Deep convolutional neural network-based lensless quantitative phase retrieval

In this paper, we employ a deep convolutional neural network for the solution of the phase retrieval problem in a lensless optical system from a single observation. We utilize U-net structured DCNN to reconstruct phase from the amplitude images at the sensor plane, and after applying computational backpropagation, complex objects' amplitude is reconstructed at the object plane. Results are demonstrated by simulation experiments.

[1]  Shuai Li,et al.  Lensless computational imaging through deep learning , 2017, ArXiv.

[2]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[3]  Zachary David Cleary Kemp,et al.  Propagation based phase retrieval of simulated intensity measurements using artificial neural networks , 2017, 1709.09940.

[4]  Yibo Zhang,et al.  Phase recovery and holographic image reconstruction using deep learning in neural networks , 2017, Light: Science & Applications.

[5]  Michael Unser,et al.  Deep Convolutional Neural Network for Inverse Problems in Imaging , 2016, IEEE Transactions on Image Processing.

[6]  Richard G. Baraniuk,et al.  prDeep: Robust Phase Retrieval with a Flexible Deep Network , 2018, ICML.

[7]  Jordan M. Malof,et al.  Deep learning for accelerated all-dielectric metasurface design. , 2019, Optics express.

[8]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[9]  R. Gerchberg.  A practical algorithm for the determination of phase from image and diffraction plane pictures , 1972 .

[10]  Guohai Situ,et al.  Learning-based lensless imaging through optically thick scattering media , 2019, Advanced Photonics.

[11]  J. Goodman.  Introduction to Fourier optics , 1969 .

[12]  Pavel A. Cheremkhin,et al.  Machine learning methods for digital holography and diffractive optics , 2020 .

[13]  Dennis Gabor,et al.  Interference Microscope with Total Wavefront Reconstruction , 1966 .

[14]  A. Ozcan,et al.  On the use of deep learning for computational imaging , 2019, Optica.

[15]  Lei Tian,et al.  Reliable deep-learning-based phase imaging with uncertainty quantification. , 2019 .

[16]  Figen S. Oktem,et al.  Deep Iterative Reconstruction for Phase Retrieval , 2019, Applied optics.

[17]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).