Advanced Three-Dimensional Visualization System for an Integral Imaging Microscope Using a Fully Convolutional Depth Estimation Network

In this paper, we propose an advanced three-dimensional visualization method for an integral imaging microscope system to simultaneously improve the resolution and quality of the reconstructed image. The main advance of the proposed method is that it generates a high-quality three-dimensional model...

Full description

Saved in:
Bibliographic Details
Main Authors: Ki-Chul Kwon, Ki Hoon Kwon, Munkh-Uchral Erdenebat, Yan-Ling Piao, Young-Tae Lim, Yu Zhao, Min Young Kim, Nam Kim
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9144380/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849422664186200064
author Ki-Chul Kwon
Ki Hoon Kwon
Munkh-Uchral Erdenebat
Yan-Ling Piao
Young-Tae Lim
Yu Zhao
Min Young Kim
Nam Kim
author_facet Ki-Chul Kwon
Ki Hoon Kwon
Munkh-Uchral Erdenebat
Yan-Ling Piao
Young-Tae Lim
Yu Zhao
Min Young Kim
Nam Kim
author_sort Ki-Chul Kwon
collection DOAJ
description In this paper, we propose an advanced three-dimensional visualization method for an integral imaging microscope system to simultaneously improve the resolution and quality of the reconstructed image. The main advance of the proposed method is that it generates a high-quality three-dimensional model without limitation of resolution by combining the high-resolution two-dimensional color image with depth data obtained through a fully convolutional neural network. First, the high-resolution two-dimensional image and an elemental image array for a specimen are captured, and the orthographic-view image is reconstructed from the elemental image array. Then, via a convolutional neural network-based depth estimation after the brightness of input images are uniformed, a more accurate and improved depth image is generated; and the noise of result depth image is filtered. Subsequently, the estimated depth data is combined with the high-resolution two-dimensional image and transformed into a high-quality three-dimensional model. In the experiment, it was confirmed that the displayed high-quality three-dimensional model could be visualized very similarly to the original image.
format Article
id doaj-art-1eade5ae99a44e0fbf96214ff1854638
institution Kabale University
issn 1943-0655
language English
publishDate 2020-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-1eade5ae99a44e0fbf96214ff18546382025-08-20T03:30:57ZengIEEEIEEE Photonics Journal1943-06552020-01-0112411410.1109/JPHOT.2020.30103199144380Advanced Three-Dimensional Visualization System for an Integral Imaging Microscope Using a Fully Convolutional Depth Estimation NetworkKi-Chul Kwon0https://orcid.org/0000-0003-0334-504XKi Hoon Kwon1https://orcid.org/0000-0003-3357-0838Munkh-Uchral Erdenebat2https://orcid.org/0000-0001-6941-8577Yan-Ling Piao3https://orcid.org/0000-0001-8809-6243Young-Tae Lim4https://orcid.org/0000-0002-3087-0619Yu Zhao5Min Young Kim6https://orcid.org/0000-0001-7263-3403Nam Kim7https://orcid.org/0000-0001-8109-2055School of Information and Communication Engineering, Chungbuk National University, Cheongju, Chungbuk, South KoreaSchool of Electronics Engineering, Kyungpook National University, Daegu, South KoreaSchool of Information and Communication Engineering, Chungbuk National University, Cheongju, Chungbuk, South KoreaSchool of Information and Communication Engineering, Chungbuk National University, Cheongju, Chungbuk, South KoreaSchool of Information and Communication Engineering, Chungbuk National University, Cheongju, Chungbuk, South KoreaCollege of Information Engineering, Yangzhou University, Yangzhou, ChinaSchool of Electronics Engineering, Kyungpook National University, Daegu, South KoreaSchool of Information and Communication Engineering, Chungbuk National University, Cheongju, Chungbuk, South KoreaIn this paper, we propose an advanced three-dimensional visualization method for an integral imaging microscope system to simultaneously improve the resolution and quality of the reconstructed image. The main advance of the proposed method is that it generates a high-quality three-dimensional model without limitation of resolution by combining the high-resolution two-dimensional color image with depth data obtained through a fully convolutional neural network. First, the high-resolution two-dimensional image and an elemental image array for a specimen are captured, and the orthographic-view image is reconstructed from the elemental image array. Then, via a convolutional neural network-based depth estimation after the brightness of input images are uniformed, a more accurate and improved depth image is generated; and the noise of result depth image is filtered. Subsequently, the estimated depth data is combined with the high-resolution two-dimensional image and transformed into a high-quality three-dimensional model. In the experiment, it was confirmed that the displayed high-quality three-dimensional model could be visualized very similarly to the original image.https://ieeexplore.ieee.org/document/9144380/Integral imaging microscopyresolution enhancementhigh-quality reconstructionfully convolutional depth estimation network
spellingShingle Ki-Chul Kwon
Ki Hoon Kwon
Munkh-Uchral Erdenebat
Yan-Ling Piao
Young-Tae Lim
Yu Zhao
Min Young Kim
Nam Kim
Advanced Three-Dimensional Visualization System for an Integral Imaging Microscope Using a Fully Convolutional Depth Estimation Network
IEEE Photonics Journal
Integral imaging microscopy
resolution enhancement
high-quality reconstruction
fully convolutional depth estimation network
title Advanced Three-Dimensional Visualization System for an Integral Imaging Microscope Using a Fully Convolutional Depth Estimation Network
title_full Advanced Three-Dimensional Visualization System for an Integral Imaging Microscope Using a Fully Convolutional Depth Estimation Network
title_fullStr Advanced Three-Dimensional Visualization System for an Integral Imaging Microscope Using a Fully Convolutional Depth Estimation Network
title_full_unstemmed Advanced Three-Dimensional Visualization System for an Integral Imaging Microscope Using a Fully Convolutional Depth Estimation Network
title_short Advanced Three-Dimensional Visualization System for an Integral Imaging Microscope Using a Fully Convolutional Depth Estimation Network
title_sort advanced three dimensional visualization system for an integral imaging microscope using a fully convolutional depth estimation network
topic Integral imaging microscopy
resolution enhancement
high-quality reconstruction
fully convolutional depth estimation network
url https://ieeexplore.ieee.org/document/9144380/
work_keys_str_mv AT kichulkwon advancedthreedimensionalvisualizationsystemforanintegralimagingmicroscopeusingafullyconvolutionaldepthestimationnetwork
AT kihoonkwon advancedthreedimensionalvisualizationsystemforanintegralimagingmicroscopeusingafullyconvolutionaldepthestimationnetwork
AT munkhuchralerdenebat advancedthreedimensionalvisualizationsystemforanintegralimagingmicroscopeusingafullyconvolutionaldepthestimationnetwork
AT yanlingpiao advancedthreedimensionalvisualizationsystemforanintegralimagingmicroscopeusingafullyconvolutionaldepthestimationnetwork
AT youngtaelim advancedthreedimensionalvisualizationsystemforanintegralimagingmicroscopeusingafullyconvolutionaldepthestimationnetwork
AT yuzhao advancedthreedimensionalvisualizationsystemforanintegralimagingmicroscopeusingafullyconvolutionaldepthestimationnetwork
AT minyoungkim advancedthreedimensionalvisualizationsystemforanintegralimagingmicroscopeusingafullyconvolutionaldepthestimationnetwork
AT namkim advancedthreedimensionalvisualizationsystemforanintegralimagingmicroscopeusingafullyconvolutionaldepthestimationnetwork