Low-light Image Enhancement Algorithm Based on Adaptive Feature Decomposition and Parallel Dual Extractor

Many existing methods based on Retin-ex model mainly rely on convolution layer to process input features, which-h lack dynamic adjustment ability and are easily disturbed by redundant information. At the same time, when the local features are transferred to Transformer for modeling, the detailed inf...

Full description

Saved in:
Bibliographic Details
Published in:Chinese Automation Congress (Online) pp. 6918 - 6923
Main Authors: Li, Ce, Li, ChaoYue, Wang, Kai, Jiang, RuiLong, Chen, HuiZhong, Xiao, LiMei
Format: Conference Proceeding
Language:English
Published: IEEE 01.11.2024
Subjects:
Adaptive Feature Decomposition
Brightness
Convolution
Feature extraction
Image color analysis
Image enhancement
Lighting
Low-light image enhancement
Noise
Noise reduction
Parallel Dual Extractor
Transformers
Visualization
ISSN:2688-0938
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Many existing methods based on Retin-ex model mainly rely on convolution layer to process input features, which-h lack dynamic adjustment ability and are easily disturbed by redundant information. At the same time, when the local features are transferred to Transformer for modeling, the detailed information may be lost, which will lead to the decline of the visual quality of the image. In this paper, an Adaptive Feature Decomposition and Parallel Double Extractor (AFD-PDE) method is proposed to solve the problems of insufficient brightness, loss of details and increased noise in the process of weak light image enhancement. By combining the weak light image with illumination prior, this method extracts illumination features and illumination maps by convolution operation and channel attention mechanism, thus realizing adaptive feature decomposition. Then, the extracted features are denoised by Parallel Double Extractor module, and the image details are restored and noise is eliminated by down-sampling and up-sampling layer by layer. Finally, a high-quality image enhancement effect is achieved by combining Gamma correction and feature fusion. The experimental results verify the superior performance of AFD-PDE method in weak light conditions, and show its broad application prospects in the field of image enhancement.
AbstractList Many existing methods based on Retin-ex model mainly rely on convolution layer to process input features, which-h lack dynamic adjustment ability and are easily disturbed by redundant information. At the same time, when the local features are transferred to Transformer for modeling, the detailed information may be lost, which will lead to the decline of the visual quality of the image. In this paper, an Adaptive Feature Decomposition and Parallel Double Extractor (AFD-PDE) method is proposed to solve the problems of insufficient brightness, loss of details and increased noise in the process of weak light image enhancement. By combining the weak light image with illumination prior, this method extracts illumination features and illumination maps by convolution operation and channel attention mechanism, thus realizing adaptive feature decomposition. Then, the extracted features are denoised by Parallel Double Extractor module, and the image details are restored and noise is eliminated by down-sampling and up-sampling layer by layer. Finally, a high-quality image enhancement effect is achieved by combining Gamma correction and feature fusion. The experimental results verify the superior performance of AFD-PDE method in weak light conditions, and show its broad application prospects in the field of image enhancement.
Author Xiao, LiMei
Li, ChaoYue
Wang, Kai
Jiang, RuiLong
Chen, HuiZhong
Li, Ce
Author_xml – sequence: 1
  givenname: Ce
  surname: Li
  fullname: Li, Ce
  organization: School of Electrical Engineering and Information Engineering, Lanzhou University of Technology,Lanzhou,China
– sequence: 2
  givenname: ChaoYue
  surname: Li
  fullname: Li, ChaoYue
  organization: School of Electrical Engineering and Information Engineering, Lanzhou University of Technology,Lanzhou,China
– sequence: 3
  givenname: Kai
  surname: Wang
  fullname: Wang, Kai
