Low-level structure feature extraction for image processing via stacked sparse denoising autoencoder

•We use deep learning for image processing by extracting image feature.•The extraction has good performance in noisy or low-light circumstance.•We optimize TV and L0 smoothing filter by the proposed feature extraction.•The features can extract image structure features regardless the inputs directly....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) Jg. 243; S. 12 - 20
Hauptverfasser: Fan, Zunlin, Bi, Duyan, He, Linyuan, Shiping, Ma, Gao, Shan, Li, Cheng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 21.06.2017
Schlagworte:
ISSN:0925-2312, 1872-8286
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract •We use deep learning for image processing by extracting image feature.•The extraction has good performance in noisy or low-light circumstance.•We optimize TV and L0 smoothing filter by the proposed feature extraction.•The features can extract image structure features regardless the inputs directly. In this paper, we propose a novel low-level structure feature extraction for image processing based on deep neural network, stacked sparse denoising autoencoder (SSDA). The current image processing methods via deep learning are directly building and learning the end-to-end mappings between the input/output. Instead, we advocate the analysis of the first layer learning features from input data. With the learned low-level structure features, we improve two edge-preserving filters that are key to image processing tasks such as denoising, High Dynamic Range (HDR) compression and details enhancement. Due to the validity and superiority of the proposed feature extraction, the results computed by the two improved filters do not suffer from the drawbacks including halos, edge blurring, noise amplification and over-enhancement. More importantly, we demonstrate that the features trained from natural images are not specific and can extract the structure features of infrared images. Hence, it is feasible to handle tasks by using the trained features directly.
AbstractList •We use deep learning for image processing by extracting image feature.•The extraction has good performance in noisy or low-light circumstance.•We optimize TV and L0 smoothing filter by the proposed feature extraction.•The features can extract image structure features regardless the inputs directly. In this paper, we propose a novel low-level structure feature extraction for image processing based on deep neural network, stacked sparse denoising autoencoder (SSDA). The current image processing methods via deep learning are directly building and learning the end-to-end mappings between the input/output. Instead, we advocate the analysis of the first layer learning features from input data. With the learned low-level structure features, we improve two edge-preserving filters that are key to image processing tasks such as denoising, High Dynamic Range (HDR) compression and details enhancement. Due to the validity and superiority of the proposed feature extraction, the results computed by the two improved filters do not suffer from the drawbacks including halos, edge blurring, noise amplification and over-enhancement. More importantly, we demonstrate that the features trained from natural images are not specific and can extract the structure features of infrared images. Hence, it is feasible to handle tasks by using the trained features directly.
Author Bi, Duyan
He, Linyuan
Li, Cheng
Shiping, Ma
Gao, Shan
Fan, Zunlin
Author_xml – sequence: 1
  givenname: Zunlin
  orcidid: 0000-0003-2226-9505
  surname: Fan
  fullname: Fan, Zunlin
  email: 18191261397@163.com
  organization: Air Force Engineering University, Aeronautics and Astronautics Engineering College, No. 1 Baling Road, Baqiao District, Xi'an, Shaanxi 710038, China
– sequence: 2
  givenname: Duyan
  surname: Bi
  fullname: Bi, Duyan
  organization: Air Force Engineering University, Aeronautics and Astronautics Engineering College, No. 1 Baling Road, Baqiao District, Xi'an, Shaanxi 710038, China
– sequence: 3
  givenname: Linyuan
  surname: He
  fullname: He, Linyuan
  organization: Air Force Engineering University, Aeronautics and Astronautics Engineering College, No. 1 Baling Road, Baqiao District, Xi'an, Shaanxi 710038, China
– sequence: 4
  givenname: Ma
  surname: Shiping
  fullname: Shiping, Ma
  organization: Air Force Engineering University, Aeronautics and Astronautics Engineering College, No. 1 Baling Road, Baqiao District, Xi'an, Shaanxi 710038, China
– sequence: 5
  givenname: Shan
  surname: Gao
  fullname: Gao, Shan
  organization: Air Force Engineering University, Aeronautics and Astronautics Engineering College, No. 1 Baling Road, Baqiao District, Xi'an, Shaanxi 710038, China
– sequence: 6
  givenname: Cheng
  surname: Li
  fullname: Li, Cheng
  organization: Air Force Aviation University, Nanhu Road, Nanguan District, Changchun, Jilin 130022, China
BookMark eNqFkMtOwzAQRS1UJErhD1jkBxJsJ3USFkio4iVVYgNryxmPK5c0rmynwN_jtqxYwGoWM-dq7jknk8ENSMgVowWjTFyviwFHcJuCU1YXlBdUiBMyZU3N84Y3YkKmtOXznJeMn5HzENY0HTLeToleuo-8xx32WYh-hDh6zAyqw8TP6BVE64bMOJ_ZjVphtvUOMAQ7rLKdVYlS8I46C1vlA2YaB2cPSzVGhwM4jf6CnBrVB7z8mTPy9nD_unjKly-Pz4u7ZQ4lFTHvgFNdG9ZRXnXU8DkwoxTvsFJCt3Reg1BUU1aCNmCYbhtWsRY7oRArxrGckeqYC96F4NHIrU9P-y_JqNybkmt5NCX3piTlMplK2M0vDGxU-9qpvu3_g2-PMKZiO4teBrCpN2rrEaLUzv4d8A1K9I0u
CitedBy_id crossref_primary_10_1109_ACCESS_2020_2991846
crossref_primary_10_1002_cpe_6155
crossref_primary_10_1186_s12911_019_0765_4
crossref_primary_10_1007_s11831_025_10260_5
crossref_primary_10_1016_j_apacoust_2020_107391
crossref_primary_10_1007_s10916_017_0814_4
crossref_primary_10_1109_ACCESS_2019_2956508
crossref_primary_10_1109_TMM_2021_3096088
crossref_primary_10_3390_su17146284
crossref_primary_10_1016_j_neucom_2017_07_017
crossref_primary_10_1155_2021_6687146
crossref_primary_10_1016_j_neucom_2020_02_051
crossref_primary_10_1007_s11042_018_6811_x
crossref_primary_10_1016_j_knosys_2020_105484
crossref_primary_10_1186_s12911_020_1113_4
crossref_primary_10_1080_03007995_2020_1837763
crossref_primary_10_1016_j_asoc_2018_10_035
crossref_primary_10_1109_ACCESS_2017_2771621
crossref_primary_10_1016_j_chb_2018_08_039
crossref_primary_10_1016_j_infrared_2017_08_015
crossref_primary_10_1109_TMI_2021_3077187
crossref_primary_10_3390_s20082179
crossref_primary_10_1016_j_epsr_2023_109300
crossref_primary_10_1109_ACCESS_2018_2889327
Cites_doi 10.1145/566654.566574
10.1090/S0002-9947-1952-0047179-6
10.1145/1360612.1360666
10.1016/j.patcog.2016.06.008
10.1016/j.neucom.2016.08.098
10.1016/j.neucom.2016.12.038
10.1016/j.infrared.2015.11.006
10.1109/TIP.2015.2487860
10.1016/j.neucom.2016.12.027
