Efficient Computer-Generated Holography Based on Mixed Linear Convolutional Neural Networks
Source abstract
Abstract
Imaging based on computer-generated holography using traditional methods has the problems of poor quality and long calculation cycles. However, recently, the development of deep learning has provided new ideas for this problem. Here, an efficient computer-generated holography (ECGH) method is proposed for computational holographic imaging. This method can be used for computational holographic imaging based on mixed linear convolutional neural networks (MLCNN). By introducing fully connected layers in the network, the suggested design is more powerful and efficient at information mining and information exchange. Using the ECGH, the pure phase image required can be obtained after calculating the custom light field. Compared with traditional computed holography based on deep learning, the method used here can reduce the number of network parameters needed for network training by about two-thirds while obtaining a high-quality image in the reconstruction, and the network structure has the potential to solve various image-reconstruction problems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Digital Holography and Microscopy · Advanced Optical Imaging Technologies · Advanced Vision and Imaging
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Science, China University of Petroleum (East China), Qingdao 266580, China
Funding
Natural Science Foundation of Shandong Province, China · Fundamental Research Funds for the Central Universities of China
References (35)
Show source-provided references
1. Digital image formation from electronically detected holograms10.1063/1.1755043 ↗
2. Poon, T.C., and Liu, J.P. (2014). Introduction to Modern Digital Holography with MATLAB, Cambridge University Press.10.1017/CBO9781139061346 ↗
3. Xu, X., Ma, T., Jiao, Z., Xu, L., Dai, D., Qiao, F., and Poon, T.-C. (2019). Novel Generalized Three-Step Phase-Shifting Interferometry with a Slight-Tilt Reference. Appl. Sci., 9.10.3390/app9235015 ↗
4. Holographic optical trapping10.1364/AO.45.000880 ↗
5. Trapping performance of holographic optical tweezers generated with different hologram algorithms10.1063/5.0033186 ↗
6. Holographic imaging and photostimulation of neural activity10.1016/j.conb.2018.03.006 ↗
7. Three-dimensional holographic photostimulation of the dendritic arbor10.1088/1741-2560/8/4/046002 ↗
8. Accurate compressed look up table method for CGH in 3D holographic display10.1364/OE.23.033194 ↗
9. Computer-generated holograms of 3-D objects composed of tilted planar segments10.1364/AO.27.003020 ↗
10. Recent progress in computer-generated holography for three-dimensional scenes10.1080/15980316.2016.1255672 ↗
11. Projection-type see-through holographic three-dimensional display10.1038/ncomms12954 ↗
12. Speeding up reconstruction of 3D tomograms in holographic flow cytometry via deep learning10.1039/D1LC01087E ↗
13. Effective bandwidth approach for the spectral splitting of solar spectrum using diffractive optical elements10.1364/OE.381822 ↗
14. Wavefront shaping assisted design of spectral splitters and solar concentrators10.1038/s41598-021-82110-w ↗
15. Augmented reality near-eye display using Pancharatnam-Berry phase lenses10.1038/s41598-019-42979-0 ↗
16. Foveated near-eye display using computational holography10.1038/s41598-020-71986-9 ↗
17. Phase determination for image and diffraction plane pictures in the electron microscope
18. Speckle-suppressed phase-only holographic three-dimensional display based on double-constraint Gerchberg-Saxton algorithm10.1364/AO.54.006994 ↗
19. Binary Fraunhofer Holograms, Generated by Computer10.1364/AO.6.001739 ↗
20. All-optical machine learning using diffractive deep neural networks10.1126/science.aat8084 ↗
21. Deep neural network for multi-depth hologram generation and its training strategy10.1364/OE.402317 ↗
22. Deep-learning-generated holography10.1364/AO.57.003859 ↗
23. Towards real-time photorealistic 3D holography with deep neural networks10.1038/s41586-020-03152-0 ↗
24. Neural holography with camera-in-the-loop training10.1145/3414685.3417802 ↗
25. Balasubramaniam, G.M., Wiesel, B., Biton, N., Kumar, R., Kupferman, J., and Arnon, S. (2022). Tutorial on the Use of Deep Learning in Diffuse Optical Tomography. Electronics, 11.10.3390/electronics11030305 ↗
26. Integrated deep learning framework for accelerated optical coherence tomography angiography10.1038/s41598-022-05281-0 ↗
27. Open-source deep learning-based automatic segmentation of mouse Schlemm’s canal in optical coherence tomography images10.1016/j.exer.2021.108844 ↗
28. Navab, N., Hornegger, J., Wells, W.M., and Frangi, A.F. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention 2015, Springer International Publishing.10.1007/978-3-319-24571-3 ↗
29. Medical image segmentation based on u-net: A review10.2352/J.ImagingSci.Technol.2020.64.2.020508 ↗
30. Reconstruction Bias U-Net for Road Extraction From Optical Remote Sensing Images10.1109/JSTARS.2021.3053603 ↗
31. Optical Coherence Tomography Vulnerable Plaque Segmentation Based on Deep Residual U-Net10.31083/j.rcm.2019.03.5201 ↗
32. Chen, T., Lu, T., Song, S., Miao, S., Gao, F., and Li, J. (2020, January 2–5). A deep learning method based on U-Net for quantitative photoacoustic imaging. Proceedings of the Photons Plus Ultrasound: Imaging and Sensing 2020, San Francisco, CA, USA.10.1117/12.2543173 ↗
33. Cryptanalysis of compressive interference-based optical encryption using a U-net deep learning network10.1016/j.optcom.2021.127641 ↗
34. Lin, M., Chen, Q., and Yan, S. (2013). Network in network. arXiv.
35. Image Quality Assessment: From Error Visibility to Structural Similarity10.1109/TIP.2003.819861 ↗