Opt Lett. 2023 Apr 1;48(7):1902-1905. doi: 10.1364/OL.483415.
Image edge processing has widespread adoption in a variety of scientific and industrial scenarios. To date, implementations of image edge processing have mostly been done electronically, but there are still difficulties to achieve real-time, high-throughput, and low power consumption image edge processing. The advantages of optical analog computing include low power consumption, fast transmission speed, and high parallel processing capability, and optical analog differentiators make this process possible. However, the proposed analog differentiators can hardly meet the requirements of broadband, polarization insensitive, high contrast, and high efficiency at the same time. Moreover, they are limited to one-dimensional differentiation or work in reflection mode. To be better compatible with two-dimensional image processing or image recognition systems, two-dimensional optical differentiators that integrate the above advantages are urgently needed. In this Letter, a two-dimensional analog optical differentiator with edge detection operating in transmission mode is proposed. It can cover the visible band, is polarization uncorrelated, and has a resolution that reaches 1.7 μm. The efficiency of the metasurface is higher than 88%.
图像边缘处理在各种科学和工业场景中得到了广泛的应用。迄今为止,图像边缘处理的实现主要是通过电子方式完成的,但仍然存在实时、高吞吐量和低功耗图像边缘处理的困难。光学模拟计算的优势包括低功耗、高速传输速度和高并行处理能力,而光学模拟微分器使得这一过程成为可能。然而,所提出的模拟微分器很难同时满足宽带、偏振不敏感、高对比度和高效率的要求。此外,它们仅限于一维微分或在反射模式下工作。为了更好地与二维图像处理或图像识别系统兼容,迫切需要集成上述优点的二维光学微分器。在这封信中,提出了一种工作在传输模式下具有边缘检测功能的二维模拟光学微分器。它可以覆盖可见光波段,与偏振无关,分辨率达到 1.7μm。该超表面的效率高于 88%。