10.1109/TIP.2016.2579306
10.1088/2040-8978/18/8/085706
10.1016/j.neucom.2015.08.127
10.1109/TPAMI.2012.213
10.1109/TPAMI.2015.2439281
10.1137/060649781
10.1016/j.acha.2007.09.003
10.1016/0167-2789(92)90242-F
ContentType Journal Article
Copyright 2017
Copyright_xml – notice: 2017
DBID AAYXX
CITATION
DOI 10.1016/j.neucom.2017.02.066
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-8286
EndPage 20
ExternalDocumentID 10_1016_j_neucom_2017_02_066
S0925231217303909
GroupedDBID ---
--K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JM
9JN
AABNK
AACTN
AADPK
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXLA
AAXUO
AAYFN
ABBOA
ABCQJ
ABFNM
ABJNI
ABMAC
ABYKQ
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
AEBSH
AEKER
AENEX
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGWIK
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
KOM
LG9
M41
MO0
MOBAO
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RIG
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SSN
SSV
SSZ
T5K
ZMT
~G-
29N
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
FEDTE
FGOYB
HLZ
HVGLF
HZ~
R2-
SBC
SEW
WUQ
XPP
~HD
ID FETCH-LOGICAL-c306t-bc20d7f1b024b0f25c1faa2be4a6d9057c6a0d013cdfcf1d981419eb6aee412e3
ISICitedReferencesCount 32
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000399511900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0925-2312
IngestDate Sat Nov 29 03:02:48 EST 2025
Tue Nov 18 21:49:07 EST 2025
Fri Feb 23 02:30:22 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Pattern recognition
Image processing
Spatial filter
Image enhancement
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-bc20d7f1b024b0f25c1faa2be4a6d9057c6a0d013cdfcf1d981419eb6aee412e3
ORCID 0000-0003-2226-9505
PageCount 9
ParticipantIDs crossref_primary_10_1016_j_neucom_2017_02_066
crossref_citationtrail_10_1016_j_neucom_2017_02_066
elsevier_sciencedirect_doi_10_1016_j_neucom_2017_02_066
PublicationCentury 2000
PublicationDate 2017-06-21
PublicationDateYYYYMMDD 2017-06-21
PublicationDate_xml – month: 06
  year: 2017
  text: 2017-06-21
  day: 21
PublicationDecade 2010
PublicationTitle Neurocomputing (Amsterdam)
PublicationYear 2017
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Yosinski, Clune, Bengio, Lipson (bib0020) 2014
Liu, Wang, Liu, Zeng, Liu, Alsaadi (bib0001) 2017; 234
li, Zhao, Yang, Wu, Zhuang, Ling, Wang (bib0004) 2016; 25
Rudin, Osher, Fatemi (bib0016) 1992; 60
Agostinelli, Anderson, Lee (bib0012) 2013
Fan, Bi, Gao, He, Ding (bib0023) 2016; 18
Hong, Yu, Wan, Tao, Wang (bib0010) 2015; 24
Dong, Loy, He, Tang (bib0007) 2016; 38
Hong, Yu, Tao, Wang (bib0011) 2015; 62
Farbman, Fattal, Lischinski, Szeliski (bib0017) 2008; 27
Zhu, Wang, Bai, Yao, Bai (bib0009) 2016; 204
Xu, Lu, Xu, Jia (bib0018) 2010; 30
Duffin, Schaeffer (bib0024) 1952; 72
Zhang, Wu (bib0005) 2016
Easley, Labate, Lim (bib0022) 2008; 25
Gou, Labate (bib0021) 2007; 39
Xu, Ren, Liu, Jia (bib0013) 2014
Fan, Bi, He, Ma (bib0025) 2016; 74
Yu, Yang, Gao, Tao (bib0003) 2016; 99
He, Sun, Tang (bib0019) 2013; 35
Sun, Zhang, An, Fan, Zhang, Wang, Dai (bib0006) 2016; vol. 9916
Sun, Zhang, Zhang, Hu (bib0008) 2017; 230
Lore, Akintayo, Sarkar (bib0014) 2016; 61
Durand, Dorsey (bib0015) 2002; 21
Tan, Tang, Zhou, Luo, Kang, Li (bib0002) 2017; 228
Durand (10.1016/j.neucom.2017.02.066_bib0015) 2002; 21
Agostinelli (10.1016/j.neucom.2017.02.066_bib0012) 2013
Xu (10.1016/j.neucom.2017.02.066_bib0018) 2010; 30
li (10.1016/j.neucom.2017.02.066_bib0004) 2016; 25
Sun (10.1016/j.neucom.2017.02.066_bib0008) 2017; 230
Lore (10.1016/j.neucom.2017.02.066_bib0014) 2016; 61
Fan (10.1016/j.neucom.2017.02.066_bib0023) 2016; 18
Duffin (10.1016/j.neucom.2017.02.066_bib0024) 1952; 72
Hong (10.1016/j.neucom.2017.02.066_bib0010) 2015; 24
Tan (10.1016/j.neucom.2017.02.066_bib0002) 2017; 228
Dong (10.1016/j.neucom.2017.02.066_bib0007) 2016; 38
Yu (10.1016/j.neucom.2017.02.066_bib0003) 2016; 99
Sun (10.1016/j.neucom.2017.02.066_bib0006) 2016; vol. 9916
Zhu (10.1016/j.neucom.2017.02.066_bib0009) 2016; 204
Xu (10.1016/j.neucom.2017.02.066_bib0013) 2014
Fan (10.1016/j.neucom.2017.02.066_bib0025) 2016; 74
Liu (10.1016/j.neucom.2017.02.066_bib0001) 2017; 234
Easley (10.1016/j.neucom.2017.02.066_bib0022) 2008; 25
He (10.1016/j.neucom.2017.02.066_bib0019) 2013; 35
Gou (10.1016/j.neucom.2017.02.066_bib0021) 2007; 39
Zhang (10.1016/j.neucom.2017.02.066_bib0005) 2016
Rudin (10.1016/j.neucom.2017.02.066_bib0016) 1992; 60
Farbman (10.1016/j.neucom.2017.02.066_bib0017) 2008; 27
Hong (10.1016/j.neucom.2017.02.066_bib0011) 2015; 62
Yosinski (10.1016/j.neucom.2017.02.066_bib0020) 2014
References_xml – start-page: 1790
  year: 2014
  end-page: 1798
  ident: bib0013
  article-title: Deep convolutional neural network for image deconvolution
  publication-title: Proceedings of Advances in Neural Information Processing Systems 27
– volume: 25
  start-page: 25
  year: 2008
  end-page: 46
  ident: bib0022
  article-title: Sparse directional image representation using the discrete shearlet transforms
  publication-title: Appl. Comput. Harmonic Anal.
– volume: 99
  start-page: 1
  year: 2016
  end-page: 11
  ident: bib0003
  article-title: Deep multimodal distance metric learning using click constraints for image ranking
  publication-title: IEEE Trans. Cybern.
– volume: 204
  start-page: 41
  year: 2016
  end-page: 50
  ident: bib0009
  article-title: Deep learning representation using autoencoder for 3D shape retrieval
  publication-title: Neurocomputing
– volume: 72
  start-page: 341
  year: 1952
  end-page: 366
  ident: bib0024
  article-title: A class of nonharmonic Fourier series
  publication-title: Trans. Am. Math. Soc.
– volume: 25
  start-page: 3919
  year: 2016
  end-page: 3930
  ident: bib0004
  article-title: DeepSaliency: multi-task deep neural network model for salient object detection
  publication-title: IEEE Trans. Image Process.
– volume: 38
  start-page: 295
  year: 2016
  end-page: 307
  ident: bib0007
  article-title: Image super-resolution using deep convolutional networks
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 24
  start-page: 5659
  year: 2015
  end-page: 5670
  ident: bib0010
  article-title: Multimodal deep autoencoder for human pose recovery
  publication-title: IEEE Trans. Image Process.
– volume: 62
  start-page: 3742
  year: 2015
  end-page: 3751
  ident: bib0011
  article-title: Image-based 3D human pose recovery by multi-view locality sensitive sparse retrieval
  publication-title: IEEE Trans. Ind. Electron.
– volume: 74
  start-page: 44
  year: 2016
  end-page: 52
  ident: bib0025
  article-title: Noise suppression and details enhancement for infrared image via novel prior
  publication-title: Infrared Phys. Technol.
