Fast Autofocusing using Tiny Transformer Networks for Digital Holographic Microscopy

TL;DR

This paper introduces tiny transformer-based neural networks for fast, accurate autofocus in digital holographic microscopy, achieving high precision and low inference time suitable for real-time applications.

Contribution

It proposes and evaluates tiny transformer models for autofocus in holography, demonstrating their efficiency and accuracy compared to traditional neural networks.

Findings

Achieves 1.2 μm average accuracy in focusing distance prediction.

Inference time under 25 ms per image on CPU.

Tiny models outperform some traditional networks in robustness and speed.

Abstract

The numerical wavefront backpropagation principle of digital holography confers unique extended focus capabilities, without mechanical displacements along z-axis. However, the determination of the correct focusing distance is a non-trivial and time consuming issue. A deep learning (DL) solution is proposed to cast the autofocusing as a regression problem and tested over both experimental and simulated holograms. Single wavelength digital holograms were recorded by a Digital Holographic Microscope (DHM) with a 10$\mathrm{x}$ microscope objective from a patterned target moving in 3D over an axial range of 92 $\mu$m. Tiny DL models are proposed and compared such as a tiny Vision Transformer (TViT), tiny VGG16 (TVGG) and a tiny Swin-Transfomer (TSwinT). The proposed tiny networks are compared with their original versions (ViT/B16, VGG16 and Swin-Transformer Tiny) and the main neural networks used in digital holography such as LeNet and AlexNet. The experiments show that the predicted focusing distance $Z_R^{\mathrm{Pred}}$ is accurately inferred with an accuracy of 1.2 $\mu$m in average in comparison with the DHM depth of field of 15 $\mu$m. Numerical simulations show that all tiny models give the $Z_R^{\mathrm{Pred}}$ with an error below 0.3 $\mu$m. Such a prospect would significantly improve the current capabilities of computer vision position sensing in applications such as 3D microscopy for life sciences or micro-robotics. Moreover, all models reach an inference time on CPU, inferior to 25 ms per inference. In terms of occlusions, TViT based on its Transformer architecture is the most robust.