Using Diffraction Deep Neural Networks for Indirect Phase Recovery Based on Zernike Polynomials
The phase recovery module is dedicated to acquiring phase distribution information within imaging systems, enabling the monitoring and adjustment of a system’s performance. Traditional phase inversion techniques exhibit limitations, such as the speed of the sensor and complexity of the system. There...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/2/698 |
| _version_ | 1827369310797955072 |
|---|---|
| author | Fang Yuan Yang Sun Yuting Han Hairong Chu Tianxiang Ma Honghai Shen |
| author_facet | Fang Yuan Yang Sun Yuting Han Hairong Chu Tianxiang Ma Honghai Shen |
| author_sort | Fang Yuan |
| collection | DOAJ |
| description | The phase recovery module is dedicated to acquiring phase distribution information within imaging systems, enabling the monitoring and adjustment of a system’s performance. Traditional phase inversion techniques exhibit limitations, such as the speed of the sensor and complexity of the system. Therefore, we propose an indirect phase retrieval approach based on a diffraction neural network. By utilizing non-source diffraction through multiple layers of diffraction units, this approach reconstructs coefficients based on Zernike polynomials from incident beams with distorted phases, thereby indirectly synthesizing interference phases. Through network training and simulation testing, we validate the effectiveness of this approach, showcasing the trained network’s capacity for single-order phase recognition and multi-order composite phase inversion. We conduct an analysis of the network’s generalization and evaluate the impact of the network depth on the restoration accuracy. The test results reveal an average root mean square error of 0.086<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula> for phase inversion. This research provides new insights and methodologies for the development of the phase recovery component in adaptive optics systems. |
| first_indexed | 2024-03-08T09:46:16Z |
| format | Article |
| id | doaj.art-115c6b4c585444edbfffdcb47e7f0437 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T09:46:16Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-115c6b4c585444edbfffdcb47e7f04372024-01-29T14:18:30ZengMDPI AGSensors1424-82202024-01-0124269810.3390/s24020698Using Diffraction Deep Neural Networks for Indirect Phase Recovery Based on Zernike PolynomialsFang Yuan0Yang Sun1Yuting Han2Hairong Chu3Tianxiang Ma4Honghai Shen5Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaThe phase recovery module is dedicated to acquiring phase distribution information within imaging systems, enabling the monitoring and adjustment of a system’s performance. Traditional phase inversion techniques exhibit limitations, such as the speed of the sensor and complexity of the system. Therefore, we propose an indirect phase retrieval approach based on a diffraction neural network. By utilizing non-source diffraction through multiple layers of diffraction units, this approach reconstructs coefficients based on Zernike polynomials from incident beams with distorted phases, thereby indirectly synthesizing interference phases. Through network training and simulation testing, we validate the effectiveness of this approach, showcasing the trained network’s capacity for single-order phase recognition and multi-order composite phase inversion. We conduct an analysis of the network’s generalization and evaluate the impact of the network depth on the restoration accuracy. The test results reveal an average root mean square error of 0.086<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>λ</mi></semantics></math></inline-formula> for phase inversion. This research provides new insights and methodologies for the development of the phase recovery component in adaptive optics systems.https://www.mdpi.com/1424-8220/24/2/698phase recoverydiffractive deep neural networkZernike polynomial |
| spellingShingle | Fang Yuan Yang Sun Yuting Han Hairong Chu Tianxiang Ma Honghai Shen Using Diffraction Deep Neural Networks for Indirect Phase Recovery Based on Zernike Polynomials Sensors phase recovery diffractive deep neural network Zernike polynomial |
| title | Using Diffraction Deep Neural Networks for Indirect Phase Recovery Based on Zernike Polynomials |
| title_full | Using Diffraction Deep Neural Networks for Indirect Phase Recovery Based on Zernike Polynomials |
| title_fullStr | Using Diffraction Deep Neural Networks for Indirect Phase Recovery Based on Zernike Polynomials |
| title_full_unstemmed | Using Diffraction Deep Neural Networks for Indirect Phase Recovery Based on Zernike Polynomials |
| title_short | Using Diffraction Deep Neural Networks for Indirect Phase Recovery Based on Zernike Polynomials |
| title_sort | using diffraction deep neural networks for indirect phase recovery based on zernike polynomials |
| topic | phase recovery diffractive deep neural network Zernike polynomial |
| url | https://www.mdpi.com/1424-8220/24/2/698 |
| work_keys_str_mv | AT fangyuan usingdiffractiondeepneuralnetworksforindirectphaserecoverybasedonzernikepolynomials AT yangsun usingdiffractiondeepneuralnetworksforindirectphaserecoverybasedonzernikepolynomials AT yutinghan usingdiffractiondeepneuralnetworksforindirectphaserecoverybasedonzernikepolynomials AT hairongchu usingdiffractiondeepneuralnetworksforindirectphaserecoverybasedonzernikepolynomials AT tianxiangma usingdiffractiondeepneuralnetworksforindirectphaserecoverybasedonzernikepolynomials AT honghaishen usingdiffractiondeepneuralnetworksforindirectphaserecoverybasedonzernikepolynomials |