  organization: School of Electrical Engineering and Information Engineering, Lanzhou University of Technology,Lanzhou,China
– sequence: 4
  givenname: RuiLong
  surname: Jiang
  fullname: Jiang, RuiLong
  organization: School of Electrical Engineering and Information Engineering, Lanzhou University of Technology,Lanzhou,China
– sequence: 5
  givenname: HuiZhong
  surname: Chen
  fullname: Chen, HuiZhong
  organization: School of Electrical Engineering and Information Engineering, Lanzhou University of Technology,Lanzhou,China
– sequence: 6
  givenname: LiMei
  surname: Xiao
  fullname: Xiao, LiMei
  organization: School of Electrical Engineering and Information Engineering, Lanzhou University of Technology,Lanzhou,China
BookMark eNo1kMtOwkAUQEejiYj8gTHzA8U7z84sawElIdEFe3Lb3sKYPkg7-Ph7TNTVWZzkLM4tu-r6jhh7EDAXAvxjnuVWOS_nEqSeC3BWpwYu2Myn3ikDyjoL-pJNpHUuAa_cDZuN4zsASCW00TBhYdN_Jk3YHyJft7gnvuwO2JXUUhd51uz7IcRDy59wpIr3Hc8qPMbwQXxFGE8D8QWVfXvsxxDDj8au4m84YNNQwxcnbPjyKw5Yxn64Y9c1NiPN_jhl29Vym78km9fndZ5tkuBFTJRWIpWlBqMKX0Atamu9kbI2UAiopaA0da5WRWHKVBoqsUJjSeq0ECXqSk3Z_W82ENHuOIQWh-_d_xx1Bn76WzI
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CAC63892.2024.10864750
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798350368604
EISSN 2688-0938
EndPage 6923
ExternalDocumentID 10864750
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62363025
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IF
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i91t-343172c4053b9b0f1f669522f50b10f21e7788f3bb5c725ecada56e247b1ca4d3
IEDL.DBID RIE
IngestDate Wed Feb 19 06:10:58 EST 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i91t-343172c4053b9b0f1f669522f50b10f21e7788f3bb5c725ecada56e247b1ca4d3
PageCount 6
ParticipantIDs ieee_primary_10864750
PublicationCentury 2000
PublicationDate 2024-Nov.-1
PublicationDateYYYYMMDD 2024-11-01
PublicationDate_xml – month: 11
  year: 2024
  text: 2024-Nov.-1
  day: 01
PublicationDecade 2020
PublicationTitle Chinese Automation Congress (Online)
PublicationTitleAbbrev CAC
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002314540
Score 1.8879166
Snippet Many existing methods based on Retin-ex model mainly rely on convolution layer to process input features, which-h lack dynamic adjustment ability and are...
SourceID ieee
SourceType Publisher
StartPage 6918
SubjectTerms Adaptive Feature Decomposition
Brightness
Convolution
Feature extraction
Image color analysis
Image enhancement
Lighting
Low-light image enhancement
Noise
Noise reduction
Parallel Dual Extractor
Transformers
Visualization
Title Low-light Image Enhancement Algorithm Based on Adaptive Feature Decomposition and Parallel Dual Extractor
URI https://ieeexplore.ieee.org/document/10864750
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF60ePCkYsU3e_CaNo9NtjnWPlCQ0kMPvZV9TGwhTUqaqD_fmTStePDgLQSyCzMw3zeb-fZj7KmnLeJYEmL1s64jBCSO8kA7mG5k94AcRZrabEJOJr35PJ42YvVaCwMA9fAZdOix_pdvc1PRUVmXXIGEpA79WMpoJ9Y6HKggUaHb5BoVsOfG3UF_QHhMcitfdPYf_7JRqVFkfPbP_c9Z-0ePx6cHpLlgR5BdstVb_umk1Fvz1zVWBT7KlpRCWoP30_cc2_7lmj8jTFmeZ7xv1YZqGyfWVxXAh0Dz5M3QFleZ5VNVkLVKyoeVSvnoqyxqN542m41Hs8GL0xgnOKvYK52ASIFvkIoFOtZu4iVRFCPPSkJXe27ieyCx8U0CrUMj_RCMsiqMwBdSe0YJG1yxVpZncM14jHTRWgOBVYRcQmOBNLiK6WEsjBY3rE1hWmx2V2Ms9hG6_eP9HTulZOzEfPesVRYVPLAT81GutsVjndBvu26hlg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8JAEN4YNNGTGjG-3YPXQh9bSo_IIxCRcODAjexjKiSlJbVVf74zpWA8ePDWNOlmM5PM9812vv0Ye2orgzgW-Vj9jG0JAZElHVAWphvZPSBHCXRpNhFMJu35PJxWYvVSCwMA5fAZNOix_JdvUl3QUVmTXIFEQB36oS-Ea2_lWvsjFaQqdJ9cpQN27LDZ7XQJkUlw5YrG7vNfRioljgxO_7mDM1b_UeTx6R5rztkBJBdsNU4_rZi6az5aY13g_WRJSaQ1eCd-S7HxX675MwKV4WnCO0ZuqLpx4n1FBrwHNFFejW1xmRg-lRmZq8S8V8iY97_yrPTjqbPZoD_rDq3KOsFahU5ueUQLXI1kzFOhsiMnarVCZFqRbyvHjlwHAmx9I08pXweuD1oa6bfAFYFytBTGu2S1JE3givEQCaMxGjwjCbuEwhKpcRXdxlhoJa5ZncK02Gwvx1jsInTzx_tHdjycvY4X49Hk5ZadUGK20r47VsuzAu7Zkf7IV-_ZQ5ncb1JUpN0
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=Chinese+Automation+Congress+%28Online%29&rft.atitle=Low-light+Image+Enhancement+Algorithm+Based+on+Adaptive+Feature+Decomposition+and+Parallel+Dual+Extractor&rft.au=Li%2C+Ce&rft.au=Li%2C+ChaoYue&rft.au=Wang%2C+Kai&rft.au=Jiang%2C+RuiLong&rft.date=2024-11-01&rft.pub=IEEE&rft.eissn=2688-0938&rft.spage=6918&rft.epage=6923&rft_id=info:doi/10.1109%2FCAC63892.2024.10864750&rft.externalDocID=10864750