CMV2U‐Net: A U‐shaped network with edge‐weighted features for detecting and localizing image splicing

The practice of cutting and pasting portions of one image into another, known as “image splicing,” is commonplace in the field of image manipulation. Image splicing detection using deep learning has been a hot research topic for the past few years. However, there are two problems with the way deep l...

Full description

Saved in:
Bibliographic Details
Published in:Journal of forensic sciences Vol. 70; no. 3; pp. 1026 - 1043
Main Authors: Akram, Arslan, Jaffar, Muhammad Arfan, Rashid, Javed, Boulaaras, Salah Mahmoud, Faheem, Muhammad
Format: Journal Article
Language:English
Published: United States Wiley Subscription Services, Inc 01.05.2025
John Wiley and Sons Inc
Subjects:
ISSN:0022-1198, 1556-4029, 1556-4029
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The practice of cutting and pasting portions of one image into another, known as “image splicing,” is commonplace in the field of image manipulation. Image splicing detection using deep learning has been a hot research topic for the past few years. However, there are two problems with the way deep learning is currently implemented: first, it is not good enough for feature fusion, and second, it uses only simple models for feature extraction and encoding, which makes the models vulnerable to overfitting. To tackle these problems, this research proposes CMV2U‐Net, an edge‐weighted U‐shaped network‐based image splicing forgery localization approach. An initial step is the development of a feature extraction module that can process two streams of input images simultaneously, allowing for the simultaneous extraction of semantically connected and semantically agnostic features. One characteristic is that a hierarchical fusion approach has been devised to prevent data loss in shallow features that are either semantically related or semantically irrelevant. This approach implements a channel attention mechanism to monitor manipulation trajectories involving multiple levels. Extensive trials on numerous public datasets prove that CMV2U‐Net provides high AUC and F1 in localizing tampered regions, outperforming state‐of‐the‐art techniques. Noise, Gaussian blur, and JPEG compression are post‐processing threats that CMV2U‐Net has successfully resisted.
AbstractList The practice of cutting and pasting portions of one image into another, known as "image splicing," is commonplace in the field of image manipulation. Image splicing detection using deep learning has been a hot research topic for the past few years. However, there are two problems with the way deep learning is currently implemented: first, it is not good enough for feature fusion, and second, it uses only simple models for feature extraction and encoding, which makes the models vulnerable to overfitting. To tackle these problems, this research proposes CMV2U-Net, an edge-weighted U-shaped network-based image splicing forgery localization approach. An initial step is the development of a feature extraction module that can process two streams of input images simultaneously, allowing for the simultaneous extraction of semantically connected and semantically agnostic features. One characteristic is that a hierarchical fusion approach has been devised to prevent data loss in shallow features that are either semantically related or semantically irrelevant. This approach implements a channel attention mechanism to monitor manipulation trajectories involving multiple levels. Extensive trials on numerous public datasets prove that CMV2U-Net provides high AUC and F1 in localizing tampered regions, outperforming state-of-the-art techniques. Noise, Gaussian blur, and JPEG compression are post-processing threats that CMV2U-Net has successfully resisted.The practice of cutting and pasting portions of one image into another, known as "image splicing," is commonplace in the field of image manipulation. Image splicing detection using deep learning has been a hot research topic for the past few years. However, there are two problems with the way deep learning is currently implemented: first, it is not good enough for feature fusion, and second, it uses only simple models for feature extraction and encoding, which makes the models vulnerable to overfitting. To tackle these problems, this research proposes CMV2U-Net, an edge-weighted U-shaped network-based image splicing forgery localization approach. An initial step is the development of a feature extraction module that can process two streams of input images simultaneously, allowing for the simultaneous extraction of semantically connected and semantically agnostic features. One characteristic is that a hierarchical fusion approach has been devised to prevent data loss in shallow features that are either semantically related or semantically irrelevant. This approach implements a channel attention mechanism to monitor manipulation trajectories involving multiple levels. Extensive trials on numerous public datasets prove that CMV2U-Net provides high AUC and F1 in localizing tampered regions, outperforming state-of-the-art techniques. Noise, Gaussian blur, and JPEG compression are post-processing threats that CMV2U-Net has successfully resisted.
The practice of cutting and pasting portions of one image into another, known as “image splicing,” is commonplace in the field of image manipulation. Image splicing detection using deep learning has been a hot research topic for the past few years. However, there are two problems with the way deep learning is currently implemented: first, it is not good enough for feature fusion, and second, it uses only simple models for feature extraction and encoding, which makes the models vulnerable to overfitting. To tackle these problems, this research proposes CMV2U‐Net, an edge‐weighted U‐shaped network‐based image splicing forgery localization approach. An initial step is the development of a feature extraction module that can process two streams of input images simultaneously, allowing for the simultaneous extraction of semantically connected and semantically agnostic features. One characteristic is that a hierarchical fusion approach has been devised to prevent data loss in shallow features that are either semantically related or semantically irrelevant. This approach implements a channel attention mechanism to monitor manipulation trajectories involving multiple levels. Extensive trials on numerous public datasets prove that CMV2U‐Net provides high AUC and F1 in localizing tampered regions, outperforming state‐of‐the‐art techniques. Noise, Gaussian blur, and JPEG compression are post‐processing threats that CMV2U‐Net has successfully resisted.
The practice of cutting and pasting portions of one image into another, known as “image splicing,” is commonplace in the field of image manipulation. Image splicing detection using deep learning has been a hot research topic for the past few years. However, there are two problems with the way deep learning is currently implemented: first, it is not good enough for feature fusion, and second, it uses only simple models for feature extraction and encoding, which makes the models vulnerable to overfitting. To tackle these problems, this research proposes CMV2U‐Net, an edge‐weighted U‐shaped network‐based image splicing forgery localization approach. An initial step is the development of a feature extraction module that can process two streams of input images simultaneously, allowing for the simultaneous extraction of semantically connected and semantically agnostic features. One characteristic is that a hierarchical fusion approach has been devised to prevent data loss in shallow features that are either semantically related or semantically irrelevant. This approach implements a channel attention mechanism to monitor manipulation trajectories involving multiple levels. Extensive trials on numerous public datasets prove that CMV2U‐Net provides high AUC and F 1 in localizing tampered regions, outperforming state‐of‐the‐art techniques. Noise, Gaussian blur, and JPEG compression are post‐processing threats that CMV2U‐Net has successfully resisted.
The practice of cutting and pasting portions of one image into another, known as "image splicing," is commonplace in the field of image manipulation. Image splicing detection using deep learning has been a hot research topic for the past few years. However, there are two problems with the way deep learning is currently implemented: first, it is not good enough for feature fusion, and second, it uses only simple models for feature extraction and encoding, which makes the models vulnerable to overfitting. To tackle these problems, this research proposes CMV2U-Net, an edge-weighted U-shaped network-based image splicing forgery localization approach. An initial step is the development of a feature extraction module that can process two streams of input images simultaneously, allowing for the simultaneous extraction of semantically connected and semantically agnostic features. One characteristic is that a hierarchical fusion approach has been devised to prevent data loss in shallow features that are either semantically related or semantically irrelevant. This approach implements a channel attention mechanism to monitor manipulation trajectories involving multiple levels. Extensive trials on numerous public datasets prove that CMV2U-Net provides high AUC and F in localizing tampered regions, outperforming state-of-the-art techniques. Noise, Gaussian blur, and JPEG compression are post-processing threats that CMV2U-Net has successfully resisted.
The practice of cutting and pasting portions of one image into another, known as “image splicing,” is commonplace in the field of image manipulation. Image splicing detection using deep learning has been a hot research topic for the past few years. However, there are two problems with the way deep learning is currently implemented: first, it is not good enough for feature fusion, and second, it uses only simple models for feature extraction and encoding, which makes the models vulnerable to overfitting. To tackle these problems, this research proposes CMV2U‐Net, an edge‐weighted U‐shaped network‐based image splicing forgery localization approach. An initial step is the development of a feature extraction module that can process two streams of input images simultaneously, allowing for the simultaneous extraction of semantically connected and semantically agnostic features. One characteristic is that a hierarchical fusion approach has been devised to prevent data loss in shallow features that are either semantically related or semantically irrelevant. This approach implements a channel attention mechanism to monitor manipulation trajectories involving multiple levels. Extensive trials on numerous public datasets prove that CMV2U‐Net provides high AUC and F 1 in localizing tampered regions, outperforming state‐of‐the‐art techniques. Noise, Gaussian blur, and JPEG compression are post‐processing threats that CMV2U‐Net has successfully resisted.
Author Faheem, Muhammad
Akram, Arslan
Jaffar, Muhammad Arfan
Rashid, Javed
Boulaaras, Salah Mahmoud
AuthorAffiliation 4 VTT Technical Research Centre of Finland Espoo Finland
3 Department of Mathematics, College of Science Qassim University Buraydah Saudi Arabia
1 Faculty of Computer Science and Information Technology The Superior University Lahore Pakistan
2 Information Technology Services University of Okara Okara Pakistan
AuthorAffiliation_xml – name: 3 Department of Mathematics, College of Science Qassim University Buraydah Saudi Arabia
– name: 4 VTT Technical Research Centre of Finland Espoo Finland
– name: 2 Information Technology Services University of Okara Okara Pakistan
– name: 1 Faculty of Computer Science and Information Technology The Superior University Lahore Pakistan
Author_xml – sequence: 1
  givenname: Arslan
  surname: Akram
  fullname: Akram, Arslan
  organization: The Superior University
– sequence: 2
  givenname: Muhammad Arfan
  surname: Jaffar
  fullname: Jaffar, Muhammad Arfan
  organization: The Superior University
– sequence: 3
  givenname: Javed
  orcidid: 0000-0003-3416-9720
  surname: Rashid
  fullname: Rashid, Javed
  organization: University of Okara
– sequence: 4
  givenname: Salah Mahmoud
  surname: Boulaaras
  fullname: Boulaaras, Salah Mahmoud
  organization: Qassim University
– sequence: 5
  givenname: Muhammad
  surname: Faheem
  fullname: Faheem, Muhammad
  email: muhammad.faheem@vtt.fi
  organization: VTT Technical Research Centre of Finland
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40177991$$D View this record in MEDLINE/PubMed
BookMark eNqFUstu1DAUtVARnQ6s2SFLbNik9SNxHDaoGtECKnRD2VqOc5Nxm4mntsOorPoJfCNfgsNMK6gEeOPHefhenXuA9gY3AELPKTmkaR3RohBZTlh1WBLC-SM0u3_ZQzNCGMsoreQ-OgjhkhAiqKBP0H5OaFlWFZ2hq8XHL-zix-33TxBf42M8HcNSr6HBA8SN81d4Y-MSQ9NBgjZgu2VMYAs6jh4Cbp3HDUQw0Q4d1kODe2d0b79NV7vSHeCw7q1J16focav7AM92-xxdnLz9vHiXnZ2fvl8cn2UmryTPWJuzqmi5FlIWrTRNXXNpBC85bdrSSGNqSorUCQgh87otc12LvBYJ0kQz4HP0Zuu7HusVNAaG6HWv1j6V42-U01b9iQx2qTr3VVFGC87yMjm82jl4dz1CiGplg4G-1wO4MShOZVFKUSX6HL18QL10ox9Sf4ozVhFGZQrmX6yUj6zIlN8cvfi98PuK7-JKhGJLMN6F4KFVxkYdrZv6sL2iRE1joaYhUNMQqF9jkXRHD3R31n9X7H7a2B5u_kdXH07Ot7qfHpzJvA
CitedBy_id crossref_primary_10_1371_journal_pone_0330632
crossref_primary_10_1007_s12672_025_03501_3
crossref_primary_10_1007_s13369_025_10528_9
Cites_doi 10.1111/srt.13524
10.3390/jimaging7040069
10.1155/2022/1090307
10.1007/978-3-030-01252-6_7
10.1109/TIFS.2022.3152362
10.3390/electronics11101607
10.1049/cje.2021.08.004
10.1016/j.ins.2022.08.005
10.1007/s11042‐022‐13312‐1
10.1117/1.JEI.32.5.053012
10.1016/j.dib.2024.110461
10.1016/j.compag.2022.107144
10.1117/1.JEI.32.4.043015
10.1109/TIM.2023.3300434
10.1109/LSP.2023.3279018
10.1007/s10044‐024‐01305‐9
10.1007/978-3-031-51583-5_11
10.1109/ACCESS.2022.3182024
10.1007/s11760‐024‐02997‐6
10.3390/a16090399
10.1007/s11042‐020‐10158‐3
10.1109/WACV48630.2021.00042
10.1007/s10462‐021‐10046‐8
10.1007/s00521‐021‐06329‐4
10.1007/s00530‐021‐00801‐w
10.1016/j.sigpro.2021.108051
10.1109/TIFS.2023.3346312
10.1007/s11042‐023‐16705‐y
10.1007/s11042‐023‐17914‐1
10.1049/2024/9929900
10.1002/int.22939
10.1145/3633203
10.1109/TPAMI.2025.3541028
10.1049/gtd2.12997
10.23919/EUSIPCO.2019.8903181
10.1016/j.dsp.2023.104005
10.1016/j.patcog.2024.110727
10.1049/ipr2.12763
10.3390/electronics11162621
10.1109/ChinaSIP.2013.6625374
10.3390/jimaging10010004
10.1007/s11042‐020‐09816‐3
10.1002/spy2.500
10.1016/j.eswa.2024.124975
10.32604/cmc.2023.041074
10.1109/TIFS.2022.3144878
ContentType Journal Article
Copyright 2025 American Academy of Forensic Sciences.
2025 American Academy of Forensic Sciences
2025. This work is published under Creative Commons Attribution License~https://creativecommons.org/licenses/by/3.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
2025 The Author(s). published by Wiley Periodicals LLC on behalf of American Academy of Forensic Sciences.
Copyright_xml – notice: 2025 American Academy of Forensic Sciences.
– notice: 2025 American Academy of Forensic Sciences
– notice: 2025. This work is published under Creative Commons Attribution License~https://creativecommons.org/licenses/by/3.0/ (the "License"). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: 2025 The Author(s). published by Wiley Periodicals LLC on behalf of American Academy of Forensic Sciences.
DBID AAYXX
CITATION
NPM
K7.
K9.
NAPCQ
7X8
5PM
DOI 10.1111/1556-4029.70033
DatabaseName CrossRef
PubMed
ProQuest Criminal Justice (Alumni)
ProQuest Health & Medical Complete (Alumni)
Nursing & Allied Health Premium
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
PubMed
ProQuest Health & Medical Complete (Alumni)
Nursing & Allied Health Premium
ProQuest Criminal Justice (Alumni)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic


PubMed
ProQuest Health & Medical Complete (Alumni)
ProQuest Health & Medical Complete (Alumni)
CrossRef
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Public Health
DocumentTitleAlternate Akram et al
EISSN 1556-4029
EndPage 1043
ExternalDocumentID PMC12153247
1011111556402970033
40177991
10_1111_1556_4029_70033
JFO70033
Genre researchArticle
Journal Article
GroupedDBID ---
.3N
.55
.GA
.GJ
.Y3
05W
0R~
10A
186
1KJ
1OC
1UQ
1US
29K
31~
33P
36Y
3O-
3SF
4.4
41~
50Y
50Z
51W
51X
52M
52N
52O
52P
52R
52S
52T
52U
52V
52W
52X
53G
5GY
5HH
5LA
5RE
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
85S
8UM
930
A01
A03
AAESR
AAEVG
AAHHS
AAHQN
AAIPD
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABEML
ABGFU
ABIVO
ABJNI
ABLJU
ABOCM
ABPVW
ABQWH
ABXGK
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACFBH
ACGFO
ACGFS
ACGOF
ACIWK
ACMXC
ACPOU
ACRPL
ACSCC
ACXBN
ACXQS
ACYXJ
ADBBV
ADBTR
ADEOM
ADIZJ
ADKYN
ADMGS
ADMHG
ADNMO
ADOZA
ADXAS
ADZMN
AEEZP
AEIGN
AEIMD
AENEX
AEQDE
AEUYR
AFBPY
AFFPM
AFGKR
AFHKK
AFWVQ
AFZJQ
AGHNM
AGQPQ
AGYGG
AHBTC
AI.
