Monolayer directional metasurface for all-optical image classifier doublet

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 challenges. To address these issues, this study introduces a monolayer directional metasurface, aimed at reducing spatial constraints and mitigating alignment issues. and eliminate the effects of alignment. Utilizing this methodology, we reveal that the metasurface trained by the diffractive deep neural network can achieve excellent digital classification results, and the classification accuracy of ideal phase mask plates and metasurface 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 alignment, thereby improving spatial utilization efficiency.