Please use this identifier to cite or link to this item:
DC FieldValueLanguage
dc.contributorChinese Mainland Affairs Office-
dc.contributorDepartment of Electronic and Information Engineering-
dc.creatorZhou, LN-
dc.creatorXiao, Y-
dc.creatorChen, W-
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.rightsThis work is licensed under a Creative Commons Attribution 4.0 License. For more information, see
dc.rightsThe following publication L. Zhou, Y. Xiao and W. Chen, "Imaging Through Turbid Media With Vague Concentrations Based on Cosine Similarity and Convolutional Neural Network," in IEEE Photonics Journal, vol. 11, no. 4, pp. 1-15, Aug. 2019, Art no. 7801315 is available at
dc.subjectImage reconstructionen_US
dc.subjectUnderwater imagingen_US
dc.subjectTurbid mediaen_US
dc.subjectCosine similarityen_US
dc.subjectDeep learningen_US
dc.titleImaging through turbid media with vague concentrations based on cosine similarity and convolutional neural networken_US
dc.typeJournal/Magazine Articleen_US
dcterms.abstractUnderwater imaging has been extensively studied to bypass the limitation aroused by scattering and absorption of water solutions. It is highly meaningful to the development of optical imaging, especially in turbid media. The existing methods developed for reconstruction of original images from speckle patterns are applied in a stable medium, which obstruct wider applications in unpredictable media. Hence, it is crucial to take changeable environments into consideration to circumvent the limits of the extant methods. In this paper, we propose a new approach based on cosine similarity for speckle classification and convolutional neural network (CNN) for the reconstruction. The targets are placed in variant densities of turbid water mixed with certain of milk, and their corresponding intensity speckle patterns are recorded by a camera. It is verified that utilization of cosine similarity for the classification of patterns recorded in changeable media ensures high fidelity for label predictions. For a speckle pattern obtained in totally unidentified media, it can make a prediction of the density which has a high probability of accuracy. We can exploit the classified density to automatically select the most appropriate datasets to train a CNN model and then make predictions in real time with the trained CNN model. The combined model presented in this paper is tolerant to the uncertainty of turbidity. Moreover, it guarantees high-accuracy pattern classification and high-quality image reconstruction. It is feasible for potential applications in harsh water solutions with unknown perturbations of concentrations.-
dcterms.bibliographicCitationIEEE photonics journal, Aug. 2019, v. 11, no. 4, 7801315, p. 1-16-
dcterms.isPartOfIEEE photonics journal-
dc.description.validate201909 bcrc-
Appears in Collections:Journal/Magazine Article
Files in This Item:
File Description SizeFormat 
Zhou_Imaging_Turbid_Media.pdf3.76 MBAdobe PDFView/Open
View full-text via PolyU eLinks SFX Query
Show simple item record
PIRA download icon_1.1View/Download Full Text


Citations as of Feb 14, 2020

Page view(s)

Citations as of Feb 12, 2020


Citations as of Feb 12, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.