2023 · Optics and Lasers in Engineering

High-precision laser focus positioning of rough surfaces by deep learning

Can Polat , Gizem Nuran Yapici , Sepehr Elahi , Parviz Elahi

Research highlights

Laser positioning on rough surfaces

Locate laser focus from diffraction patterns while accounting for surface roughness and camera noise.

Why we investigated it

Surface texture changes the optical signal, making precise positioning difficult across different workpieces.

What the work contributes

A CNN classifies diffraction-pattern images at focus positions spaced by about 7% of the lens's Rayleigh length; a theoretical model studies noise effects.

What the evidence shows

Experiments on copper, silicon, and steel report positioning accuracy above 99% under the tested setup.

Build on this work

Use the measurement spacing and noise model as references for evaluating focus detectors on rough surfaces.

  • Laser positioning
  • Rough surfaces
  • Diffraction imaging
  • Deep learning
Cite
@article{polat2023highprecision,
  title = {High-precision laser focus positioning of rough surfaces by deep learning},
  author = {Can Polat and Gizem Nuran Yapici and Sepehr Elahi and Parviz Elahi},
  year = 2023,
  journal = {Optics and Lasers in Engineering},
  doi = {10.1016/j.optlaseng.2023.107646},
}