Time-efficient non-degenerate ghost imaging powered by deep learning

Quantum ghost imaging utilizes entangled photon pairs to enable an alternative image acquisition method. Information from either one of the photons does not allow for image reconstruction, however the image can be reconstructed by utilising the correlations that exist between the photon pair. Interestingly, these photon pairs can be either degenerate or non-degenerate in nature. Non-degenerate ghost imaging offers the ability to image with wavelength bandwidths where spatially resolving detectors are impractical, ineffective or expensive. Due to the scanning nature of spatially resolving detectors and the inherent low light levels of quantum experiments, imaging speeds are rather unsatisfactory. To overcome this limitation, we propose a two-step deep learning approach to establish an optimal early stopping point, tested on a non-degenerate system. In step one, we enhance the reconstructed image after each measurement by a deep convolution auto-encoder, followed by step two where a classifier is used to recognise the image. We achieved a recognition confidence of 75% at 20% of the image reconstruction time, hence reducing the image reconstruction time 5-fold while maintaining the image information. This, therefore, leads to a faster, more efficient image acquisition technique. Although tested on a non-degenerate system, our procedure can be extended to many such systems that are of quantum nature. We believe that this two-step deep learning approach will prove valuable to the community who are focusing their efforts on time-efficient ghost imaging.

[1]  Shengmei Zhao,et al.  Fast reconstructed and high-quality ghost imaging with fast Walsh–Hadamard transform , 2016 .

[2]  Andrew Forbes,et al.  Towards time-efficient ghost imaging , 2020 .

[3]  Miles J. Padgett,et al.  Principles and prospects for single-pixel imaging , 2018, Nature Photonics.

[4]  Xianmin Zhang,et al.  Deep-learning denoising computational ghost imaging , 2020 .

[5]  Hong-Chao Liu,et al.  Imaging reconstruction comparison of different ghost imaging algorithms , 2020, Scientific Reports.

[6]  Alberto Tosi,et al.  Photon-sparse microscopy: Visible light imaging using infrared illumination , 2015 .

[7]  Jeffrey H. Shapiro,et al.  Computational ghost imaging , 2008, 2009 Conference on Lasers and Electro-Optics and 2009 Conference on Quantum electronics and Laser Science Conference.

[8]  O. Katz,et al.  Compressive ghost imaging , 2009, 0905.0321.

[9]  Qionghai Dai,et al.  High Speed Computational Ghost Imaging via Spatial Sweeping , 2017, Scientific Reports.

[10]  Guangshun Li,et al.  Compressed-Sensing-based Gradient Reconstruction for Ghost Imaging , 2019, International Journal of Theoretical Physics.

[11]  Liang Jiang,et al.  Denoising ghost imaging under a small sampling rate via deep learning for tracking and imaging moving objects. , 2020, Optics express.

[12]  Y. Shih.  Quantum Imaging , 2007, IEEE Journal of Selected Topics in Quantum Electronics.

[13]  Qun Hao,et al.  Improving Imaging Quality of Real-time Fourier Single-pixel Imaging via Deep Learning , 2019, Sensors.

[14]  Yanhua Shih,et al.  Resolution of ghost imaging for nondegenerate spontaneous parametric down-conversion , 2008 .

[15]  R. Boyd,et al.  An introduction to ghost imaging: quantum and classical , 2017, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[16]  Roderick Murray-Smith,et al.  Deep learning for real-time single-pixel video , 2018, Scientific Reports.

[17]  Aristide Dogariu,et al.  Correlated imaging with shaped spatially partially coherent light. , 2006, Optics letters.

[18]  Zibang Zhang,et al.  Comprehensive comparison of single-pixel imaging methods , 2020 .

[19]  Guohai Situ,et al.  Deep-learning-based ghost imaging , 2017, Scientific Reports.

[20]  Shih,et al.  Optical imaging by means of two-photon quantum entanglement. , 1995, Physical review. A, Atomic, molecular, and optical physics.

[21]  Qun Hao,et al.  DeepGhost: real-time computational ghost imaging via deep learning , 2020, Scientific Reports.

[22]  Takayuki Takahashi,et al.  Computational ghost imaging using deep learning , 2017, ArXiv.

[23]  Ronald E. Meyers,et al.  Quantum ghost imaging experiments , 2006, SPIE Optics + Photonics.

[24]  A. Gatti,et al.  Ghost imaging with thermal light: comparing entanglement and classical correlation. , 2003, Physical review letters.

[25]  Robert W. Boyd,et al.  Two-color ghost imaging , 2008 .

[26]  R. Weissleder.  A clearer vision for in vivo imaging , 2001, Nature Biotechnology.

[27]  Zibang Zhang,et al.  Three-dimensional single-pixel imaging with far fewer measurements than effective image pixels. , 2016, Optics letters.

[28]  Jeffrey H. Shapiro,et al.  The physics of ghost imaging , 2012, Quantum Information Processing.

[29]  Zhishen Tong,et al.  Spectral Camera based on Ghost Imaging via Sparsity Constraints , 2015, Scientific Reports.

[30]  Robert W. Boyd,et al.  Entangled-photon compressive ghost imaging , 2011 .

[31]  R. Boyd,et al.  "Two-Photon" coincidence imaging with a classical source. , 2002, Physical review letters.

[32]  John C Howell,et al.  Realization of the Einstein-Podolsky-Rosen paradox using momentum- and position-entangled photons from spontaneous parametric down conversion. , 2004, Physical review letters.

[33]  Robert W Boyd,et al.  Resolution limits of quantum ghost imaging. , 2018, Optics express.