Refined Multi-Focus image fusion using Multi-Scale neural network with SpSwin Autoencoder-based matting
This paper proposes a novel method based on a Multi-Scale neural network with a SpatialSwin (SpSwin) Autoencoder-based matting for the multi-focus image fusion (MFIF) task. The proposed strategy introduces several innovations to enhance image quality and address challenges like boundary precision an...
Saved in:
| Published in: | Expert systems with applications Vol. 276; p. 126980 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Ltd
01.06.2025
|
| Subjects: | |
| ISSN: | 0957-4174 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | This paper proposes a novel method based on a Multi-Scale neural network with a SpatialSwin (SpSwin) Autoencoder-based matting for the multi-focus image fusion (MFIF) task. The proposed strategy introduces several innovations to enhance image quality and address challenges like boundary precision and texture preservation. The Sum of Edge-Weighted Gaussian-based Modified Laplacian (SEWG-ML) focus measure is developed to refine boundary detection, while a Pyramid Squeeze Attention (PSA) module dynamically adapts spatial and channel-wise attention at multiple scales for precise feature refinement. Trimap generation integrates superpixel segmentation and fuzzy k-means clustering for accurate foreground-background separation. The SpSwin Autoencoder leverages Swin Transformers for hierarchical token reduction and includes a Hierarchical Feature Enhancement Block (HFEB) to reconstruct high-level contextual features, ensuring seamless image fusion with reduced artifacts. These contributions result in a robust, high-performance framework. Experimental evaluations on benchmark datasets demonstrate superior performance, with metrics including SSIM (0.982), PSNR (39.60 dB), and MI (7.968), surpassing existing techniques. The proposed method in this paper is especially good at preserving fine details and suppressing artifacts, indicating its potential applicability in surveillance, medical imaging, and object detection. |
|---|---|
| AbstractList | This paper proposes a novel method based on a Multi-Scale neural network with a SpatialSwin (SpSwin) Autoencoder-based matting for the multi-focus image fusion (MFIF) task. The proposed strategy introduces several innovations to enhance image quality and address challenges like boundary precision and texture preservation. The Sum of Edge-Weighted Gaussian-based Modified Laplacian (SEWG-ML) focus measure is developed to refine boundary detection, while a Pyramid Squeeze Attention (PSA) module dynamically adapts spatial and channel-wise attention at multiple scales for precise feature refinement. Trimap generation integrates superpixel segmentation and fuzzy k-means clustering for accurate foreground-background separation. The SpSwin Autoencoder leverages Swin Transformers for hierarchical token reduction and includes a Hierarchical Feature Enhancement Block (HFEB) to reconstruct high-level contextual features, ensuring seamless image fusion with reduced artifacts. These contributions result in a robust, high-performance framework. Experimental evaluations on benchmark datasets demonstrate superior performance, with metrics including SSIM (0.982), PSNR (39.60 dB), and MI (7.968), surpassing existing techniques. The proposed method in this paper is especially good at preserving fine details and suppressing artifacts, indicating its potential applicability in surveillance, medical imaging, and object detection. |
| ArticleNumber | 126980 |
| Author | Yu, Shanchuan Jiang, Shengchuan |
| Author_xml | – sequence: 1 givenname: Shengchuan surname: Jiang fullname: Jiang, Shengchuan organization: Department of Traffic Engineering, Business School, University of Shanghai for Science and Technology, Shanghai 200093, China – sequence: 2 givenname: Shanchuan surname: Yu fullname: Yu, Shanchuan email: yushanchuan@cmhk.com organization: National Engineering and Research Center for Mountainous Highways, China Merchants Chongqing Communications Research & Design Institute Co. Ltd, Chongqing 400067, China |
