A transformer-based real-time focus detection technique for wide-field interferometric microscopy

buir.contributor.authorPolat, Can
buir.contributor.authorÇukur, Tolga
buir.contributor.orcidPolat, Can|0000-0002-1458-302X
buir.contributor.orcidÇukur, Tolga|0000-0002-2296-851X
dc.citation.epage4en_US
dc.citation.spage1
dc.contributor.authorPolat, Can
dc.contributor.authorGüngör, A.
dc.contributor.authorYorulmaz, M.
dc.contributor.authorKızılelma, B.
dc.contributor.authorÇukur, Tolga
dc.coverage.spatialİstanbul, Türkiye
dc.date.accessioned2024-03-22T13:22:23Z
dc.date.available2024-03-22T13:22:23Z
dc.date.issued2023-08-28
dc.departmentDepartment of Electrical and Electronics Engineering
dc.descriptionDate of Conference: 05-08 July 2023
dc.descriptionConference Name: 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023
dc.description.abstractWide-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.
dc.description.abstractGeniş-alan interferometrik mikroskopi (GİM), tekli biyolojik nanopartiküllerin yüksek hassasiyetle görüntülenmesi için kullanılmaktadır. Ancak, görüntü kalitesi görüntünün odaklanma performansından oldukça etkilenmektedir. Bu sebeple, odak tespiti görüntüleme ve mikroskopi literatüründe aktif çalışılan bir konudur. Bu problemin çözümüne yönelik, GİM odağının tespiti için evrişim ve dönüştürücü tabanlı yenilikçi bir derin öğrenme tekniği önerilmektedir. Yöntem, literatürdeki diğer odak tespit teknikleriyle kıyaslanmış ve daha az sayıda parametre ile daha yüksek başarım elde edilebildiği gösterilmiştir. Ayrıca, yöntem düşük çıkarım zamanı sayesinde gerçek zamanlı odak tespitinde bulunabilmektedir.
dc.description.provenanceMade available in DSpace on 2024-03-22T13:22:23Z (GMT). No. of bitstreams: 1 A_transformer-based_real-time_focus_detection_technique_for_wide-field_interferometric_microscopy.pdf: 11111211 bytes, checksum: 761cc4c417c0302c82833f9b5aeda4af (MD5) Previous issue date: 2023-08en
dc.identifier.doi10.1109/SIU59756.2023.10223991
dc.identifier.eisbn9798350343557
dc.identifier.isbn9798350343564
dc.identifier.issn2165-0608
dc.identifier.urihttps://hdl.handle.net/11693/115092
dc.language.isoTurkish
dc.publisherIEEE - Institute of Electrical and Electronics Engineers
dc.relation.isversionofhttps://dx.doi.org/10.1109/SIU59756.2023.10223991
dc.source.title2023 31st Signal Processing and Communications Applications Conference (SIU 2023)
dc.subjectDeep learning
dc.subjectFocus detection
dc.subjectConvolution
dc.subjectTransformer
dc.subjectMicroscopy
dc.subjectReal-time
dc.subjectDerin öğrenme
dc.subjectOdak tespiti
dc.subjectEvrişim
dc.subjectDönüştürücü
dc.subjectMikroskop
dc.subjectGerçek-zamanlı
dc.titleA transformer-based real-time focus detection technique for wide-field interferometric microscopy
dc.title.alternativeGeniş-alan interferometrik mikroskop için dönüştürücü tabanlı gerçek zamanlı odak tespiti tekniği
dc.typeConference Paper

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
A_transformer-based_real-time_focus_detection_technique_for_wide-field_interferometric_microscopy.pdf
Size:
10.6 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.01 KB
Format:
Item-specific license agreed upon to submission
Description: