Abstract
Reconstructing target objects from strong speckle images is a key step for solving complex inverse scattering imaging problems. Deep learning (DL) methods are very effective for producing high quality object reconstruction, especially for speckle image reconstruction (SIR). Understanding the relationship between DL network structures and reconstruction results helps improve the reconstruction quality. Although previous studies have explored this issue, few of them considered dilated convolution adjustment and effective receptive field optimization of DL networks in image reconstruction for improving the reconstruction quality. In this paper, we propose a two stage enhancement network for speckle image reconstruction, in addition, we present an effective receptive field optimization method for maximizing the usage of the network capability. Specifically, in the first stage, we propose a growth model exploiting the dilation rates under the assumption that the central area pixels of images have a much bigger impact on the output field than the outer area pixels, and accordingly optimize the effective receptive field of the networks. Then, based on our growth model, in the second stage, the enhancement network jointly utilizes complementary information from the objective loss and perceptual loss when reconstructing objects. Extensive experiments show that our new network outperforms five state-of-the-art methods in the MAE, MSE, PSNR, and SSIM evaluating measures.
Similar content being viewed by others
Data Availability
Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.
References
Anoop B, Girish G, Sudeep P, Rajan J (2019) Despeckling algorithms for optical coherence tomography images: a review, Advanced Classification Techniques for Healthcare Analysis :286–310
Candes EJ, Li X, Soltanolkotabi M (2015) Phase retrieval via wirtinger flow: theory and algorithms. IEEE Trans Inf Theory 61(4):1985–2007
Chen J, Ying H, Liu X, Gu J, Feng R, Chen T, Gao H, Jian W (2020) A transfer learning based super-resolution microscopy for biopsy slice images: the joint methods perspective. IEEE/ACM Trans Comput Biol Bioinforma 18 (1):103–113
Chen T, Liu X, Feng R, Wang W, Yuan C, Lu W, He H, Gao H, Ying H, Chen DZ, Wu J (2021) Discriminative cervical lesion detection in colposcopic images with global class activation and local bin excitation. IEEE J Biomed Health Inf 26(4):1411–1421
Deng X, Yang R, Xu M, Dragotti PL (2019) Wavelet domain style transfer for an effective perception-distortion tradeoff in single image super-resolution. In: ICCV, pp 3076–3085
Gao H, Xu K, Cao M, Xiao J, Xu Q, Yin Y (2021) The deep features and attention mechanism-based method to dish healthcare under social IoT systems: an empirical study with a hand-deep local–global net. IEEE Trans Comput Soc Syst 9(1):336–347
Gupta RK, Bruce GD, Powis SJ, Dholakia K (2020) Deep learning enabled laser speckle wavemeter with a high dynamic range. Laser Photonics Rev 14:2000120
Horé A., Ziou D (2020) Image quality metrics: PSNR vs. SSIM
Huang GB, Ramesh M, Berg T, Learned-Miller E (2008) Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In: Dans Workshop on Faces in ‘Real-Life’ Images: Detection, Alignment, and Recognition. https://hal.inria.fr/inria-00321923
Hyun D, Brickson LL, Looby KT, Dahl JJ (2019) Beamforming and speckle reduction using neural networks. IEEE Trans Ultrason Ferroelectrics Freq Control 66(5):898–910
Kakkava E, Rahmani B, Borhani N, Tegin U, Loterie D, Konstantinou G, Moser C, Psaltis D (2019) Imaging through multimode fibers using deep learning: the effects of intensity versus holographic recording of the speckle pattern. Opt Fiber Technol 52:101985
Katz O, Heidmann P, Fink M, Gigan S (2014) Non-invasive single-shot imaging through scattering layers and around corners via speckle correlations. Nat Photonics 8:784–790
Kim M, Choi W, Choi Y, Yoon C, Choi W (2015) Transmission matrix of a scattering medium and its applications in biophotonics. Opt Express 23(10):12468–12668
Lan T, Li K (2021) Efficient reconstruction of industrial images using optimized HMK splines. IEEE Trans Ind Inform 17(7):4657–4668
LeCun Y, Cortes C, Burges CJ (2010) MNIST handwritten digit database. AT&T Labs. http://yann.lecun.com/exdb/mnist. Accessed 1998
Liu Y, Yu J, Han Y (2018) Understanding the effective receptive field in semantic image segmentation. Multimed Tools Appl 77:22159–22171
Li Y, Xue Y, Tian L (2018) Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media. Optica 5(10):1181–1190
Li S, Deng M, Lee J, Sinha A, Barbastathis G (2018) Imaging through glass diffusers using densely connected convolutional networks. Optica 5 (7):803–813
Li Y, Cheng S, Xue Y, Tian L (2021) Displacement-agnostic coherent imaging through scatter with an interpretable deep neural network. Opt Express 29(2):2244–2257
Luo W, Li Y, Urtasun R, Zemel R (2016) Understanding the effective receptive field in deep convolutional neural networks 30Th conference on neural information processing systems (NIPS)
Mirza M, Osindero S (2014) Conditional generative adversarial nets. CoRR. arXiv:1411.1784
Mishra S, Chen DZ, Hu XS (2020) A data-aware deep supervised method for retinal vessel segmentation. In: IEEE 17Th international symposium on biomedical imaging (ISBI), pp 1254–1257
Mohan E, Rajeshi A, Sunitha G, Konduru RM, Auanija J, Babu LG (2021) A deep neural network learning-based speckle noise removal technique for enhancing the quality of synthetic-aperture radar images. Concurrency Computation Practice Experience., to be published
Mosk AP, Lagendijk A, Lerosey G, Fink M (2012) Controlling waves in space and time for imaging and focusing in complex media. Nat Photonics 6(5):283–292
Pathak D, Krahenbuhl P, Donahue J, Darrell T, Efros AA (2016) Context encoders: feature learning by inpainting. IEEE Conf Comput Vis Pattern Recognit :2536–2544
Romera E, Alvarez JM, Bergasa LM, Arroyo R (2018) ERFNEt: Efficient residual factorized ConvNet for real-time semantic segmentation. IEEE Trans Intell Transp Syst 19(1):263–272
Sanghvi Y, Kalepu Y, Khankhoje UK (2020) Embedding deep learning in inverse scattering problems. IEEE Trans Comput Imaging 6:46–56
Santos MS, Kalantari NK (2020) Single image HDR reconstruction using a CNN with masked features and perceptual loss. ACM Trans Graph 39 (4):80:1–80:10
Satat G, Tancik M, Raskar R (2020) Lensless imaging with compressive ultrafast sensing. IEEE Trans Comput Imaging 3(3):398–407
Sharma MK, Metzler CA, Nagesh S, Baraniuk RG, Cossairt O, Veeraraghavan A (2020) Inverse scattering via transmission matrices: broadband illumination and fast phase retrieval algorithms. IEEE Trans Comput Imaging 6:95–108
Shensa MJ (1992) The discrete wavelet transform: Wedding the a trous and Mallat algorithms. IEEE Trans Signal Process 40(10):2464–2482
Sinha A, Lee J, Li S, Barbastathis G (2017) Lensless computational imaging through deep learning. Optica 4(9):1117–1125
Sun Y, Shi J, Sun L, Fan J, Zeng G (2019) Image reconstruction through dynamic scattering media based on deep learning. Opt Express 27(11):16032–16044
Tan HL, Li Z, Tan YH, Rahardja S, Yeo C (2013) A perceptually relevant MSE-based image quality metric. IEEE Trans Image Process 22 (11):4447–4458
Uelwer T, Oberstra A, Harmeling S (2021) Phase retrieval using conditional generative adversarial networks. In: International conference on pattern recognition (ICPR), pp 10–15
Vellekoop IM, Mosk AP (2007) Focusing coherent light through opaque strongly scattering media. Opt Lett 32(16):2309–2311
Wang Z, Ji S (2018) Smoothed dilated convolutions for improved dense prediction. In: KDD, London, United Kingdom, pp 2486–2495
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Xiao H, Rasul K, Vollgraf R Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747
Xiao J, Xu H, Gao H, Bian M, Li Y (2021) A weakly supervised semantic segmentation network by aggregating seed cues: the multi-object proposal generation perspective. ACM Trans Multimed Comput Commun Appl 17(1s):1–19
Xu K, Ba JL, Kiros R, Courville A, Salakhutdinov R, Zemel R, Bengio Y (2015) Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of machine learning research (PMLR), vol. 37, pp. 2048–2057
Yang Y, Deng L, Jiao P, Chua Y, Pei J, Ma C, Li G (2020) Transfer learning in general lensless Imaging through scattering media. In: IEEE conference on industrial electronics and applications (ICIEA), pp 1132–1141
Yao HM, Sha WEI, Jiang L (2019) Two-step enhanced deep learning approach for electromagnetic inverse scattering problems. IEEE Antennas Wirel Propag Lett 18(11):2254–2258
Yao HM, Jiang L, Sha WEI (2020) Enhanced deep learning approach based on the deep convolutional encoder-decoder architecture for electromagnetic inverse scattering problems. IEEE Antennas Wirel Propag Lett 19(7):1211–1215
Yoon S, Kim M, Jang M, Choi Y, Choi W, Kang S, Choi W (2020) Deep optical imaging within complex scattering media. Nat Rev 2:141–158
Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122
Yuan Z, Wang H Multiple scattering media imaging via end-to-end neural network. arXiv:1806.09968
Zhou Z, Wang Y, Guo Y, Qi Y, Yu J (2020) Image quality improvement of hand-held ultrasound devices with a two-stage generative adversarial network. IEEE Trans Biomed Eng 67(1):298–311
Zhu H, Cao Z, Lian L, Ye G, Gao H, Jian W (2022) Cariesnet: a deep learning approach for segmentation of multi-stage caries lesion from oral panoramic X-ray image. Neural Comput Applic 7:1–9
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China under Grants (62031018, 61971227).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of Interests
Authors Linli Xu, Peixian Liang, Jing Han, Lianfa Bai and Danny Z. Chen declare that they have no conflicts of interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xu, L., Liang, P., Han, J. et al. A two-stage enhancement network with optimized effective receptive field for speckle image reconstruction. Multimed Tools Appl 82, 19923–19943 (2023). https://doi.org/10.1007/s11042-022-14208-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-14208-w