| BookMark | eNp9kMtOwzAQRb0oEm3hB1j5BxL8SOpUYlNVFJCKkAisLdeZFJfUrmyHiL_HVbti0VnMLEbnSvdM0Mg6CwjdUZJTQmf3uxzCoHJGWJlTNptXZITGZF6KrKCiuEaTEHaEUEGIGKPtO7TGQoNf-y6abOV0H7DZqy3gtg_GWZy23Z7ftVYdYAu9V106cXD-Gw8mfuH6UA_G4kUfHVjtGvDZRoWUu1cxpoAbdNWqLsDt-U7R5-rxY_mcrd-eXpaLdaY5q2KmBLA0QvCm1EyLuU4FNpuqaARvmQbFWSmEonpGCKecF6AVqYoWFAUKJeVTVJ1ytXcheGilNlHFVCR6ZTpJiTxKkjt5lCSPkuRJUkLZP_Tgkwn_exl6OEGQSv0Y8DJokwxAYzzoKBtnLuF_YVeGVg |
| CitedBy_id | crossref_primary_10_3934_electreng_2025023 crossref_primary_10_1016_j_eswa_2025_128895 |
| Cites_doi | 10.1049/ipr2.12668 10.1007/s40747-023-01151-y 10.1016/j.jksuci.2023.101751 10.1016/j.ijmecsci.2022.107741 10.1016/j.neunet.2024.106603 10.1016/j.imavis.2024.105210 10.1016/j.ijleo.2022.170223 10.1016/j.compeleceng.2024.109629 10.1016/j.displa.2024.102837 10.1016/j.inffus.2023.102125 10.1007/s00521-023-08568-z 10.1016/j.compeleceng.2024.109299 10.1038/s41598-023-35663-x 10.1007/s00521-022-07766-5 10.1109/TIP.2023.3276330 10.1049/ipr2.12363 10.1109/JSTARS.2023.3239119 10.1038/s41598-024-69193-x 10.1016/j.bspc.2022.103534 10.1007/s42979-022-01607-x 10.1016/j.eswa.2023.121156 10.1049/ipr2.12430 10.1016/j.inffus.2024.102230 10.1016/j.autcon.2023.105213 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd |
| Copyright_xml | – notice: 2025 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.eswa.2025.126980 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_eswa_2025_126980 S0957417425006025 |
| GroupedDBID | --K --M .DC .~1 0R~ 13V 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AAAKF AABNK AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AARIN AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABMVD ABUCO ACDAQ ACGFS ACHRH ACNTT ACRLP ACVFH ACZNC ADBBV ADCNI ADEZE ADTZH AEBSH AECPX AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AFXIZ AGCQF AGHFR AGRNS AGUBO AGUMN AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALEQD ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APLSM APXCP AXJTR BJAXD BKOJK BLXMC BNPGV BNSAS CS3 DU5 EBS EFJIC EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX IHE J1W JJJVA KOM LG9 LY1 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 ROL RPZ SDF SDG SDP SDS SES SEW SPC SPCBC SSB SSD SSH SSL SST SSV SSZ T5K TN5 ~G- 29G 9DU AAAKG AAQXK AAYXX ABKBG ABUFD ABWVN ABXDB ACLOT ACNNM ACRPL ADJOM ADMUD ADNMO AGQPQ ASPBG AVWKF AZFZN CITATION EFKBS EFLBG EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET WUQ XPP ZMT ~HD |
| ID | FETCH-LOGICAL-c328t-a7e2222773d5c2c79c269bb84d73f2cea32577a1c60031334eca084fea1e1e513 |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001486933800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0957-4174 |
| IngestDate | Tue Nov 18 21:47:17 EST 2025 Sat Nov 29 07:55:22 EST 2025 Sat Jun 21 16:53:52 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Combined Convolutional Blocks (CCBs) Pyramid Squeeze Attention (PSA) And Hierarchical Feature Enhancement Block (HFEB) Depthwise Separable Convolution (DSC) SpatialSwin (SpSwin) Autoencoder Transpose Convolution (TC) Image fusion |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c328t-a7e2222773d5c2c79c269bb84d73f2cea32577a1c60031334eca084fea1e1e513 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_eswa_2025_126980 crossref_primary_10_1016_j_eswa_2025_126980 elsevier_sciencedirect_doi_10_1016_j_eswa_2025_126980 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-06-01 |
| PublicationDateYYYYMMDD | 2025-06-01 |
| PublicationDate_xml | – month: 06 year: 2025 text: 2025-06-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Expert systems with applications |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Jin, Xi, Zhou, Ren, Yang, Jiang (b0050) 2023; 17 Chen, Jiang, Li, Yao (b0015) 2024; 103 Xie, Guo, Li, He, Zhou (b0120) 2024; 1–24 Mahler, Wang, Steiglechner, Birk, Heczko, Scheffler, Lohmann (b0085) 2023 Reyad, Sarhan, Arafa (b0090) 2023; 35 Karacan (b0055) 2023; 119 Liu, Peng, Liu, Zhao, Su, Zhang (b0080) 2023; 35 Fang, Ning, Mao, Zhang, Zhao, Hu, Wang (b0035) 2024; 117 Zhai, Ouyang, Luo, Chen, Zeng (b0130) 2024 Elshamy, Abu-Elnasr, Elhoseny, Elmougy (b0030) 2024; 14 Bouzos, Andreadis, Mitianoudis (b0010) 2023; 32 Vidyashree, Rajendra (b0110) 2023; 4 Li, Zhang, Liu, Peng, Wang, Liu (b0060) 2024; 179 Li, Li, Lu, Wang, Zhou (b0070) 2023; 272 Sheikh, Meier, Blankenship, Vangelatos, Zhao, Marcus, Grigoropoulos (b0105) 2022; 236 Zhang, Wu, Yuan, Zhao (b0135) 2022; 16 Behera, Bakshi, Nappi, Sa (b0005) 2023; 16 Rivera-Aguilar, Cuevas, Pérez, Camarena, Rodríguez (b0095) 2024; 1–17 Shao, Jin, Jiang, Miao, Wang, Chu (b0100) 2024; 119 Duan, Luo, Zhang (b0020) 2024; 235 Wang, Qu, Zhang, Xie (b0115) 2024; 105 Ghezelbash, Maghsoudi, Shamekhi, Pradhan, Daviran (b0040) 2023; 35 Huang, Cai, Zhang, Lu, Hammad, Fan (b0045) 2024; 158 Elshamy, Abu-Elnasr, Elhoseny, Elmougy (b0025) 2023; 13 Zhai, Chen, Wang, Ouyang, Zeng (b0125) 2024 Zhou, Jin, Jiang, Cai, Lee, Yao (b0140) 2022; 16 Li, Li, Jiang (b0065) 2023; 9 Li, Li, Fu, Peng (b0075) 2022; 74 Bouzos (10.1016/j.eswa.2025.126980_b0010) 2023; 32 Li (10.1016/j.eswa.2025.126980_b0070) 2023; 272 Huang (10.1016/j.eswa.2025.126980_b0045) 2024; 158 Shao (10.1016/j.eswa.2025.126980_b0100) 2024; 119 Ghezelbash (10.1016/j.eswa.2025.126980_b0040) 2023; 35 Liu (10.1016/j.eswa.2025.126980_b0080) 2023; 35 Rivera-Aguilar (10.1016/j.eswa.2025.126980_b0095) 2024; 1–17 Li (10.1016/j.eswa.2025.126980_b0060) 2024; 179 Zhou (10.1016/j.eswa.2025.126980_b0140) 2022; 16 Duan (10.1016/j.eswa.2025.126980_b0020) 2024; 235 Reyad (10.1016/j.eswa.2025.126980_b0090) 2023; 35 Chen (10.1016/j.eswa.2025.126980_b0015) 2024; 103 Mahler (10.1016/j.eswa.2025.126980_b0085) 2023 Elshamy (10.1016/j.eswa.2025.126980_b0030) 2024; 14 Xie (10.1016/j.eswa.2025.126980_b0120) 2024; 1–24 Elshamy (10.1016/j.eswa.2025.126980_b0025) 2023; 13 Li (10.1016/j.eswa.2025.126980_b0065) 2023; 9 Sheikh (10.1016/j.eswa.2025.126980_b0105) 2022; 236 Zhai (10.1016/j.eswa.2025.126980_b0130) 2024 Behera (10.1016/j.eswa.2025.126980_b0005) 2023; 16 Zhai (10.1016/j.eswa.2025.126980_b0125) 2024 Jin (10.1016/j.eswa.2025.126980_b0050) 2023; 17 Zhang (10.1016/j.eswa.2025.126980_b0135) 2022; 16 Fang (10.1016/j.eswa.2025.126980_b0035) 2024; 117 Karacan (10.1016/j.eswa.2025.126980_b0055) 2023; 119 Li (10.1016/j.eswa.2025.126980_b0075) 2022; 74 Wang (10.1016/j.eswa.2025.126980_b0115) 2024; 105 Vidyashree (10.1016/j.eswa.2025.126980_b0110) 2023; 4 |
| References_xml | – volume: 17 start-page: 733 year: 2023 end-page: 746 ident: b0050 article-title: An unsupervised multi‐focus image fusion method based on Transformer and U‐Net publication-title: IET Image Processing – volume: 1–17 year: 2024 ident: b0095 article-title: A new histogram equalization technique for contrast enhancement of grayscale images using the differential evolution algorithm publication-title: Neural Computing and Applications – volume: 119 year: 2024 ident: b0100 article-title: Multi-focus image fusion based on transformer and depth information learning publication-title: Computers and Electrical Engineering – volume: 9 start-page: 7395 year: 2023 end-page: 7422 ident: b0065 article-title: GIPC-GAN: An end-to-end gradient and intensity joint proportional constraint generative adversarial network for multi-focus image fusion publication-title: Complex & Intelligent Systems – volume: 117 year: 2024 ident: b0035 article-title: A multi-focus image fusion network combining dilated convolution with learnable spacings and residual dense network publication-title: Computers and Electrical Engineering – volume: 16 start-page: 499 year: 2022 end-page: 508 ident: b0135 article-title: CFNet: Context fusion network for multi‐focus images publication-title: IET Image Processing – volume: 272 year: 2023 ident: b0070 article-title: Multi-focus image fusion with convolutional neural network based on Dempster-Shafer theory publication-title: Optik – volume: 235 year: 2024 ident: b0020 article-title: Combining transformers with CNN for multi-focus image fusion publication-title: Expert Systems with Applications – volume: 16 start-page: 1558 year: 2022 end-page: 1574 ident: b0140 article-title: MCRD‐Net: An unsupervised dense network