AIACR
AIAGR
AIDAL
AITYG
AIURR
AIWBW
AJBDE
AJUXI
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ASPBG
ATUGU
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMXJE
BROTX
BRXPI
BY8
C45
CAG
COF
CS3
D-6
D-7
D-E
D-F
D-I
D0L
DCZOG
DPXWK
DR2
DRFUL
DRMAN
DRSTM
DU5
EBD
EBS
EJD
EMOBN
EV9
EX3
EYL
F00
F01
F04
F5P
FEDTE
FUBAC
G-S
G.N
GODZA
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
H~9
IX1
J0M
K48
KBYEO
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MQT
MRFUL
MRMAN
MRSTM
MSFUL
MSMAN
MSSTM
MVM
MXFUL
MXMAN
MXSTM
N04
N05
N9A
NF~
NHB
NP-
O66
O9-
OHT
OIG
OVD
P2P
P2W
P2X
P2Z
P4B
P4D
PQQKQ
Q.N
Q11
QB0
QJJ
R.K
RNS
ROL
RSM
RX1
SJN
SUPJJ
SV3
TEORI
TN5
TWZ
UB1
UCJ
ULE
URZ
V8K
VH1
W8V
W99
WBFHL
WBKPD
WH7
WHG
WIH
WIJ
WIK
WOHZO
WOW
WQJ
WXI
WXSBR
WYISQ
X7M
XG1
YR5
YRY
YYQ
YZZ
ZCG
ZGI
ZHY
ZKG
ZUP
ZXP
ZZTAW
~02
~IA
~WT
AAMMB
AAYXX
AEFGJ
AGXDD
AIDQK
AIDYY
CITATION
O8X
NPM
K7.
K9.
NAPCQ
7X8
5PM
ID FETCH-LOGICAL-c4983-2f4295f3a6885f8cdbb38c63731df7c8ccb105616e6684bf74ab64b67c8a0a2e3
IEDL.DBID DRFUL
ISICitedReferencesCount 6
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001480529500035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0022-1198
1556-4029
IngestDate Tue Nov 04 02:01:57 EST 2025
Fri Jul 11 18:50:01 EDT 2025
Thu Nov 20 01:06:40 EST 2025
Thu Nov 20 01:00:40 EST 2025
Sat Jun 14 01:31:03 EDT 2025
Tue Nov 18 22:38:15 EST 2025
Sat Nov 29 07:48:34 EST 2025
Fri May 02 10:26:05 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 3
Keywords digital forensics
image authentication
image splicing detection
feature fusion
image forgery localization
U‐shaped network
Language English
License 2025 American Academy of Forensic Sciences.
This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c4983-2f4295f3a6885f8cdbb38c63731df7c8ccb105616e6684bf74ab64b67c8a0a2e3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0003-3416-9720
OpenAccessLink https://pubmed.ncbi.nlm.nih.gov/PMC12153247
PMID 40177991
PQID 3198890700
PQPubID 49292
PageCount 18
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_12153247
proquest_miscellaneous_3185786915
proquest_journals_3229021803
proquest_journals_3198890700
pubmed_primary_40177991
crossref_citationtrail_10_1111_1556_4029_70033
crossref_primary_10_1111_1556_4029_70033
wiley_primary_10_1111_1556_4029_70033_JFO70033
PublicationCentury 2000
PublicationDate May 2025
PublicationDateYYYYMMDD 2025-05-01
PublicationDate_xml – month: 05
  year: 2025
  text: May 2025
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Colorado Springs
– name: Hoboken
PublicationTitle Journal of forensic sciences
PublicationTitleAlternate J Forensic Sci
PublicationYear 2025
Publisher Wiley Subscription Services, Inc
John Wiley and Sons Inc
Publisher_xml – name: Wiley Subscription Services, Inc
– name: John Wiley and Sons Inc
References 2022; 199
2019; 8
2023; 32
2021; 7
2023; 30
2023; 35
2023; 17
2023; 16
2025; 8
2023; 19
2021; 183
2024; 10
2024; 54
2024; 78
2024
2021; 30
2024; 17
2023; 82
2022; 610
2024; 18
2022; 28
2022; 2022
2023
2022; 81
2023; 29
2021
2024; 83
2024; 2024
2019
2018
2024; 20
2022; 37
2023; 136
2024; 155
2016
2022; 10
2022; 55
2013
2022; 11
2024; 257
2024; 27
2023; 72
2022; 17
2021; 80
e_1_2_10_23_1
e_1_2_10_46_1
e_1_2_10_21_1
e_1_2_10_44_1
e_1_2_10_40_1
IFS T (e_1_2_10_41_1) 2019; 8
e_1_2_10_2_1
e_1_2_10_4_1
e_1_2_10_18_1
e_1_2_10_53_1
e_1_2_10_6_1
e_1_2_10_16_1
e_1_2_10_39_1
e_1_2_10_55_1
e_1_2_10_8_1
e_1_2_10_14_1
e_1_2_10_37_1
e_1_2_10_13_1
e_1_2_10_34_1
e_1_2_10_11_1
e_1_2_10_32_1
e_1_2_10_30_1
e_1_2_10_51_1
Chen X (e_1_2_10_42_1) 2021
e_1_2_10_29_1
e_1_2_10_27_1
e_1_2_10_25_1
e_1_2_10_48_1
e_1_2_10_24_1
e_1_2_10_45_1
e_1_2_10_22_1
e_1_2_10_43_1
e_1_2_10_20_1
Guo X (e_1_2_10_26_1) 2023
e_1_2_10_52_1
e_1_2_10_3_1
e_1_2_10_19_1
e_1_2_10_54_1
e_1_2_10_5_1
e_1_2_10_17_1
e_1_2_10_38_1
e_1_2_10_7_1
e_1_2_10_15_1
e_1_2_10_36_1
e_1_2_10_12_1
e_1_2_10_35_1
e_1_2_10_9_1
e_1_2_10_10_1
e_1_2_10_33_1
e_1_2_10_31_1
e_1_2_10_50_1
e_1_2_10_28_1
Wu Y (e_1_2_10_49_1) 2019
e_1_2_10_47_1
References_xml – volume: 17
  start-page: 819
  year: 2022
  end-page: 834
  article-title: Self‐adversarial training incorporating forgery attention for image forgery localization
  publication-title: IEEE Trans Inf Forensics Secur
– volume: 28
  start-page: 363
  issue: 2
  year: 2022
  end-page: 374
  article-title: Hybrid features and semantic reinforcement network for image forgery detection
  publication-title: Multimed Syst
– volume: 18
  start-page: 3341
  issue: 4
  year: 2024
  end-page: 3352
  article-title: Toward effective image forensics via a novel computationally efficient framework and a new image splice dataset
  publication-title: Signal Image Video Process
– volume: 80
  start-page: 3571
  issue: 3
  year: 2021
  end-page: 3599
  article-title: Copy move and splicing forgery detection using deep convolution neural network, and semantic segmentation
  publication-title: Multimed Tools Appl
– volume: 27
  issue: 3
  year: 2024
  article-title: MSU‐Net: the multi‐scale supervised U‐Net for image splicing forgery localization
  publication-title: Pattern Anal Applic
– start-page: 14185
  year: 2021
  end-page: 14193
– volume: 155
  year: 2024
  article-title: D‐Net: a dual‐encoder network for image splicing forgery detection and localization
  publication-title: Pattern Recogn
– volume: 11
  issue: 10
  year: 2022
  article-title: A novel deep learning architecture with multi‐scale guided learning for image splicing localization
  publication-title: Electronics
– volume: 82
  start-page: 1873
  issue: 2
  year: 2023
  end-page: 1904
  article-title: A comprehensive survey on image authentication for tamper detection with localization
  publication-title: Multimed Tools Appl
– start-page: 9543
  year: 2019
  end-page: 9552
– volume: 30
  start-page: 1069
  issue: 6
  year: 2021
  end-page: 1079
  article-title: A quaternion two‐stream R‐CNN network for pixel‐level color image splicing localization
  publication-title: Chin J Electron
– volume: 83
  start-page: 31759
  issue: 11
  year: 2024
  end-page: 31782
  article-title: Image splicing manipulation location by multi‐scale dual‐channel supervision
  publication-title: Multimed Tools Appl
– volume: 16
  issue: 9
  year: 2023
  article-title: Detecting image forgery over social media using U‐NET with grasshopper optimization
  publication-title: Algorithms
– start-page: 1
  year: 2019
  end-page: 5
– volume: 11
  issue: 16
  year: 2022
  article-title: A multiscale fusion lightweight image‐splicing tamper‐detection model
  publication-title: Electronics
– volume: 19
  start-page: 2143
  issue: 1
  year: 2023
  end-page: 2156
  article-title: Attacking image splicing detection and localization algorithms using synthetic traces
  publication-title: IEEE Trans Inf Forensics Secur
– start-page: 101
  year: 2018
  end-page: 117
– volume: 10
  issue: 1
  year: 2024
  article-title: Harmonizing image forgery detection & localization: fusion of complementary approaches
  publication-title: J Imaging
– volume: 54
  issue: 11
  year: 2024
  article-title: Multilayer cyberattacks identification and classification using machine learning in internet of blockchain (IoBC)‐based energy networks
  publication-title: Data Brief
– volume: 78
  start-page: 145
  issue: 1
  year: 2024
  end-page: 166
  article-title: Weber law based approach for multi‐class image forgery detection
  publication-title: Comput Mater Contin
– start-page: 185
  year: 2024
  end-page: 196
– volume: 17
  start-page: 1883
  issue: 6
  year: 2023
  end-page: 1892
  article-title: A lightweight image splicing tampering localization method based on MobileNetV2 and SRM
  publication-title: IET Image Process
– volume: 20
  issue: 11
  year: 2024
  article-title: A comprehensive survey on methods for image integrity
  publication-title: ACM Trans Multimed Comput Commun Appl
– volume: 610
  start-page: 73
  year: 2022
  end-page: 89
  article-title: DS‐UNet: a dual streams UNet for refined image forgery localization
  publication-title: Inform Sci
– volume: 7
  issue: 4
  year: 2021
  article-title: A comprehensive review of deep‐learning‐based methods for image forensics
  publication-title: J Imaging
– volume: 2022
  issue: 1
  year: 2022
  article-title: Image forgery detection using tamper‐guided dual self‐attention network with multiresolution hybrid feature
  publication-title: Secur Commun Netw
– volume: 35
  start-page: 5015
  issue: 7
  year: 2023
  end-page: 5031
  article-title: DCU‐Net: a dual‐channel U‐shaped network for image splicing forgery detection
  publication-title: Neural Comput & Applic
– volume: 136
  year: 2023
  article-title: Feature enhancement and supervised contrastive learning for image splicing forgery detection
  publication-title: Digit Signal Process
– article-title: Pixel‐inconsistency modeling for image manipulation localization
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 30
  start-page: 623
  year: 2023
  end-page: 627
  article-title: TBFormer: two‐branch transformer for image forgery localization
  publication-title: IEEE Signal Process Lett
– start-page: 3155
  year: 2023
  end-page: 3165
– volume: 17
  start-page: 443
  year: 2022
  end-page: 456
  article-title: Robust image forgery detection against transmission over online social networks
  publication-title: IEEE Trans Inf Forensics Secur
– volume: 29
  issue: 11
  year: 2023
  article-title: Segmentation and classification of skin lesions using hybrid deep learning method in the Internet of Medical Things
  publication-title: Skin Res Technol
– volume: 257
  year: 2024
  article-title: Multi‐scale noise‐guided progressive network for image splicing detection and localization
  publication-title: Expert Syst Appl
– start-page: 422
  year: 2013
  end-page: 426
– volume: 8
  start-page: 310
  issue: 4
  year: 2019
  end-page: 318
  article-title: IEEE IFS‐TC image forensics challenge database
  publication-title: IEEE Signal Process
– volume: 183
  year: 2021
  article-title: Multi‐semantic CRF‐based attention model for image forgery detection and localization
  publication-title: Signal Process
– year: 2016
– volume: 37
  start-page: 8291
  issue: 11
  year: 2022
  end-page: 8308
  article-title: Image splicing forgery detection by combining synthetic adversarial networks and hybrid dense U‐net based on multiple spaces
  publication-title: Int J Intell Syst
– volume: 10
  start-page: 62751
  year: 2022
  end-page: 62762
  article-title: FBI‐Net: frequency‐based image forgery localization via multitask learning with self‐attention
  publication-title: IEEE Access
– volume: 81
  start-page: 22611
  issue: 16
  year: 2022
  end-page: 22628
  article-title: Encoder‐decoder based convolutional neural networks for image forgery detection
  publication-title: Multimed Tools Appl
– start-page: 375
  year: 2021
  end-page: 384
– volume: 32
  issue: 5
  year: 2023
  article-title: Dual encoder network with efficient channel attention refinement module for image splicing forgery detection
  publication-title: J Electron Imaging
– volume: 8
  issue: 1
  year: 2025
  article-title: Hybrid neural network methods for the detection of credit card fraud
  publication-title: Secur Priv
– volume: 199
  year: 2022
  article-title: Crop pests and diseases recognition using DANet with TLDP
  publication-title: Comput Electron Agric
– volume: 2024
  issue: 1
  year: 2024
  article-title: CFA‐based splicing forgery localization method via statistical analysis
  publication-title: IET Signal Process
– volume: 32
  issue: 4
  year: 2023
  article-title: VGG16Unet: effective passive model for image splicing forgery localization
  publication-title: J Electron Imaging
– volume: 17
  start-page: 4794
  issue: 21
  year: 2024
  end-page: 4809
  article-title: Using machine learning ensemble method for detection of energy theft in smart meters
  publication-title: IET Gener Transm Distrib
– year: 2023
– volume: 83
  start-page: 62721
  issue: 23
  year: 2024
  end-page: 62739
  article-title: FP‐Net: frequency‐perception network with adversarial training for image manipulation localization
  publication-title: Multimed Tools Appl
– volume: 55
  start-page: 1629
  issue: 3
  year: 2022
  end-page: 1679
  article-title: Passive image forensics using universal techniques: review
  publication-title: Artif Intell Rev
– volume: 72
  issue: 1
  year: 2023
  article-title: Multi‐scale attention network for detection and localization of image splicing forgery
  publication-title: IEEE Trans Instrum Meas
– ident: e_1_2_10_54_1
  doi: 10.1111/srt.13524
– ident: e_1_2_10_5_1
  doi: 10.3390/jimaging7040069
– start-page: 3155
  volume-title: Proceedings of the 2023 IEEE/CVF conference on computer vision and pattern recognition (CVPR); 2023 Jun 18–22; Vancouver, Canada
  year: 2023
  ident: e_1_2_10_26_1
– ident: e_1_2_10_21_1
  doi: 10.1155/2022/1090307
– ident: e_1_2_10_14_1
  doi: 10.1007/978-3-030-01252-6_7
– ident: e_1_2_10_44_1
  doi: 10.1109/TIFS.2022.3152362
– ident: e_1_2_10_24_1
  doi: 10.3390/electronics11101607
– ident: e_1_2_10_23_1
  doi: 10.1049/cje.2021.08.004
– ident: e_1_2_10_36_1
  doi: 10.1016/j.ins.2022.08.005
– ident: e_1_2_10_7_1
  doi: 10.1007/s11042‐022‐13312‐1
– ident: e_1_2_10_20_1
  doi: 10.1117/1.JEI.32.5.053012
– volume: 8
  start-page: 310
  issue: 4
  year: 2019
  ident: e_1_2_10_41_1
  article-title: IEEE IFS‐TC image forensics challenge database
  publication-title: IEEE Signal Process
– ident: e_1_2_10_52_1
  doi: 10.1016/j.dib.2024.110461
– ident: e_1_2_10_37_1
  doi: 10.1016/j.compag.2022.107144
– ident: e_1_2_10_19_1
  doi: 10.1117/1.JEI.32.4.043015
– ident: e_1_2_10_11_1
  doi: 10.1109/TIM.2023.3300434
– ident: e_1_2_10_17_1
  doi: 10.1109/LSP.2023.3279018
– ident: e_1_2_10_47_1
  doi: 10.1007/s10044‐024‐01305‐9
– ident: e_1_2_10_9_1
  doi: 10.1007/978-3-031-51583-5_11
– ident: e_1_2_10_25_1
  doi: 10.1109/ACCESS.2022.3182024
– ident: e_1_2_10_18_1
– ident: e_1_2_10_51_1
  doi: 10.1007/s11760‐024‐02997‐6
– ident: e_1_2_10_22_1
  doi: 10.3390/a16090399
– ident: e_1_2_10_33_1
  doi: 10.1007/s11042‐020‐10158‐3
– ident: e_1_2_10_28_1
  doi: 10.1109/WACV48630.2021.00042
– ident: e_1_2_10_2_1
  doi: 10.1007/s10462‐021‐10046‐8
– ident: e_1_2_10_30_1
  doi: 10.1007/s00521‐021‐06329‐4
– ident: e_1_2_10_39_1
– ident: e_1_2_10_31_1
  doi: 10.1007/s00530‐021‐00801‐w
– ident: e_1_2_10_29_1
  doi: 10.1016/j.sigpro.2021.108051
– ident: e_1_2_10_38_1
– start-page: 14185
  volume-title: Proceedings of the 2021 IEEE/CVF international conference on computer vision (ICCV); 2021 oct 11–17; Montreal, BC, Canada
  year: 2021
  ident: e_1_2_10_42_1
– ident: e_1_2_10_16_1
  doi: 10.1109/TIFS.2023.3346312
– ident: e_1_2_10_40_1
– ident: e_1_2_10_4_1
  doi: 10.1007/s11042‐023‐16705‐y
– start-page: 9543
  volume-title: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR); 2019 June 15–20; Long Beach, CA
  year: 2019
  ident: e_1_2_10_49_1
– ident: e_1_2_10_48_1
  doi: 10.1007/s11042‐023‐17914‐1
– ident: e_1_2_10_8_1
  doi: 10.1049/2024/9929900
– ident: e_1_2_10_43_1
  doi: 10.1002/int.22939
– ident: e_1_2_10_3_1
  doi: 10.1145/3633203
– ident: e_1_2_10_50_1
  doi: 10.1109/TPAMI.2025.3541028
– ident: e_1_2_10_53_1
  doi: 10.1049/gtd2.12997
– ident: e_1_2_10_13_1
  doi: 10.23919/EUSIPCO.2019.8903181
– ident: e_1_2_10_46_1
  doi: 10.1016/j.dsp.2023.104005
– ident: e_1_2_10_10_1
  doi: 10.1016/j.patcog.2024.110727
– ident: e_1_2_10_12_1
  doi: 10.1049/ipr2.12763
– ident: e_1_2_10_34_1
  doi: 10.3390/electronics11162621
– ident: e_1_2_10_15_1
  doi: 10.1109/ChinaSIP.2013.6625374
– ident: e_1_2_10_27_1
  doi: 10.3390/jimaging10010004
– ident: e_1_2_10_32_1
  doi: 10.1007/s11042‐020‐09816‐3
– ident: e_1_2_10_55_1
  doi: 10.1002/spy2.500
– ident: e_1_2_10_35_1
  doi: 10.1016/j.eswa.2024.124975
– ident: e_1_2_10_6_1
  doi: 10.32604/cmc.2023.041074
– ident: e_1_2_10_45_1
  doi: 10.1109/TIFS.2022.3144878
SSID ssj0006161
Score 2.4593964
Snippet The practice of cutting and pasting portions of one image into another, known as “image splicing,” is commonplace in the field of image manipulation. Image...
The practice of cutting and pasting portions of one image into another, known as "image splicing," is commonplace in the field of image manipulation. Image...
