(50-1) 07 * << * >> * Russian * English * Content * All Issues

Design of DOE robust to positioning errors for optical classification purposes
D.V. Soshnikov1,2, L.L. Doskolovich1,2, G.A. Motz1,2, N.V. Golovastikov1,2, E.A. Bezus1,2, D.A. Bykov1,2

1Image Processing Systems Institute, NRC "Kurchatov Institute", 443001, Samara, Russia, Molodogvardeyskaya 151;
2Samara National Research University, 443086, Samara, Russia, Moskovskoye Shosse 34

  Full text (PDF)

DOI: 10.18287/COJ1693

Article ID: 1693

Language: English

Abstract:
A method for designing diffractive optical elements (DOEs) robust to positioning errors is proposed for classification problems. Within this method, classification error is represented by a functional that depends on the phase function of the DOE and a random vector describing positioning errors as a transverse shift of the DOE with respect to the optical axis. The mathematical expectation of this functional is used as a loss functional in the gradient-based design of the DOE, with explicit expressions obtained for the derivatives of the loss functional. Using this method, a DOE is designed for classification of handwritten digit images. According to the computational modelling results, the designed DOE demonstrates good performance (classification accuracy exceeding 96 % and a "contrast" value exceeding 13 %, where the contrast is used to characterize the ratio of the energy in a predicted class region to the energies in other class regions) for two-pixel misalignments along both coordinate axes, corresponding to a shift of the DOE center up to 17 wavelengths.

Keywords:
diffractive optical element, phase function, image classification, scalar diffraction theory, optimization, gradient method.

Acknowledgements:
This work was supported by the Ministry of Science and Higher Education of the Russian Federation (state assignment to Samara University FSSS-2024-14) in the part of DOE design with account for positioning errors and by the Russian Science Foundation (project No. 24-19-00080) in the part of obtaining the derivatives of the loss functionals.

Citation:
Soshnikov DV, Doskolovich LL, Motz GA, Golovastikov NV, Bezus EA, Bykov DA. Design of DOE robust to positioning errors for optical classification purposes. Computer Optics 2026; 50(1): 1693. DOI: 10.18287/COJ1693.

References:

  1. Shen Y, Harris N, Skirlo S, et al. Deep learning with coherent nanophotonic circuits. Nat Photon 2017; 11: 441-446. DOI: 10.1038/nphoton.2017.93.
  2. Harris NC, Carolan J, Bunandar D, et al. Linear programmable nanophotonic processors. Optica 2018; 5: 1623-1631. DOI: 10.1364/OPTICA.5.001623.
  3. Zhu HH, Zou J, Zhang H, et al. Space-efficient optical computing with an integrated chip diffractive neural network. Nat Commun 2022; 13: 1044. DOI: 10.1038/s41467-022-28702-0.
  4. Zhang H, Gu M, Jiang XD, et al. An optical neural chip for implementing complex-valued neural network. Nat Commun 2021; 12: 457. DOI: 10.1038/s41467-020-20719-7.
  5. Zhang J, Wu B, Cheng J, et al. Compact, efficient, and scalable nanobeam core for photonic matrix-vector multiplication. Optica 2024; 11: 190-196. DOI: 10.1364/OPTICA.506603.
  6. Lin X, Rivenson Y, Yardimci NT, et al. All-optical machine learning using diffractive deep neural networks. Science 2018; 361: 1004-1008. DOI: 10.1126/science.aat8084.
  7. Chang J, Sitzmann V, Dun X, et al. Hybrid optical-electronic convolutional neural networks with optimized diffractive optics for image classification. Sci Rep 2018; 8: 12324. DOI: 10.1038/s41598-018-30619-y.
  8. Yan T, Wu J, Zhou T, et al. Fourier-space Diffractive Deep Neural Network. Phys Rev Lett 2019; 123: 023901. DOI: 10.1103/PhysRevLett.123.023901.
  9. Luo Y, Mengu D, Yardimci NT, et al. Design of task-specific optical systems using broadband diffractive neural networks. Light Sci Appl 2019; 8: 112. DOI: 10.1038/s41377-019-0223-1.
  10. Zhou T, Fang L, Yan T, et al. In situ optical backpropagation training of diffractive optical neural networks. Photon Res 2020; 8: 940-953. DOI: 10.1364/PRJ.389553.
  11. Mengu D, Zhao Y, Yardimci NT, et al. Misalignment resilient diffractive optical networks. Nanophotonics 2020; 9(13): 4207-4219. DOI: 10.1515/nanoph-2020-0291.
  12. Zhou T, Lin X, Wu J, et al. Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit. Nat Photonics 2021; 15: 367-373. DOI: 10.1038/s41566-021-00796-w.
  13. Chen H, Feng J, Jiang M, et al. Diffractive Deep Neural Networks at Visible Wavelengths. Engineering 2021; 7(10): 1483-1491. DOI: 10.1016/j.eng.2020.07.032.
  14. Ferdman B, Saguy A, Xiao D, Shechtman Y. Diffractive optical system design by cascaded propagation. Opt Express 2022; 30: 27509-27530. DOI: 10.1364/OE.465230.
  15. Zheng S, Xu S, Fan D. Orthogonality of diffractive deep neural network. Opt Lett 2022; 47: 1798-1801. DOI: 10.1364/OL.449899.
  16. Zheng MJ, Shi L, Zi J. Optimize performance of a diffractive neural network by controlling the Fresnel number. Photon Res 2022; 10: 2667-2676. DOI: 10.1364/PRJ.474535.
  17. Wang T, Ma SY, Wright LG, et al. An optical neural network using less than 1 photon per multiplication. Nat Commun 2022; 13: 123. DOI: 10.1038/s41467-021-27774-8.
  18. Soshnikov DV, Doskolovich LL, Motz GA, et al. Design of Cascaded Diffractive Optical Elements for Optical Beam Shaping and Image Classification Using a Gradient Method. Photonics 2023; 10: 766. DOI: 10.3390/photonics10070766.
  19. Soshnikov DV, Doskolovich LL, Byzov EV. Gradient method for designing cascaded DOEs and its application in the problem of classifying handwritten digits. Computer Optics 2023; 47(5): 691-701. DOI: 10.18287/2412-6179-CO-1314.
  20. Kulce O, Mengu D, Rivenson Y, Ozcan A. All-optical synthesis of an arbitrary linear transformation using diffractive surfaces. Light Sci Appl 2021; 10: 196. DOI: 10.1038/s41377-021-00623-5.
  21. Li J, Gan T, Bai B, et al. Massively parallel universal linear transformations using a wavelength-multiplexed diffractive optical network. Adv Photonics 2023; 5(1): 016003. DOI: 10.1117/1.AP.5.1.016003.
  22. Mengu D, Tabassum A, Jarrahi M, et al. Snapshot multispectral imaging using a diffractive optical network. Light Sci Appl 2023; 12: 86. DOI: 10.1038/s41377-023-01135-0.
  23. Lohmann AW, Paris DP. Binary Fraunhofer Holograms, Generated by Computer. Appl Opt 1967; 6: 1739-1748. DOI: 10.1364/AO.6.001739.
  24. Fienup JR. Phase retrieval algorithms: a comparison. Appl Opt 1982; 21: 2758-2769. DOI: 10.1364/AO.21.002758.
  25. Soifer VA, Kotlyar VV, Doskolovich LL. Iterative methods for diffractive optical elements computation. London: Taylor & Francis; 1997. DOI: 10.1201/9781482272918.
  26. Ripoll O, Kettunen V, Herzig HP. Review of iterative Fourier transform algorithms for beam shaping applications. Opt Eng 2004; 43: 2549-2556. DOI: 10.1117/1.1804543.
  27. Latychevskaia T. Iterative phase retrieval in coherent diffractive imaging: practical issues. Appl Opt 2018; 57: 7187-7197. DOI: 10.1364/AO.57.007187.
  28. Deng X, Chen RT. Design of cascaded diffractive phase elements for three-dimensional multiwavelength optical interconnects. Opt Lett 2000; 25: 1046-1048. DOI: 10.1364/OL.25.001046.
  29. Alkan Gülses A, Jenkins BK. Cascaded diffractive optical elements for improved multiplane image reconstruction. Appl Opt 2013; 52: 3608-3616. DOI: 10.1364/AO.52.003608.
  30. Wang H, Piestun R. Dynamic 2D implementation of 3D diffractive optics. Optica 2018; 5: 1220-1228. DOI: 10.1364/OPTICA.5.001220.
  31. Doskolovich LL, Mingazov AA, Byzov EV, et al. Hybrid design of diffractive optical elements for optical beam shaping. Opt Express 2021; 29: 31875-31890. DOI: 10.1364/OE.439641.
  32. Kingma DP, Ba J. Adam: A method for stochastic optimization. Preprint arXiv:1412.6980, 2015.
  33. Robert CP, Casella G. Monte Carlo Statistical Methods. 2nd ed. Berlin: Springer; 2004.
  34. Schmidt JD. Numerical Simulation of Optical Wave Propagation with Examples in MATLAB. Bellingham: SPIE; 2010.
  35. Cubillos M, Jimenez E. Numerical simulation of optical propagation using sinc approximation. J Opt Soc Am A 2022; 39: 1403-1413. DOI: 10.1364/JOSAA.461355.

151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20