with multi‐scale convolutional block attention for multi‐focus image fusion publication-title: IET Image Processing – volume: 119 year: 2023 ident: b0055 article-title: Multi-image transformer for multi-focus image fusion publication-title: Signal Processing: Image Communication – volume: 4 start-page: 190 year: 2023 ident: b0110 article-title: An improvised sentiment analysis model on twitter data using stochastic gradient descent (SGD) optimization algorithm in stochastic gate neural network (SGNN) publication-title: SN computer science – volume: 236 year: 2022 ident: b0105 article-title: Systematic design of Cauchy symmetric structures through Bayesian optimization publication-title: International Journal of Mechanical Sciences – volume: 35 start-page: 719 year: 2023 end-page: 733 ident: b0040 article-title: Genetic algorithm to optimize the SVM and K-means algorithms for mapping of mineral prospectivity publication-title: Neural Computing and Applications – volume: 105 year: 2024 ident: b0115 article-title: New insights into multi-focus image fusion: A fusion method based on multi-dictionary linear sparse representation and region fusion model publication-title: Information Fusion – year: 2024 ident: b0125 article-title: W-shaped network combined with dual transformers and edge protection for multi-focus image fusion publication-title: Image and Vision Computing – volume: 179 year: 2024 ident: b0060 article-title: Multi-focus image fusion with parameter adaptive dual channel dynamic threshold neural P systems publication-title: Neural Networks – volume: 13 start-page: 8814 year: 2023 ident: b0025 article-title: Improving the efficiency of RMSProp optimizer by utilizing Nestrove in deep learning publication-title: Scientific Reports – start-page: 123 year: 2023 end-page: 132 ident: b0085 publication-title: Pretraining is All You Need: A Multi-Atlas Enhanced Transformer Framework for Autism Spectrum Disorder Classification – volume: 74 year: 2022 ident: b0075 article-title: MSENet: A multi-scale enhanced network based on unique features guidance for medical image fusion publication-title: Biomedical Signal Processing and Control – year: 2024 ident: b0130 article-title: MSI-DTrans: A multi-focus image fusion using multilayer semantic interaction and dynamic transformer publication-title: Displays – volume: 16 start-page: 1771 year: 2023 end-page: 1784 ident: b0005 article-title: Superpixel-based multiscale CNN approach toward multiclass object segmentation from UAV-captured aerial images publication-title: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing – volume: 103 year: 2024 ident: b0015 article-title: A defocus and similarity attention-based cascaded network for multi-focus and misaligned image fusion publication-title: Information Fusion – volume: 35 start-page: 17095 year: 2023 end-page: 17112 ident: b0090 article-title: A modified Adam algorithm for deep neural network optimization publication-title: Neural Computing and Applications – volume: 158 year: 2024 ident: b0045 article-title: Crack detection of masonry structure based on thermal and visible image fusion and semantic segmentation publication-title: Automation in Construction – volume: 32 start-page: 2915 year: 2023 end-page: 2930 ident: b0010 article-title: A convolutional neural network-based conditional random field model for structured multi-focus image fusion robust to noise publication-title: IEEE Transactions on Image Processing – volume: 35 year: 2023 ident: b0080 article-title: AFCANet: An adaptive feature concatenate attention network for multi-focus image fusion publication-title: Journal of King Saud University-Computer and Information Sciences – volume: 14 start-page: 19534 year: 2024 ident: b0030 article-title: Enhancing colorectal cancer histology diagnosis using modified deep neural networks optimizer publication-title: Scientific Reports – volume: 1–24 year: 2024 ident: b0120 article-title: SwinMFF: Toward high-fidelity end-to-end multi-focus image fusion via swin transformer-based network publication-title: The Visual Computer – volume: 