– volume: vol. 9916
  year: 2016
  ident: bib0006
  article-title: Fast and accurate image denoising via a deep convolutional-pairs network
  publication-title: Advances in Multimedia Information Processing, PCM 2016. Lecture Notes in Computer Science
– volume: 234
  start-page: 11
  year: 2017
  end-page: 26
  ident: bib0001
  article-title: A survey of deep neural network architectures and their applications
  publication-title: Neurocomputing
– start-page: 3320
  year: 2014
  end-page: 3328
  ident: bib0020
  article-title: How transferable are features in deep neural networks?
  publication-title: Proceedings of Advances in Neural Information Processing Systems 27
– start-page: 2499
  year: 2016
  end-page: 2503
  ident: bib0005
  article-title: Fast depth image denoising and enhancement using a deep convolutional network
  publication-title: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing
– volume: 27
  start-page: 15
  year: 2008
  end-page: 19
  ident: bib0017
  article-title: Edge preserving decompositions for multi-scale tone and detail manipulation
  publication-title: ACM Trans. Graph.
– volume: 35
  start-page: 1397
  year: 2013
  end-page: 1409
  ident: bib0019
  article-title: Guided image filtering
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 60
  start-page: 259
  year: 1992
  end-page: 268
  ident: bib0016
  article-title: Nonlinear total variation based noise removal algorithms
  publication-title: Phys. D: Nonlinear Phenom.
– volume: 228
  start-page: 165
  year: 2017
  end-page: 175
  ident: bib0002
  article-title: Photograph aesthetical evaluation and classification with deep convolutional neural networks
  publication-title: Neurocomputing
– volume: 61
  start-page: 650
  year: 2016
  end-page: 662
  ident: bib0014
  article-title: LLNet: a deep autoencoder approach to natural low-light image enhancement
  publication-title: Pattern Recognit.
– start-page: 1493
  year: 2013
  end-page: 1501
  ident: bib0012
  article-title: Adaptive multi-column deep neural networks with application to robust image denoising
  publication-title: Proceedings of Advances in Neural Information Processing Systems 26
– volume: 30
  start-page: 174
  year: 2010
  ident: bib0018
  article-title: Image smoothing via
  publication-title: ACM Trans. Graph.
– volume: 21
  start-page: 257
  year: 2002
  end-page: 266
  ident: bib0015
  article-title: Fast bilateral filtering for the display of high-dynamic-range images
  publication-title: ACM Trans. Graph.
– volume: 230
  start-page: 374
  year: 2017
  end-page: 381
  ident: bib0008
  article-title: Generalized extreme learning machine autoencoder and a new deep neural network
  publication-title: Neurocomputing
– volume: 39
  start-page: 298
  year: 2007
  end-page: 318
  ident: bib0021
  article-title: Optimally sparse multidimensional representation using shearlets
  publication-title: SIAM J. Math. Anal.
– volume: 18
  year: 2016
  ident: bib0023
  article-title: Adaptive enhancement for infrared image using shearlet frame
  publication-title: J. Opt.
– start-page: 3320
  year: 2014
  ident: 10.1016/j.neucom.2017.02.066_bib0020
  article-title: How transferable are features in deep neural networks?
– volume: 21
  start-page: 257
  issue: 3
  year: 2002
  ident: 10.1016/j.neucom.2017.02.066_bib0015
  article-title: Fast bilateral filtering for the display of high-dynamic-range images
  publication-title: ACM Trans. Graph.
  doi: 10.1145/566654.566574
– volume: 99
  start-page: 1
  year: 2016
  ident: 10.1016/j.neucom.2017.02.066_bib0003
  article-title: Deep multimodal distance metric learning using click constraints for image ranking
  publication-title: IEEE Trans. Cybern.
