|
|
Frontiers of Information Technology & Electronic Engineering
ISSN 2095-9184 (print), ISSN 2095-9230 (online)
2021 Vol.22 No.10 P.1277-1288
Deep learning based wavefront sensor for complex wavefront detection in adaptive optical microscopes
Abstract: The Shack-Hartmann wavefront sensor (SHWS) is an essential tool for wavefront sensing in adaptive optical microscopes. However, the distorted spots induced by the complex wavefront challenge its detection performance. Here, we propose a deep learning based wavefront detection method which combines point spread function image based Zernike coefficient estimation and wavefront stitching. Rather than using the centroid displacements of each micro-lens, this method first estimates the Zernike coefficients of local wavefront distribution over each micro-lens and then stitches the local wavefronts for reconstruction. The proposed method can offer low root mean square wavefront errors and high accuracy for complex wavefront detection, and has potential to be applied in adaptive optical microscopes.
Key words: Adaptive optics, Wavefront detection, Deep learning, Zernike coefficients, Microscopy
1浙江大学医学院，现代光学仪器国家重点实验室，浙江大学医学院附属第一医院神经内科，中国杭州市，310009
2浙江大学光电科学与工程学院，中国杭州市，310027
3浙江大学脑科学与脑医学学院，中国医学科学院情感和情感障碍的脑机制创新单元，教育部脑与脑机融合前沿科学中心，，中国杭州市，310058
摘要：Shack-Hartmann波前传感器（SHWS）是自适应光学显微镜中用于波前传感的重要工具。然而，由复杂波前相位分布引起的畸变点阵限制了其探测性能。本文提出一种基于深度学习的波前探测方法，该方法结合了基于点扩散函数图像的泽尼克（Zernike）系数估计和波前相位分布拼接。该方法不仅仅使用每个子孔径的质心位移，而是通过子孔径的点扩散函数分布估计局部波前对应的Zernike系数，然后拼接局部波前进行重建。本文所提方法可实现高精度的复杂波前检测，获得的波前残差均方根误差值显著降低，在自适应光学显微中具有极大应用潜力。
关键词组：
References:
Open peer comments: Debate/Discuss/Question/Opinion
<1>
DOI:
10.1631/FITEE.2000422
CLC number:
O439
Download Full Text:
Downloaded:
3709
Download summary:
<Click Here>Downloaded:
1319Clicked:
5867
Cited:
0
On-line Access:
2021-10-08
Received:
2020-08-21
Revision Accepted:
2020-12-17
Crosschecked:
2021-01-25