17 start-page: 733 issue: 3 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0050 article-title: An unsupervised multi‐focus image fusion method based on Transformer and U‐Net publication-title: IET Image Processing doi: 10.1049/ipr2.12668 – volume: 9 start-page: 7395 issue: 6 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0065 article-title: GIPC-GAN: An end-to-end gradient and intensity joint proportional constraint generative adversarial network for multi-focus image fusion publication-title: Complex & Intelligent Systems doi: 10.1007/s40747-023-01151-y – volume: 35 issue: 9 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0080 article-title: AFCANet: An adaptive feature concatenate attention network for multi-focus image fusion publication-title: Journal of King Saud University-Computer and Information Sciences doi: 10.1016/j.jksuci.2023.101751 – volume: 236 year: 2022 ident: 10.1016/j.eswa.2025.126980_b0105 article-title: Systematic design of Cauchy symmetric structures through Bayesian optimization publication-title: International Journal of Mechanical Sciences doi: 10.1016/j.ijmecsci.2022.107741 – volume: 179 year: 2024 ident: 10.1016/j.eswa.2025.126980_b0060 article-title: Multi-focus image fusion with parameter adaptive dual channel dynamic threshold neural P systems publication-title: Neural Networks doi: 10.1016/j.neunet.2024.106603 – year: 2024 ident: 10.1016/j.eswa.2025.126980_b0125 article-title: W-shaped network combined with dual transformers and edge protection for multi-focus image fusion publication-title: Image and Vision Computing doi: 10.1016/j.imavis.2024.105210 – volume: 272 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0070 article-title: Multi-focus image fusion with convolutional neural network based on Dempster-Shafer theory publication-title: Optik doi: 10.1016/j.ijleo.2022.170223 – volume: 119 year: 2024 ident: 10.1016/j.eswa.2025.126980_b0100 article-title: Multi-focus image fusion based on transformer and depth information learning publication-title: Computers and Electrical Engineering doi: 10.1016/j.compeleceng.2024.109629 – year: 2024 ident: 10.1016/j.eswa.2025.126980_b0130 article-title: MSI-DTrans: A multi-focus image fusion using multilayer semantic interaction and dynamic transformer publication-title: Displays doi: 10.1016/j.displa.2024.102837 – volume: 103 year: 2024 ident: 10.1016/j.eswa.2025.126980_b0015 article-title: A defocus and similarity attention-based cascaded network for multi-focus and misaligned image fusion publication-title: Information Fusion doi: 10.1016/j.inffus.2023.102125 – start-page: 123 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0085 – volume: 35 start-page: 17095 issue: 23 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0090 article-title: A modified Adam algorithm for deep neural network optimization publication-title: Neural Computing and Applications doi: 10.1007/s00521-023-08568-z – volume: 117 year: 2024 ident: 10.1016/j.eswa.2025.126980_b0035 article-title: A multi-focus image fusion network combining dilated convolution with learnable spacings and residual dense network publication-title: Computers and Electrical Engineering doi: 10.1016/j.compeleceng.2024.109299 – volume: 13 start-page: 8814 issue: 1 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0025 article-title: Improving the efficiency of RMSProp optimizer by utilizing Nestrove in deep learning publication-title: Scientific Reports doi: 10.1038/s41598-023-35663-x – volume: 35 start-page: 719 issue: 1 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0040 article-title: Genetic algorithm to optimize the SVM and K-means algorithms for mapping of mineral prospectivity publication-title: Neural Computing and Applications doi: 10.1007/s00521-022-07766-5 – volume: 32 start-page: 2915 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0010 article-title: A convolutional neural network-based conditional random field model for structured multi-focus image fusion robust to noise publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2023.3276330 – volume: 