Recurrent Nerual Imaging: An Evolutionary Approach for Mixed Possion-Gaussian Image Denoising

Recurrent neural networks (RNNs) are traditionally used for machine learning applications for temporal sequences such as natural language processing. Its application to image processing is relatively new. In this paper, we apply RNNs to denoise images corrupted by mixed Poisson and Gaussian noise. T...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA) S. 484 - 489
Hauptverfasser: Ranganath, Aditya, DeGuchy, Omar, Santiago, Fabian, Singhal, Mukesh, Marcia, Roummel
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.12.2022
Schlagworte:
autoencoders
image denoising
Imaging
Knowledge engineering
Machine learning
Natural language processing
Noise measurement
Noise reduction
Recurrent neural networks
upsampling
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Recurrent neural networks (RNNs) are traditionally used for machine learning applications for temporal sequences such as natural language processing. Its application to image processing is relatively new. In this paper, we apply RNNs to denoise images corrupted by mixed Poisson and Gaussian noise. The motivation for using an RNN comes from viewing the denoising of the Poisson-Gaussian realization as a temporal process. The network then attempts to trace back the steps that create the noisy realization in order to arrive at the noiseless reconstruction. Numerical experiments demonstrate that our proposed RNN approach outperforms convolutional autoen-coder methods for denoising and upsampling low-resolution images from the CIFAR-10 dataset.
AbstractList Recurrent neural networks (RNNs) are traditionally used for machine learning applications for temporal sequences such as natural language processing. Its application to image processing is relatively new. In this paper, we apply RNNs to denoise images corrupted by mixed Poisson and Gaussian noise. The motivation for using an RNN comes from viewing the denoising of the Poisson-Gaussian realization as a temporal process. The network then attempts to trace back the steps that create the noisy realization in order to arrive at the noiseless reconstruction. Numerical experiments demonstrate that our proposed RNN approach outperforms convolutional autoen-coder methods for denoising and upsampling low-resolution images from the CIFAR-10 dataset.
Author Singhal, Mukesh
Ranganath, Aditya
DeGuchy, Omar
Marcia, Roummel
Santiago, Fabian
Author_xml – sequence: 1
  givenname: Aditya
  surname: Ranganath
  fullname: Ranganath, Aditya
  organization: University of California, Merced,School of Engineering,Merced,CA,USA,95343
– sequence: 2
  givenname: Omar
  surname: DeGuchy
  fullname: DeGuchy, Omar
  organization: University of California, Merced,Applied Mathematics,Merced,CA,USA,95343
– sequence: 3
  givenname: Fabian
  surname: Santiago
  fullname: Santiago, Fabian
  organization: University of California, Merced,Applied Mathematics,Merced,CA,USA,95343
– sequence: 4
  givenname: Mukesh
  surname: Singhal
  fullname: Singhal, Mukesh
  organization: University of California, Merced,School of Engineering,Merced,CA,USA,95343
– sequence: 5
  givenname: Roummel
  surname: Marcia
  fullname: Marcia, Roummel
  organization: University of California, Merced,Applied Mathematics,Merced,CA,USA,95343
BookMark eNotjlFLwzAUhSPog5v-A4X8gc6bmyZtfCt1zsGmIvoo45qmM9AlI13F_XuL-nQOHL6PM2GnIQbH2LWAmRBgbpb1elUppY2eISDOAKAoT9hEaK1yjaWU5-z9xdkhJRcO_NGlgTq-3NHWh-0trwKff8VuOPgYKB15td-nSPaTtzHxtf92DX-OfT-u2YKGsVD4hR2_cyH6fpRcsLOWut5d_ueUvd3PX-uHbPW0WNbVKvMI-SFrLFjQSARStlblQpFptPko0RbalMpJtEQFWoWylQXlDeY5KmUaMK7ERk7Z1Z_XO-c2--R34-GNANBGaJQ_VKBQ_g
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICMLA55696.2022.00078
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 1665462833
9781665462839
EndPage 489
ExternalDocumentID 10069162
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  funderid: 10.13039/100000001
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i204t-dc0c062aa033fc5415a9d69b82c76985e32caa72c523f37a4d2442559d09e82d3
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000980994900069&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Jan 18 11:14:48 EST 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i204t-dc0c062aa033fc5415a9d69b82c76985e32caa72c523f37a4d2442559d09e82d3
PageCount 6
ParticipantIDs ieee_primary_10069162
PublicationCentury 2000
PublicationDate 2022-Dec.
PublicationDateYYYYMMDD 2022-12-01
PublicationDate_xml – month: 12
  year: 2022
  text: 2022-Dec.
PublicationDecade 2020
PublicationTitle 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)
PublicationTitleAbbrev ICMLA
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8368926
Snippet Recurrent neural networks (RNNs) are traditionally used for machine learning applications for temporal sequences such as natural language processing. Its...
SourceID ieee
SourceType Publisher
StartPage 484
SubjectTerms autoencoders
image denoising
Imaging
Knowledge engineering
Machine learning
Natural language processing
Noise measurement
Noise reduction
Recurrent neural networks
upsampling
Title Recurrent Nerual Imaging: An Evolutionary Approach for Mixed Possion-Gaussian Image Denoising
URI https://ieeexplore.ieee.org/document/10069162
WOSCitedRecordID wos000980994900069&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF60ePCkYsU3e_C6muaxD2-ltlqwpYhCL1ImuxMIaCJpUvTfu7uNj4sHb2FJWJg8vpnJfN9HyIVFGWNxTjIOccRi2dMs7WlgoJyYus1vIQFvNiGmUzmfq1lLVvdcGET0w2d46Q79v3xT6sa1yuwbHnCbztgv7qYQfE3Walk5vUBdjQeT-36ScOVGD0IvxOnc0365pnjQGO38c7td0v2h39HZN7DskQ0s9snzg-uMOy0lOsWqgRc6fvUOQ9e0X9Dhqn2EoPqg_VYnnNqElE7ydzR0Vrpp14LdQrN0tEl_MdIbLMrcdQu65Gk0fBzcsdYbgeVhENfM6EAHPAQIoijTiYVhUIarVIZacCUTjEINIEJtC80sEhAbi-OufDCBQhma6IB0irLAQ0LTNEtFJIXkKGKFSQr2_ESLOLPlDpd4RLouNou3tfzF4issx3-sn5BtF_71zMcp6dRVg2dkS6_qfFmd-5v2CUPomaM
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFA0yBX1SceK3efA1mqXNl29jbm64lSET9iIjTVIYaCvdOvTfm2T148UH30ppCSRpzr2395wDwJVDGeNwTiCm4gjFoqVR2tIKKenF1F18q6gKZhM8ScR0Ksc1WT1wYay1ofnMXvvL8C_fFLrypTL3hWPmwhl34m7SOCZ4TdeqeTktLG8GndGwTSmTvvmABClO75_2yzclwEZv958D7oHmDwEPjr-hZR9s2PwAPD_62rhXU4KJLSv1AgevwWPoFrZz2F3Vm0iVH7BdK4VDF5LC0fzdGjgufL9rju5VtfDEyfCyhXc2L-a-XtAET73upNNHtTsCmhMcL5HRWGNGlMJRlGnqgFhJw2QqiOZMCmojopXiRLtUM4u4io1Dcp9AGCytICY6BI28yO0RgGmapTwSXDDLY2lpqtzzVPM4cwkPE_YYNP3czN7WAhizr2k5-eP-JdjuT0bD2XCQPJyCHb8U6w6QM9BYlpU9B1t6tZwvyouwgJ9wU5zq
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2022+21st+IEEE+International+Conference+on+Machine+Learning+and+Applications+%28ICMLA%29&rft.atitle=Recurrent+Nerual+Imaging%3A+An+Evolutionary+Approach+for+Mixed+Possion-Gaussian+Image+Denoising&rft.au=Ranganath%2C+Aditya&rft.au=DeGuchy%2C+Omar&rft.au=Santiago%2C+Fabian&rft.au=Singhal%2C+Mukesh&rft.date=2022-12-01&rft.pub=IEEE&rft.spage=484&rft.epage=489&rft_id=info:doi/10.1109%2FICMLA55696.2022.00078&rft.externalDocID=10069162