Data-Decoupled Scattering Imaging Method Based on Autocorrelation Enhancement

Target recovery through scattering media is an important aspect of optical imaging. Although various algorithms combining deep-learning methods for target recovery through scattering media exist, they have limitations in terms of robustness and generalization. To address these issues, this study proposes a data-decoupled scattering imaging method based on autocorrelation enhancement. This method constructs basic-element datasets, acquires the speckle images corresponding to these elements, and trains a deep-learning model using the autocorrelation images generated from the elements using speckle autocorrelation as prior physical knowledge to achieve the scattering recovery imaging of targets across data domains. To remove noise terms and enhance the signal-to-noise ratio, a deep-learning model based on the encoder–decoder structure was used to recover a speckle autocorrelation image with a high signal-to-noise ratio. Finally, clarity reconstruction of the target is achieved by applying the traditional phase-recovery algorithm. The results demonstrate that this process improves the peak signal-to-noise ratio of the data from 15 to 37.28 dB and the structural similarity from 0.38 to 0.99, allowing a clear target image to be reconstructed. Meanwhile, supplementary experiments on the robustness and generalization of the method were conducted, and the results prove that it performs well on frosted glass plates with different scattering characteristics.

[1]  Yan Lou,et al.  Research on Key Technologies of Super-Resolution Reconstruction of Medium and Long Wave Maritime Infrared Image , 2022, Applied Sciences.

[2]  Detian Huang,et al.  Gradient-Guided and Multi-Scale Feature Network for Image Super-Resolution , 2022, Applied Sciences.

[3]  Siddhartha Rawat,et al.  cGAN-assisted imaging through stationary scattering media. , 2022, Optics express.

[4]  Xiaopeng Shao,et al.  Reconstructing Images of Two Adjacent Objects Passing through Scattering Medium via Deep Learning , 2021, Optics Express.

[5]  Jing Han,et al.  Efficient color imaging through unknown opaque scattering layers via physics-aware learning. , 2021, Optics express.

[6]  C. Li,et al.  Transmission Mueller matrix imaging with spatial filtering. , 2021, Optics letters.

[7]  Enmin Lu,et al.  Image super-resolution via channel attention and spatial attention , 2021, Applied Intelligence.

[8]  Ken Xingze Wang,et al.  Object recognition for remarkably small field-of-view with speckles , 2021 .

[9]  Ian Goodfellow,et al.  Generative adversarial networks , 2020, Commun. ACM.

[10]  Yujia Xue,et al.  Displacement-agnostic coherent imaging through scatter with an interpretable deep neural network. , 2020, Optics express.

[11]  Jiawei Luo,et al.  Retrieving the optical transmission matrix of a multimode fiber using the extended Kalman filter. , 2020, Optics express.

[12]  Arnaldo G. Leal-Junior,et al.  Optical Fiber Specklegram Sensors for Mechanical Measurements: A Review , 2020, IEEE Sensors Journal.

[13]  Guihua Zeng,et al.  Photon-limited imaging through scattering medium based on deep learning. , 2019, Optics express.

[14]  Chao Zuo,et al.  Learning-based method to reconstruct complex targets through scattering medium beyond the memory effect. , 2019, Optics express.

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

[16]  Xingzhao Liu,et al.  Imaging through scattering media using speckle pattern classification based support vector regression. , 2018, Optics express.

[17]  Guang-Can Guo,et al.  Deep hybrid scattering image learning , 2018, Journal of Physics D: Applied Physics.

[18]  George Barbastathis,et al.  Imaging through glass diffusers using densely connected convolutional networks , 2017, Optica.

[19]  M. Fink,et al.  Non-invasive single-shot imaging through scattering layers and around corners via speckle correlations , 2014, Nature Photonics.

[20]  Jacopo Bertolotti,et al.  Non-invasive imaging through opaque scattering layers , 2012, Nature.

[21]  G. Lerosey,et al.  Controlling waves in space and time for imaging and focusing in complex media , 2012, Nature Photonics.

[22]  V. Ntziachristos.  Going deeper than microscopy: the optical imaging frontier in biology , 2010, Nature Methods.

[23]  S. Popoff,et al.  Measuring the transmission matrix in optics: an approach to the study and control of light propagation in disordered media. , 2009, Physical review letters.

[24]  A. Mosk,et al.  Focusing coherent light through opaque strongly scattering media. , 2007, Optics letters.

[25]  J R Fienup,et al.  Phase retrieval algorithms: a comparison. , 1982, Applied optics.

[26]  Jun Liu,et al.  Single-shot optical speckle imaging based on pseudothermal illumination , 2019, Acta Physica Sinica.

[27]  R. Singh,et al.  Phase shifting digital holography with the Hanbury Brown–Twiss approach , 2019 .

[28]  Mohinder Malhotra.  Single Image Haze Removal Using Dark Channel Prior , 2016 .