SourceID pubmedcentral
proquest
pubmed
crossref
wiley
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1026
SubjectTerms Agnosticism
Compression
Data loss
Deep learning
digital forensics
Encoding
Extraction
Feature extraction
feature fusion
Forgery
image authentication
Image compression
image forgery localization
Image manipulation
Image processing
image splicing detection
Learning
Localization
Manipulation
Methodological problems
Original Paper
U‐shaped network
Title CMV2U‐Net: A U‐shaped network with edge‐weighted features for detecting and localizing image splicing
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2F1556-4029.70033
https://www.ncbi.nlm.nih.gov/pubmed/40177991
https://www.proquest.com/docview/3198890700
https://www.proquest.com/docview/3229021803
https://www.proquest.com/docview/3185786915
https://pubmed.ncbi.nlm.nih.gov/PMC12153247
Volume 70
WOSCitedRecordID wos001480529500035&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1556-4029
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0006161
  issn: 0022-1198
  databaseCode: DRFUL
  dateStart: 20060101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1ba9RAFD7YrQ-CeL-srWUEH3xJSTLJXHwr1UVEVxFX9i3MLXRR09JsFfrUn-Bv9Jf0nEk2dK0igm8JZyZkJuc-J98BeMqFK5Uv0sSgvUkKr0VitCoTm3MnPJocp21sNiGnUzWf6_d9NSH9C9PhQwwJN5KMqK9JwI1tLwg5GkJB0Y_eldSQbAM2c-TecgSbLz5MZm8GdSwyka0gwzMMsXt8Hyrn-eUR66bpkr95uWzyojsb7dHk5n9YyS240TujbK_jnttwJTR34HqXyWPdD0p34fP-20_57OfZj2lYPmd7jC7bA3MUPGu6GnJGyVxGiTkkfY-5ViTWIWKGtgzdYuYDHVagmWSm8Swa0MUp3S6-okJjLZ2i4-09mE1eftx_lfQtGhJXaMWTvEZ7VtbcCKXKWjlvLVdOcMkzX0unnLMZxSgiCKEKW8vCWFFYgSSTmjzw-zBqDpvwEBhPc69LVBAeeYd7YeqCW3QfbCHRomb1GHZXX6dyPX45tdH4Uq3iGNrHivaxivs4hmfDhKMOuuPPQ7dXn7vqZbitUDkppVElpr8nE1I-Okgpzn4ykFE46cTFNOHwhB6hUCMKnZVjeNAxz_AqGNhKid75GNQaWw0DCPh7ndIsDiIAOCGCoCMscUsiX_1tedXrybt48ehfJ2zBtZwaHscKz20YLY9PwmO46r4tF-3xDmzIudrpBe4cXqYodA
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3da9RAEF-0FRSKn7U9rbqCD76kJNnNfvhWqkfV6wnSk76F_Qo9tGlprgo--Sf0b-xf4swmF-6sIoJvCZMNyWZmfjOzm98Q8oIJVyjP08QA3iTca5EYrYrE5swJD5DjtI3NJuR4rA4P9eK_MC0_RF9wQ8uI_hoNHAvSC1YOSCgw_dHbEjuSXSerHJQJtHz19cfhZNT7Y5GJbM4ZnkGO3RH84H6eX26xjE1XAs6r-yYX49kISMM7_-NV7pLbXThKd1r9uUeuhfo-WWtrebT9RekB-by7_ymfXP64GIfZK7pD8bA5MqfB07rdRU6xnEuxNAeib7HaCsIqRNbQhkJgTH3A5QoASmpqTyOETr_j6fQYXBptcB0dTtfJZPjmYHcv6Zo0JI5rxZK8AkQrKmaEUkWlnLeWKSeYZJmvpFPO2QyzFBGEUNxWkhsruBUgMqnJA3tIVuqTOmwSytLc6wJchAftYV6YijMLAYTlEjA1qwZke_55StcxmGMjjS_lPJPBeSxxHss4jwPysh9w2pJ3_PnSrfn3LjsrbkpwT0ppcIrp78XIlQ8hUgqjn_diME9cczF1ODnHWyjwiUJnxYBstNrTPwqktlJCfD4gakmv-guQ-ntZUk-PIgU4coJAKCxhSqJi_e31ynfDD_Hg0b8OeEZu7h3sj8rR2_H7x-RWju2P437PLbIyOzsPT8gN93U2bc6ednb3EyFfK3w
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Li9RAEC50VkQQ34_RVVvw4CVLku50Ot6WXYOPdRRxZG-hX2EHd7PDZlbBkz_B3-gvsaqTCTOuIoK3hEqHpFNVX1V15yuAJ1zaTDkRRxrxJhKukJEuVBaZlFvpEHJsYUKziXwyUfv7xeq_MB0_xFBwI8sI_poM3M9dvWLliISS0p9iK6eOZOdhQ1ArmRFs7L4vp3uDP5aJTJac4Qnm2D3BD-3n-eUW69h0JuA8u29yNZ4NgFRe_R-vcg2u9OEo2-705zqc880NuNzV8lj3i9JN-LTz5mM6_fHt-8QvnrFtRoftgZ57x5puFzmjci6j0hyKvoRqKwprH1hDW4aBMXOelisQKJluHAsQOvtKp7MjdGmspXV0PL0F0_L5h50XUd-kIbKiUDxKa0S0rOZaKpXVyjpjuLKS5zxxdW6VtSahLEV6KZUwdS60kcJIFOlYp57fhlFz3Pi7wHicuiJDF-FQe7iTuhbcYABhRI6YmtRj2Fp-nsr2DObUSOOwWmYyNI8VzWMV5nEMT4cB846848-Xbi6_d9VbcVuhe1KqQKcY_15MXPkYIsU4-vEgRvOkNRfd-ONTuoVCnyiLJBvDnU57hkfB1DbPMT4fg1rTq-ECov5elzSzg0ABTpwgGArnOCVBsf72etWr8m04uPevAx7BxXe7ZbX3cvL6PlxKqftx2O65CaPFyal_ABfs58WsPXnYm91Pa2sq9w
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=CMV2U%E2%80%90Net%3A+A+U%E2%80%90shaped+network+with+edge%E2%80%90weighted+features+for+detecting+and+localizing+image+splicing&rft.jtitle=Journal+of+forensic+sciences&rft.au=Akram%2C+Arslan&rft.au=Jaffar%2C+Muhammad+Arfan&rft.au=Rashid%2C+Javed&rft.au=Boulaaras%2C+Salah+Mahmoud&rft.date=2025-05-01&rft.issn=0022-1198&rft.eissn=1556-4029&rft.volume=70&rft.issue=3&rft.spage=1026&rft.epage=1043&rft_id=info:doi/10.1111%2F1556-4029.70033&rft.externalDBID=10.1111%252F1556-4029.70033&rft.externalDocID=JFO70033
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0022-1198&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0022-1198&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0022-1198&client=summon