Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network
<jats:p>Lensless holography promises compact, low-cost optical apparatus designs with similar performance to traditional imaging setups. Here, we propose the use of a silicon micro-LED fabricated in a commercial CMOS microelectronics process as the illumination source in a le...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Optica Publishing Group
2023
|
| Online Access: | https://hdl.handle.net/1721.1/150779 |
| _version_ | 1826202031671476224 |
|---|---|
| author | Kang, Iksung de Cea, Marc Xue, Jin Li, Zheng Barbastathis, George Ram, Rajeev J |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Kang, Iksung de Cea, Marc Xue, Jin Li, Zheng Barbastathis, George Ram, Rajeev J |
| author_sort | Kang, Iksung |
| collection | MIT |
| description | <jats:p>Lensless holography promises compact, low-cost optical apparatus
designs with similar performance to traditional imaging setups. Here,
we propose the use of a silicon micro-LED fabricated in a commercial
CMOS microelectronics process as the illumination source in a lensless
holographic microscope. Its small emission area
(<jats:inline-formula>
<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline">
<mml:mrow class="MJX-TeXAtom-ORD">
<mml:mo><<!-- < --></mml:mo>
</mml:mrow>
<mml:mn>4</mml:mn>
<mml:mspace width="thinmathspace" />
<mml:mtext>µ<!-- µ --></mml:mtext>
<mml:msup>
<mml:mrow class="MJX-TeXAtom-ORD">
<mml:mi mathvariant="normal">m</mml:mi>
</mml:mrow>
<mml:mn>2</mml:mn>
</mml:msup>
</mml:math>
</jats:inline-formula>) ensures high spatial
coherence without the need for a pinhole and results in a large NA
setup, circumventing the limits to the source-to-sample distance
encountered by conventional lensless holography apparatus. The scene
is reconstructed using an untrained deep neural network architecture
that simultaneously performs spectral recovery by learning from the
given single experimental diffraction intensity. We envision this
synergetic combination of CMOS micro-LEDs and the machine learning
framework can be used in other computational imaging applications,
such as a compact microscope for live-cell tracking or spectroscopic
imaging of biological materials.</jats:p> |
| first_indexed | 2024-09-23T12:01:07Z |
| format | Article |
| id | mit-1721.1/150779 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T12:01:07Z |
| publishDate | 2023 |
| publisher | Optica Publishing Group |
| record_format | dspace |
| spelling | mit-1721.1/1507792023-05-20T03:28:10Z Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network Kang, Iksung de Cea, Marc Xue, Jin Li, Zheng Barbastathis, George Ram, Rajeev J Massachusetts Institute of Technology. Department of Mechanical Engineering <jats:p>Lensless holography promises compact, low-cost optical apparatus designs with similar performance to traditional imaging setups. Here, we propose the use of a silicon micro-LED fabricated in a commercial CMOS microelectronics process as the illumination source in a lensless holographic microscope. Its small emission area (<jats:inline-formula> <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> <mml:mrow class="MJX-TeXAtom-ORD"> <mml:mo><<!-- < --></mml:mo> </mml:mrow> <mml:mn>4</mml:mn> <mml:mspace width="thinmathspace" /> <mml:mtext>µ<!-- µ --></mml:mtext> <mml:msup> <mml:mrow class="MJX-TeXAtom-ORD"> <mml:mi mathvariant="normal">m</mml:mi> </mml:mrow> <mml:mn>2</mml:mn> </mml:msup> </mml:math> </jats:inline-formula>) ensures high spatial coherence without the need for a pinhole and results in a large NA setup, circumventing the limits to the source-to-sample distance encountered by conventional lensless holography apparatus. The scene is reconstructed using an untrained deep neural network architecture that simultaneously performs spectral recovery by learning from the given single experimental diffraction intensity. We envision this synergetic combination of CMOS micro-LEDs and the machine learning framework can be used in other computational imaging applications, such as a compact microscope for live-cell tracking or spectroscopic imaging of biological materials.</jats:p> 2023-05-19T13:48:24Z 2023-05-19T13:48:24Z 2022 2023-05-19T13:45:48Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/150779 Kang, Iksung, de Cea, Marc, Xue, Jin, Li, Zheng, Barbastathis, George et al. 2022. "Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network." Optica, 9 (10). en 10.1364/OPTICA.470712 Optica Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Optica Publishing Group Optica |
| spellingShingle | Kang, Iksung de Cea, Marc Xue, Jin Li, Zheng Barbastathis, George Ram, Rajeev J Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network |
| title | Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network |
| title_full | Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network |
| title_fullStr | Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network |
| title_full_unstemmed | Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network |
| title_short | Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network |
| title_sort | simultaneous spectral recovery and cmos micro led holography with an untrained deep neural network |
| url | https://hdl.handle.net/1721.1/150779 |
| work_keys_str_mv | AT kangiksung simultaneousspectralrecoveryandcmosmicroledholographywithanuntraineddeepneuralnetwork AT deceamarc simultaneousspectralrecoveryandcmosmicroledholographywithanuntraineddeepneuralnetwork AT xuejin simultaneousspectralrecoveryandcmosmicroledholographywithanuntraineddeepneuralnetwork AT lizheng simultaneousspectralrecoveryandcmosmicroledholographywithanuntraineddeepneuralnetwork AT barbastathisgeorge simultaneousspectralrecoveryandcmosmicroledholographywithanuntraineddeepneuralnetwork AT ramrajeevj simultaneousspectralrecoveryandcmosmicroledholographywithanuntraineddeepneuralnetwork |