Generative-Adversarial-Networks-based Ghost Recognition

TL;DR

This paper introduces a novel imaging-free target recognition method that combines ghost imaging and generative adversarial networks, reducing reliance on high-quality images and improving turbulence resistance.

Contribution

It proposes a new approach integrating ghost imaging with GANs for target recognition, bypassing traditional image reconstruction limitations.

Findings

Achieves promising recognition performance in experiments.

Provides turbulence-free recognition capability.

Reduces dependence on high-quality target images.

Abstract

Nowadays, target recognition technique plays an important role in many fields. However, the current target image information based methods suffer from the influence of image quality and the time cost of image reconstruction. In this paper, we propose a novel imaging-free target recognition method combining ghost imaging (GI) and generative adversarial networks (GAN). Based on the mechanism of GI, a set of random speckles sequence is employed to illuminate target, and a bucket detector without resolution is utilized to receive echo signal. The bucket signal sequence formed after continuous detections is constructed into a bucket signal array, which is regarded as the sample of GAN. Then, conditional GAN is used to map bucket signal array and target category. In practical application, the speckles sequence in training step is employed to illuminate target, and the bucket signal array is input GAN for recognition. The proposed method can improve the problems caused by conventional recognition methods that based on target image information, and provide a certain turbulence-free ability. Extensive experiments show that the proposed method achieves promising performance.