Abstract
Diffractive deep neural networks, known for their passivity, high scalability, and high efficiency, offer great potential in holographic imaging, target recognition, and object classification. However, previous endeavors have been hampered by spatial size and alignment. To address these issues, this study introduces a monolayer directional metasurface, aimed at reducing spatial constraints and mitigating alignment issues. Utilizing this methodology, we use MNIST datasets to train diffractive deep neural networks and realize digital classification, revealing that the metasurface can achieve excellent digital image classification results, and the classification accuracy of ideal phase mask plates and metasurface for phase-only modulation can reach 84.73% and 84.85%, respectively. Despite a certain loss of degrees of freedom compared to multi-layer phase mask plates, the single-layer metasurface is easier to fabricate and align, thereby improving spatial utilization efficiency.
© 2024 Optica Publishing Group
Full Article | PDF ArticleCorrections
16 May 2024: A typographical correction was made to the author affiliations.
More Like This
Jasna V. Crnjanski, Isidora Teofilović, Marko M. Krstić, and Dejan M. Gvozdić
Opt. Lett. 49(5) 1153-1156 (2024)
Naike Wei, Yingying Sun, Tingting Jiang, and Qiong Gao
Opt. Lett. 49(8) 1941-1944 (2024)
Yuxin Ma, Kaifei Tang, Jun Lu, Zhenxing Sun, Lu Yao, Yujiang Wang, Zhenzhen Xu, Mi Li, Xin Wang, Rulei Xiao, Yu Xin, Jiahui Liu, Xiang Ji, Wei Jiang, Yuechun Shi, and Xiangfei Chen
Opt. Lett. 49(10) 2629-2632 (2024)