These results demonstrate that integrating feature engineering with ANNs offers significant potential for accurate and computationally efficient SH wavefront sensing.

Förderung

  • Indian Institute of Science Education and Research Berhampur
  • Indian Council of Medical Research
  • Science and Engineering Research Board

Zitieren

APA

Tarai, A. K., Sangiri, S., Pampana, L. K., Shukla, S. K., & Akondi, V. (2026). Feature engineering with neural networks in Shack–Hartmann wavefront sensing. Journal of the Optical Society of America A, 43(8), D64. https://doi.org/10.1364/josaa.590445

Vancouver

Tarai AK, Sangiri S, Pampana LK, Shukla SK, Akondi V. Feature engineering with neural networks in Shack–Hartmann wavefront sensing. Journal of the Optical Society of America A. 2026;43(8):D64. doi:10.1364/josaa.590445

BibTeX
@article{Tarai2026,
  author = {Tarai, Akash Kumar and Sangiri, Suman and Pampana, Likhith Kumar and Shukla, Sambit Kumar and Akondi, Vyas},
  title = {Feature engineering with neural networks in Shack–Hartmann wavefront sensing},
  journal = {Journal of the Optical Society of America A},
  year = {2026},
  volume = {43},
  number = {8},
  pages = {D64},
  doi = {10.1364/josaa.590445}
}
Kostenlos starten →