Imaging reconstruction through strongly scattering media by using convolutional neural networks

Li, Qiongyao; Zhao, Jun; Zhang, Yanzhu; Lai, Xuetian; Chen, Ziyang; Pu, Jixiong

doi:10.1016/j.optcom.2020.126341

Cited by 22 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A difficulty arises in imaging an object placed between two diffusers, in that the object is illuminated with a diffused wave. 14 , 27 – 29 We investigated image reconstruction of an object placed between two diffusers, as shown in Fig. 1 .…”

Section: Resultsmentioning

confidence: 99%

“…CNNs have been used to retrieve amplitude objects behind a random medium using either a single 13 or multiple diffusers. 14 Deep-learning-based methods also enable imaging under low-photon conditions 15 and reconstruction of objects through dynamic scattering media. 16 However, these methods face several challenges, such as the selection of the training framework, scalability, and optical systems.…”

Section: Introductionmentioning

confidence: 99%

“…The scope of this work is limited to optical systems for imaging through light-scattering obscurants using deep learning. Optical systems can be classified into those encoding objects as transmission mode 8 , 14 , 15 , 17 – 19 and reflection mode. 9 – 11 , 13 , 16 , 20 – 24 In both modes, optical systems, such as lensless imaging systems, 8 , 10 , 17 , 20 , 21 , 23 imaging systems with one or two lenses, 9 , 11 , 14 – 16 , 18 , 19 , 22 and imaging systems with a camera lens 13 , 24 have been investigated.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigation of image plane for image reconstruction of objects through diffusers via deep learning

Tsukada

Watanabe

2022

J. Biomed. Opt.

View full text Add to dashboard Cite

. Significance: The imaging of objects hidden in light-scattering media is a vital practical task in a wide range of applications, including biological imaging. Deep-learning-based methods have been used to reconstruct images behind scattering media under complex scattering conditions, but improvements in the quality of the reconstructed images are required. Aim: To investigate the effect of image plane on the accuracy of reconstructed images. Approach: Light reflected from an object passing through glass diffusers is captured by changing the image plane of an optical imaging system. Images are reconstructed by deep learning, and evaluated in terms of structural similarity index measure, classification accuracy of digital images, and training and testing error curves. Results: The reconstruction accuracy was improved for the case in which the diffuser was imaged, compared to the case where the object was imaged. The training and testing error curves show that the loss converged to lower values in fewer epochs when the diffuser was imaged. Conclusions: The proposed approach demonstrates an improvement in the accuracy of the reconstruction of objects hidden through glass diffusers by imaging glass diffuser surfaces, and can be applied to objects at unknown locations in a scattering medium.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigation of image plane for image reconstruction of objects through diffusers via deep learning

Tsukada

Watanabe

2022

J. Biomed. Opt.

View full text Add to dashboard Cite

show abstract

“…The experimental requirements of speckle-related methods are relatively simple, but the imaging field of view is limited by the memory effect range, which is inversely proportional to the medium thickness. With the development of deep learning [14], an increasing number of researchers are using neural networks to address these issues concerning the scattering media problem [15][16][17]. Indeed, deep learning has shown great potential in solving the problems caused by scattering, but it is limited by the training data.…”

Section: Introductionmentioning

confidence: 99%

Improving Compressed Sensing Image Reconstruction Based on Atmospheric Modulation Using the Distributed Cumulative Synthesis Method

Lei

Yang

et al. 2021

IEEE Photonics J.

View full text Add to dashboard Cite

The problem of long-distance imaging through timevarying scattering media, such as the atmosphere, is encountered in many science fields. Recent studies have demonstrated that random atmospheric variability can be considered a spatial light modulator in compressed sensing imaging. However, the quality of the reconstructed image needs to be further improved. In this paper, we propose a distributed cumulative synthesis method to improve the compressed sensing image reconstruction based on atmospheric modulation. For multiple original images of various types, the compressed sensing imaging simulation experiment with different sampling rates was conducted using the distributed cumulative synthesis method. The simulation results show that, compared with the imaging method using a single light source, the distributed cumulative synthesis method can effectively improve the quality of the reconstructed image, whether it is full sampling or undersampling. In addition, a sparsity impact factor is defined to quantify the reconstruction ability of the measurement matrix obtained by the distributed cumulative synthesis method. This value can be used as an evaluation index for the optimized design of the measurement matrix by the distributed cumulative synthesis method. Noise analysis shows that the proposed method has better anti-noise performance than the single light source imaging method.

show abstract

“…These curves show that MDN achieves faster loss decrease and lower loss value than dense-net. We also replace all the dense blocks by standard convolutional layers to make it a typical U-net, which has parameters over 30-million[24]. Compared to the typical U-net, the number of parameters of our network is reduced by nearly 63%, which improves the training efficiency.…”

mentioning

confidence: 99%

Mutual Transfer Learning of Reconstructing Images Through a Multimode Fiber or a Scattering Medium

Lai

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

In recent years, convolutional neural network (CNN) has been successfully applied to reconstruct image from the speckle, which is generated as an object passes through a scattering medium or a multimode fiber (MMF). To reconstruct image from the speckle, the CNN must be trained with a large number of object-speckle pairs (training dataset), and the trained CNN is capable of reconstructing image from dataset (test dataset), which is taken in the same condition as the training dataset. However, in some cases, data type and the scattering medium may vary with the situation. In this case, the CNN has to be retrained using a large number of new data taken from the new scattering media for reconstructing image. In this paper, we develop a CNN called as Mobiledense-net (MDN) to realize the mutual transfer learning. Specifically, the MDN is first pre-trained with a large number of object-speckle pairs taken from MMF or scattering slab, then tuned with quite small number of object-speckle pairs from scattering slab or MMF. It is shown that in this case the MDN can reconstruct image from the speckle with quite good quality, in which the speckle is taken from MMF or the scattering slab. We also show that using a more complex dataset for pre-training, the amount of data for pre-training can be largely reduced and reconstruction quality can be further improved. Using transfer learning, the reconstruction quality is quite good, being up to 99% . The results in this paper provide a more generalized method for studying the imaging through scattering imaging or MMF by using CNN.INDEX TERMS Imaging, convolutional neural network (CNN), Mobiledense-net (MDN), transfer learning, scattering medium, multimode fiber (MMF).

show abstract

Imaging reconstruction through strongly scattering media by using convolutional neural networks

Cited by 22 publications

References 31 publications

Investigation of image plane for image reconstruction of objects through diffusers via deep learning

Investigation of image plane for image reconstruction of objects through diffusers via deep learning

Improving Compressed Sensing Image Reconstruction Based on Atmospheric Modulation Using the Distributed Cumulative Synthesis Method

Mutual Transfer Learning of Reconstructing Images Through a Multimode Fiber or a Scattering Medium

Contact Info

Product

Resources

About