– volume: 72
  start-page: 341
  year: 1952
  ident: 10.1016/j.neucom.2017.02.066_bib0024
  article-title: A class of nonharmonic Fourier series
  publication-title: Trans. Am. Math. Soc.
  doi: 10.1090/S0002-9947-1952-0047179-6
– volume: 27
  start-page: 15
  issue: 3
  year: 2008
  ident: 10.1016/j.neucom.2017.02.066_bib0017
  article-title: Edge preserving decompositions for multi-scale tone and detail manipulation
  publication-title: ACM Trans. Graph.
  doi: 10.1145/1360612.1360666
– volume: vol. 9916
  year: 2016
  ident: 10.1016/j.neucom.2017.02.066_bib0006
  article-title: Fast and accurate image denoising via a deep convolutional-pairs network
– volume: 61
  start-page: 650
  year: 2016
  ident: 10.1016/j.neucom.2017.02.066_bib0014
  article-title: LLNet: a deep autoencoder approach to natural low-light image enhancement
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2016.06.008
– volume: 30
  start-page: 174
  issue: 6
  year: 2010
  ident: 10.1016/j.neucom.2017.02.066_bib0018
  article-title: Image smoothing via L0 gradient minimization
  publication-title: ACM Trans. Graph.
– volume: 228
  start-page: 165
  year: 2017
  ident: 10.1016/j.neucom.2017.02.066_bib0002
  article-title: Photograph aesthetical evaluation and classification with deep convolutional neural networks
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.08.098
– volume: 234
  start-page: 11
  year: 2017
  ident: 10.1016/j.neucom.2017.02.066_bib0001
  article-title: A survey of deep neural network architectures and their applications
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.12.038
– start-page: 2499
  year: 2016
  ident: 10.1016/j.neucom.2017.02.066_bib0005
  article-title: Fast depth image denoising and enhancement using a deep convolutional network
– volume: 74
  start-page: 44
  year: 2016
  ident: 10.1016/j.neucom.2017.02.066_bib0025
  article-title: Noise suppression and details enhancement for infrared image via novel prior
  publication-title: Infrared Phys. Technol.
  doi: 10.1016/j.infrared.2015.11.006
– start-page: 1493
  year: 2013
  ident: 10.1016/j.neucom.2017.02.066_bib0012
  article-title: Adaptive multi-column deep neural networks with application to robust image denoising
– volume: 24
  start-page: 5659
  issue: 12
  year: 2015
  ident: 10.1016/j.neucom.2017.02.066_bib0010
  article-title: Multimodal deep autoencoder for human pose recovery
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2015.2487860
– volume: 62
  start-page: 3742
  issue: 6
  year: 2015
  ident: 10.1016/j.neucom.2017.02.066_bib0011
  article-title: Image-based 3D human pose recovery by multi-view locality sensitive sparse retrieval
  publication-title: IEEE Trans. Ind. Electron.
– start-page: 1790
  year: 2014
  ident: 10.1016/j.neucom.2017.02.066_bib0013
  article-title: Deep convolutional neural network for image deconvolution
– volume: 230
  start-page: 374
  year: 2017
  ident: 10.1016/j.neucom.2017.02.066_bib0008
  article-title: Generalized extreme learning machine autoencoder and a new deep neural network
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2016.12.027
– volume: 25
  start-page: 3919
  issue: 8
  year: 2016
  ident: 10.1016/j.neucom.2017.02.066_bib0004
  article-title: DeepSaliency: multi-task deep neural network model for salient object detection
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2016.2579306
– volume: 18
  issue: 8
  year: 2016
  ident: 10.1016/j.neucom.2017.02.066_bib0023
  article-title: Adaptive enhancement for infrared image using shearlet frame
  publication-title: J. Opt.
  doi: 10.1088/2040-8978/18/8/085706
– volume: 204
  start-page: 41
  year: 2016
  ident: 10.1016/j.neucom.2017.02.066_bib0009
  article-title: Deep learning representation using autoencoder for 3D shape retrieval
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.08.127
– volume: 35
  start-page: 1397
  year: 2013
  ident: 10.1016/j.neucom.2017.02.066_bib0019
  article-title: Guided image filtering
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2012.213
– volume: 38
  start-page: 295
  issue: 2
  year: 2016
  ident: 10.1016/j.neucom.2017.02.066_bib0007
  article-title: Image super-resolution using deep convolutional networks
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2015.2439281
– volume: 39
  start-page: 298
  issue: 1
  year: 2007
  ident: 10.1016/j.neucom.2017.02.066_bib0021
  article-title: Optimally sparse multidimensional representation using shearlets
  publication-title: SIAM J. Math. Anal.
