版权所有:内蒙古大学图书馆 技术提供:维普资讯• 智图
内蒙古自治区呼和浩特市赛罕区大学西街235号 邮编: 010021
出 版 物:《Optoelectronics Letters》 (光电子快报(英文))
年 卷 期:2025年
学科分类:080901[工学-物理电子学] 0809[工学-电子科学与技术(可授工学、理学学位)] 08[工学] 080401[工学-精密仪器及机械] 080203[工学-机械设计及理论] 0804[工学-仪器科学与技术] 0802[工学-机械工程] 0803[工学-光学工程]
基 金:Opening Foundation of Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems (2019LODTS004) Tianjin Key Laboratory of Micro-scale Optical Information Science and Technology
摘 要:Multimode fibers (MMFs) have great potential for endoscopic imaging due to the high number of modes and a small core diameter. Deep learning based on neural networks has received increasing attention in the field of scattering image reconstruction. However, most studies focus on designing complex network architectures to improve reconstruction, but these network models struggle to reconstruct images in a weak laser field. In the paper, a lightweight generative adversarial network model combined with a histogram specification algorithm is designed to reconstruct speckles in the weak laser field through MMF. Experimental results show that the reconstruction results of our algorithm have better metrics. Moreover, the model demonstrates excellent cross-domain generalization ability with regards to the Fashion-MNIST dataset. It is worth mentioning that we found that the speckles after inactivation still retain the ability to be reconstructed, which enhances the robustness of the model