(49-3) 17 * << * >> * Russian * English * Content * All Issues

Object classification using a single-pixel camera and neural networks
A.A. Reutov 1, D.V. Babukhin 1, D.V. Sych 1

1 P.N. Lebedev Physical Institute, RAS,
53 Leninskiy Prospekt, Moscow, 119991, Russia

 PDF, 13 MB

DOI: 10.18287/2412-6179-CO-1538

Pages: 517-524.

Full text of article: Russian language.

Abstract:
Single pixel imaging is a promising method of imaging without using multi-pixel matrices. Unlike traditional methods, the image here is not directly registered, but computed. Recently, machine learning techniques have started to be used to solve this problem. In this paper, we show the potential application of convolutional neural networks in single-pixel imaging to classify objects from a substantially incomplete set of measurements. We find the dependence of classification accuracy on various object sampling parameters. The proposed methods can be used in real devices as efficient software.

Keywords:
single-pixel imaging, object classification without image restoration, convolutional networks.

Citation:
Reutov AA, Babukhin DV, Sych DV. Object classification using a single-pixel camera and neural networks. Computer Optics 2025; 49(3): 517-524. DOI: 10.18287/2412-6179-CO-1538.

Acknowledgements:
This work was supported by Russian Science Foundation (Project No. 23-22-00381, https://rscf.ru/project/23-22-00381/).

References:
  1. Duarte MF, Davenport MA, Takhar D, Laska JN, Sun T, Kelly KF, Baraniuk RG. Single-pixel imaging via compressive sampling. IEEE Signal Process Mag 2008; 25(2): 83-91. DOI: 10.1109/MSP.2007.914730.
  2. Gibson GM, Johnson SD, Padget MJ. Single-pixel imaging 12 years on: a review. Opt Express 2020; 28(19): 28190-28208. DOI: 10.1364/OE.403195.
  3. Shcherbatenko M, Elezov M, Manova N, Sedykh K, Korneev A, Korneeva Yu, Dryazgov M, Simonov N, Feimov A, Goltsman G, Sych D. Single-pixel camera with a large-area microstrip superconducting single photon detector on a multimode fiber. Appl Phys Lett 2021; 118(18): 181103. DOI: 10.1063/5.0046049.
  4. Aguilar RA, Hermosa N, Soriano MN. Low-cost Fourier ghost imaging using a light-dependent resistor. Am J Phys 2019; 87(12): 976-981. DOI: 10.1119/10.0000163.
  5. Edgar MP, Gibson GM, Bowman RW, Sun B, Radwell N, Mitchell KJ, Welsh SS, Padgett MJ. Simultaneous real-time visible and infrared video with single-pixel detectors. Sci Rep 2015; 5(1): 10669. DOI: 10.1038/srep10669.
  6. Higham CF, Murray-Smith R, Padgett MJ, Edgar MP. Deep learning for real-time single-pixel video. Sci Rep 2018; 8(1): 2369. DOI: 10.1038/s41598-018-20521-y.
  7. Zhang Y, Edgar MP, Sun B, Radwell N, Gibson GM, Padgett MJ. 3D single-pixel video. J Opt 2016; 18(3): 035203. DOI: 10.1088/2040-8978/18/3/035203.
  8. Zhang Z, Li X, Zheng S, Yao M, Zheng G, Zhong J. Image-free classification of fast-moving objects using “learned” structured illumination and single-pixel detection. Opt Express 2020; 28(9): 13269-13278. DOI: 10.1364/OE.392370.
  9. Mur AL, Leclerc P, Peyrin F, Ducros N. Single-pixel image reconstruction from experimental data using neural networks. Opt Express 2021; 29(11): 17097-17110. DOI: 10.1364/OE.424228.
  10. Xie S, Peng L, Bian L. Large-scale single-pixel imaging via deep learning. Proc SPIE 2023; 12317: 1231703. DOI: 10.1117/12.2643014.
  11. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv Preprint. 2017. Source: <https://arxiv.org/abs/1412.6980>. DOI: 10.48550/arXiv.1412.6980.
  12. Sych DV. Optimization of compressed sampling in single-pixel imaging. Bull Lebedev Phys Inst 2024; 51: 202-205. DOI: 10.3103/S1068335624600463.
  13. Sych D. Influence of detector noise on compressed sampling single-pixel imaging. J Russ Laser Res 2024; 45(3): 286-294. DOI: 10.1007/s10946-024-10213-6.
  14. Baldominos A, Saez Y, Isasi P. A survey of handwritten character recognition with mnist and emnist. Appl Sci 2019; 9(15): 3169. DOI: 10.3390/app9153169.

© 2009, IPSI RAS
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