  doi: 10.1137/060649781
– volume: 25
  start-page: 25
  issue: 1
  year: 2008
  ident: 10.1016/j.neucom.2017.02.066_bib0022
  article-title: Sparse directional image representation using the discrete shearlet transforms
  publication-title: Appl. Comput. Harmonic Anal.
  doi: 10.1016/j.acha.2007.09.003
– volume: 60
  start-page: 259
  year: 1992
  ident: 10.1016/j.neucom.2017.02.066_bib0016
  article-title: Nonlinear total variation based noise removal algorithms
  publication-title: Phys. D: Nonlinear Phenom.
  doi: 10.1016/0167-2789(92)90242-F
SSID ssj0017129
Score 2.3686154
Snippet •We use deep learning for image processing by extracting image feature.•The extraction has good performance in noisy or low-light circumstance.•We optimize TV...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 12
SubjectTerms Deep learning
Image enhancement
Image processing
Pattern recognition
Spatial filter
Title Low-level structure feature extraction for image processing via stacked sparse denoising autoencoder
URI https://dx.doi.org/10.1016/j.neucom.2017.02.066
Volume 243
WOSCitedRecordID wos000399511900002&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
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-8286
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017129
  issn: 0925-2312
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1ba9swFBYh3cNedh9rd0EPewselnyR_RhGSzdKGbQbYS9GtqQtIXVCGmftv9hP3jmSfGEtu8FeTFAsW-h8Oj76dC6EvE7x9M_ANpVpKYPYJCyQJoblLgyYr1yWqfW2-HQiTk-z2Sz_MBp9b2NhdktR19nVVb7-r6KGNhA2hs7-hbi7h0ID_AahwxXEDtc_EvzJ6luwRFegicsNiycERtv8nRPQxBtfHBzdC-cX6LGzdrECyBns5hLJBVjZagKqZnOJUVX1am7_lM12hWkvlXfoXbSJnxp4gC0O4WmH6QVmX1AItY5mOHJE6-cGM3P0zLxVec11D9Fj7ZmC66ZvPPuKFba_uNiiIU_BrFMd73mKmwE0joXkSQAmplPI2ungTHAb3T5U0jyOBmq2vd_p3PDWT4FjJRZvat2gXxAOyWZnTX_KvG2_5Wc4EBwHA40X5RgRusdFkmdjsjd9dzh7351MCcZd_kY_8DYc0_oM3nzX7ebOwIQ5f0Du-b0HnTrMPCQjXT8i99u6HtSr-cdEdRCiHYSohxDtIUQBQtRCiPYQogAh6iFEHYRoByE6gNAT8vHo8PztceCrcQQVbCu3QVnxUAnDSrDqytDwpGJGSl7qWKYqB7O_SmWoYEdRKVMZpvKMxSzXZSq1jhnX0VMyrle1fkYozxNhjC7DSMWxlDozYZmoRMWiYqVSyT6J2kkrKp-qHiumLIvWJ3FRuKkucKqLkBcw1fsk6HqtXaqW39wvWnkU3tx0ZmQBEPplz4N_7vmc3O3XxgsyBiHql-ROtdvOLzevPNZ-AJf-q5s
linkProvider Elsevier
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%3Ajournal&rft.genre=article&rft.atitle=Low-level+structure+feature+extraction+for+image+processing+via+stacked+sparse+denoising+autoencoder&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Fan%2C+Zunlin&rft.au=Bi%2C+Duyan&rft.au=He%2C+Linyuan&rft.au=Shiping%2C+Ma&rft.date=2017-06-21&rft.pub=Elsevier+B.V&rft.issn=0925-2312&rft.eissn=1872-8286&rft.volume=243&rft.spage=12&rft.epage=20&rft_id=info:doi/10.1016%2Fj.neucom.2017.02.066&rft.externalDocID=S0925231217303909
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon