Fast Autofocusing using Tiny Networks for Digital Holographic Microscopy

by   Stéphane Cuenat, et al.

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 10x microscope objective from a patterned target moving in 3D over an axial range of 92 μm. Tiny DL models are proposed and compared such as a tiny Vision Transformer (TViT), tiny VGG16 (TVGG) and a tiny Swin-Transfomer (TSwinT). The experiments show that the predicted focusing distance Z_R^Pred is accurately inferred with an accuracy of 1.2 μm in average in comparison with the DHM depth of field of 15 μm. Numerical simulations show that all tiny models give the Z_R^Pred with an error below 0.3 μm. 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 state of the art inference time on CPU, less than 25 ms per inference.


page 1

page 3

page 4

page 5

page 7

page 8


Convolutional Neural Network (CNN) vs Visual Transformer (ViT) for Digital Holography

In Digital Holography (DH), it is crucial to extract the object distance...

Deep Learning Enhanced Extended Depth-of-Field for Thick Blood-Film Malaria High-Throughput Microscopy

Fast accurate diagnosis of malaria is still a global health challenge fo...

Model Asset eXchange: Path to Ubiquitous Deep Learning Deployment

A recent trend observed in traditionally challenging fields such as comp...

MMDF: Mobile Microscopy Deep Framework

In the last decade, a huge step was done in the field of mobile microsco...

Classic versus deep approaches to address computer vision challenges

Computer vision and image processing address many challenging applicatio...

Please sign up or login with your details

Forgot password? Click here to reset