Image Reconstruction of Multimode Fiber Scattering Media Based on Deep Learning

被引：11
作者：
Meng Lu [1 ]
Hu Haifeng [1 ,2 ]
Hu Jinzhou [1 ]
Bu Sihang [1 ]
Gao Han [1 ]
机构：
[1] Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110004, Liaoning, Peoples R China
[2] Univ Shanghai Sci & Technol, Sch Opt Elect & Comp Engn, Shanghai 200093, Peoples R China
来源：
CHINESE JOURNAL OF LASERS-ZHONGGUO JIGUANG | 2020年 / 47卷 / 12期
关键词：
fiber optics; image processing; multimode fiber; deep learning; dense connection; image reconstruction; DenseUnet; LIGHT;
D O I：
10.3788/CJL202017.1206005
中图分类号：
O43 [光学];
学科分类号：
070207 ; 0803 ;
摘要：
Multimode fiber is a thick scattering medium. When the target image is projected onto the multimode optical fiber, multimode coupling will occur, thereby generating speckle images at the output of the fiber. In this work, multimode optical fiber imaging is restored based on deep learning, and the distortion of thick scattering media imaging is solved. DenseUnet is used and the speckle image is used as the input of the model for reconstructing the target image. The DenseUnet model employs a fusion mechanism to deepen the network depth, thus, improving the reconstruction accuracy and realizing good robustness. The experimental results reveal that DenseUnet can be used to reconstruct speckle images produced by multimode optical fibers with different lengths.
引用
收藏
页数：10
相关论文
共 21 条
[1]   Learning to see through multimode fibers [J].
Borhani, Navid ;
Kakkava, Eirini ;
Moser, Christophe ;
Psaltis, Demetri .
OPTICA, 2018, 5 (08) :960-966
[2]  
Fan P F, 2018, DEEP LEARNING HIGH V
[3]   Densely Connected Convolutional Networks [J].
Huang, Gao ;
Liu, Zhuang ;
van der Maaten, Laurens ;
Weinberger, Kilian Q. .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :2261-2269
[4]  
HUANG Hui-ling, 2015, CHINESE J LASERS, V42
[5]  
LeCun Y., 2001, IEEE INT SIGN PROC, P306
[6]  
Li C., 2019, INFRAR LASER ENG, V48
[7]   Imaging through glass diffusers using densely connected convolutional networks [J].
Li, Shuai ;
Deng, Mo ;
Lee, Justin ;
Sinha, Ayan ;
Barbastathis, George .
OPTICA, 2018, 5 (07) :803-813
[8]  
Li YZ, 2018, DEEP SPECKLE CORRELA
[9]  
Lin M, 2020, NETWORK IN NETWORK
[10]   Low illumination underwater light field images reconstruction using deep convolutional neural networks [J].
Lu, Huimin ;
Li, Yujie ;
Uemura, Tomoki ;
Kim, Hyoungseop ;
Serikawa, Seiichi .
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2018, 82 :142-148
123