Diffractive Neural Networks with Improved Expressive Power for Grayscale Image Classification

• Minjia Zheng, wenzhe liu, Lei Shi, and Jian Zi
• received 11/29/2023; accepted 02/29/2024; posted 03/20/2024; Doc. ID 513845
• Abstract: In order to harness diffractive neural networks (DNNs) for tasks that better align with real-world computer vision requirements, the incorporation of grayscale is essential. Currently, DNNs is not powerful to accomplish grayscale image processing tasks due to limitations in their expressive power. In our work, we elucidate the relationship between the improvement in the expressive power of DNNs and the increase in the number of phase modulation layers, as well as the optimization of the Fresnel number, which can describe the diffraction process. To demonstrate this point, we numerically trained a double-layer DNN, addressing the prerequisites for intensity-based grayscale image processing. Furthermore, we experimentally constructed this double-layer DNN based on digital micromirror devices and spatial light modulators, achieving 8-level intensity-based grayscale image classification for the MNIST and Fashion-MNIST datasets for the first time. This optical system achieved the maximum accuracies of 95.10% and 80.61%, respectively.