Terahertz Image Super-Resolution Reconstruction of Passive Safety Inspection Based on Generative Adversarial Network

When passive terahertz imaging technology is used in Safety inspection, it has low image resolution and is susceptible to environment. As a result, it is difficult to support the demand for high-resolution terahertz images in related projects. This paper proposes a passive terahertz image reconstruction method based on improved Generative Adversarial Networks, and compares it with other existing methods. Experimental results show that the improved SRGAN method has higher peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).