Autofocusing algorithm for a digital holographic imaging system using convolutional neural networks

Kyungchan Son, Wooyoung Jeong, Wonseok Jeon, Hyunseok Yang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Digital holographic imaging systems are promising three-dimensional imaging systems that acquire holograms via interference of a reference wave and an object wave. Using digital holography and the numerical diffraction theory, an image can be reconstructed at any distance from the hologram. However, accurate determination of the distance of the object from the hologram is required to focus the image. Various autofocusing algorithms have been studied. The conventional autofocusing algorithm creates the focused image by evaluating iteratively reconstructed images using focus metrics. Owing to the iterative image reconstruction process, the computational time is very long. In this paper, an autofocusing algorithm for a digital holographic imaging system using convolutional neural networks, similar to pattern recognition systems, is proposed. Using the proposed method, the distance of the object from the hologram is obtained more rapidly than using the conventional method.

Original languageEnglish
Article number09SB02
JournalJapanese Journal of Applied Physics
Volume57
Issue number9
DOIs
Publication statusPublished - 2018 Sep

Fingerprint

Holograms
Imaging systems
Neural networks
Pattern recognition systems
Wave interference
Holography
image reconstruction
Image reconstruction
pattern recognition
holography
Diffraction
interference
diffraction

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Physics and Astronomy(all)

Cite this

@article{7212ef5fdd124f6ab0caba2ef2afd4c8,
title = "Autofocusing algorithm for a digital holographic imaging system using convolutional neural networks",
abstract = "Digital holographic imaging systems are promising three-dimensional imaging systems that acquire holograms via interference of a reference wave and an object wave. Using digital holography and the numerical diffraction theory, an image can be reconstructed at any distance from the hologram. However, accurate determination of the distance of the object from the hologram is required to focus the image. Various autofocusing algorithms have been studied. The conventional autofocusing algorithm creates the focused image by evaluating iteratively reconstructed images using focus metrics. Owing to the iterative image reconstruction process, the computational time is very long. In this paper, an autofocusing algorithm for a digital holographic imaging system using convolutional neural networks, similar to pattern recognition systems, is proposed. Using the proposed method, the distance of the object from the hologram is obtained more rapidly than using the conventional method.",
author = "Kyungchan Son and Wooyoung Jeong and Wonseok Jeon and Hyunseok Yang",
year = "2018",
month = "9",
doi = "10.7567/JJAP.57.09SB02",
language = "English",
volume = "57",
journal = "Japanese Journal of Applied Physics, Part 1: Regular Papers & Short Notes",
issn = "0021-4922",
publisher = "Japan Society of Applied Physics",
number = "9",

}

Autofocusing algorithm for a digital holographic imaging system using convolutional neural networks. / Son, Kyungchan; Jeong, Wooyoung; Jeon, Wonseok; Yang, Hyunseok.

In: Japanese Journal of Applied Physics, Vol. 57, No. 9, 09SB02, 09.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Autofocusing algorithm for a digital holographic imaging system using convolutional neural networks

AU - Son, Kyungchan

AU - Jeong, Wooyoung

AU - Jeon, Wonseok

AU - Yang, Hyunseok

PY - 2018/9

Y1 - 2018/9

N2 - Digital holographic imaging systems are promising three-dimensional imaging systems that acquire holograms via interference of a reference wave and an object wave. Using digital holography and the numerical diffraction theory, an image can be reconstructed at any distance from the hologram. However, accurate determination of the distance of the object from the hologram is required to focus the image. Various autofocusing algorithms have been studied. The conventional autofocusing algorithm creates the focused image by evaluating iteratively reconstructed images using focus metrics. Owing to the iterative image reconstruction process, the computational time is very long. In this paper, an autofocusing algorithm for a digital holographic imaging system using convolutional neural networks, similar to pattern recognition systems, is proposed. Using the proposed method, the distance of the object from the hologram is obtained more rapidly than using the conventional method.

AB - Digital holographic imaging systems are promising three-dimensional imaging systems that acquire holograms via interference of a reference wave and an object wave. Using digital holography and the numerical diffraction theory, an image can be reconstructed at any distance from the hologram. However, accurate determination of the distance of the object from the hologram is required to focus the image. Various autofocusing algorithms have been studied. The conventional autofocusing algorithm creates the focused image by evaluating iteratively reconstructed images using focus metrics. Owing to the iterative image reconstruction process, the computational time is very long. In this paper, an autofocusing algorithm for a digital holographic imaging system using convolutional neural networks, similar to pattern recognition systems, is proposed. Using the proposed method, the distance of the object from the hologram is obtained more rapidly than using the conventional method.

UR - http://www.scopus.com/inward/record.url?scp=85053303919&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053303919&partnerID=8YFLogxK

U2 - 10.7567/JJAP.57.09SB02

DO - 10.7567/JJAP.57.09SB02

M3 - Article

AN - SCOPUS:85053303919

VL - 57

JO - Japanese Journal of Applied Physics, Part 1: Regular Papers & Short Notes

JF - Japanese Journal of Applied Physics, Part 1: Regular Papers & Short Notes

SN - 0021-4922

IS - 9

M1 - 09SB02

ER -