2023 · IEEE SIU 2023
A Transformer-Based Real-Time Focus Detection Technique for Wide-Field Interferometric Microscopy
Can Polat , Alper Güngör , Mustafa Yorulmaz , Bilal Kızılelma , Tolga ÇukurResearch highlights
Focus detection for interferometric microscopy
Combine convolution and attention for real-time focus estimation in wide-field interferometric microscopy.
Why we investigated it
Image focus affects the visibility of biological nanoparticles, so a detector must be precise and fast enough for acquisition.
What the work contributes
The proposed network combines convolutional processing with a transformer and is compared with other focus-detection methods.
What the evidence shows
The study reports improved precision with fewer parameters than the compared methods, together with low inference time.
Build on this work
Use the architecture and evaluation setup as references when developing focus estimation for interferometric imaging.
- Interferometric microscopy
- Transformers
- Focus detection
- Biological imaging
Abstract
Wide-field interferometric microscopy (WIM) has been utilized for visualization of individual biological nanoparticles with high sensitivity. However, the image quality is highly affected by the focusing of the image. Hence, focus detection has been an active research field within the scope of imaging and microscopy. To tackle this issue, we propose a novel convolution and transformer based deep learning technique to detect focus in WIM. The method is compared to other focus detecton techniques and is able to obtain higher precision with less number of parameters. Furthermore, the model achieves real-time focus detection thanks to its low inference time.
Cite
@article{polat2023transformerbased,
title = {A Transformer-Based Real-Time Focus Detection Technique for Wide-Field Interferometric Microscopy},
author = {Can Polat and Alper Güngör and Mustafa Yorulmaz and Bilal Kızılelma and Tolga Çukur},
year = 2023,
journal = {IEEE SIU 2023},
doi = {10.1109/siu59756.2023.10223991},
}