1–24 year: 2024 ident: 10.1016/j.eswa.2025.126980_b0120 article-title: SwinMFF: Toward high-fidelity end-to-end multi-focus image fusion via swin transformer-based network publication-title: The Visual Computer – volume: 16 start-page: 499 issue: 2 year: 2022 ident: 10.1016/j.eswa.2025.126980_b0135 article-title: CFNet: Context fusion network for multi‐focus images publication-title: IET Image Processing doi: 10.1049/ipr2.12363 – volume: 16 start-page: 1771 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0005 article-title: Superpixel-based multiscale CNN approach toward multiclass object segmentation from UAV-captured aerial images publication-title: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing doi: 10.1109/JSTARS.2023.3239119 – volume: 1–17 year: 2024 ident: 10.1016/j.eswa.2025.126980_b0095 article-title: A new histogram equalization technique for contrast enhancement of grayscale images using the differential evolution algorithm publication-title: Neural Computing and Applications – volume: 14 start-page: 19534 issue: 1 year: 2024 ident: 10.1016/j.eswa.2025.126980_b0030 article-title: Enhancing colorectal cancer histology diagnosis using modified deep neural networks optimizer publication-title: Scientific Reports doi: 10.1038/s41598-024-69193-x – volume: 119 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0055 article-title: Multi-image transformer for multi-focus image fusion publication-title: Signal Processing: Image Communication – volume: 74 year: 2022 ident: 10.1016/j.eswa.2025.126980_b0075 article-title: MSENet: A multi-scale enhanced network based on unique features guidance for medical image fusion publication-title: Biomedical Signal Processing and Control doi: 10.1016/j.bspc.2022.103534 – volume: 4 start-page: 190 issue: 2 year: 2023 ident: 10.1016/j.eswa.2025.126980_b0110 article-title: An improvised sentiment analysis model on twitter data using stochastic gradient descent (SGD) optimization algorithm in stochastic gate neural network (SGNN) publication-title: SN computer science doi: 10.1007/s42979-022-01607-x – volume: 235 year: 2024 ident: 10.1016/j.eswa.2025.126980_b0020 article-title: Combining transformers with CNN for multi-focus image fusion publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2023.121156 – volume: 16 start-page: 1558 issue: 6 year: 2022 ident: 10.1016/j.eswa.2025.126980_b0140 article-title: MCRD‐Net: An unsupervised dense network with multi‐scale convolutional block attention for multi‐focus image fusion publication-title: IET Image Processing doi: 10.1049/ipr2.12430 – volume: 105 year: 2024 ident: 10.1016/j.eswa.2025.126980_b0115 article-title: New insights into multi-focus image fusion: A fusion method based on multi-dictionary linear sparse representation and region fusion model publication-title: Information Fusion doi: 10.1016/j.inffus.2024.102230 – volume: 158 year: 2024 ident: 10.1016/j.eswa.2025.126980_b0045 article-title: Crack detection of masonry structure based on thermal and visible image fusion and semantic segmentation publication-title: Automation in Construction doi: 10.1016/j.autcon.2023.105213 |
| SSID | ssj0017007 |
| Score | 2.4804533 |
| Snippet | This paper proposes a novel method based on a Multi-Scale neural network with a SpatialSwin (SpSwin) Autoencoder-based matting for the multi-focus image fusion... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 126980 |
| SubjectTerms | And Hierarchical Feature Enhancement Block (HFEB) Combined Convolutional Blocks (CCBs) Depthwise Separable Convolution (DSC) Image fusion Pyramid Squeeze Attention (PSA) SpatialSwin (SpSwin) Autoencoder Transpose Convolution (TC) |
| Title | Refined Multi-Focus image fusion using Multi-Scale neural network with SpSwin Autoencoder-based matting |
| URI | https://dx.doi.org/10.1016/j.eswa.2025.126980 |
| Volume | 276 |
| WOSCitedRecordID | wos001486933800001&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 issn: 0957-4174 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0017007 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtZ3Nb9MwFMAt6Dhw4RsxvuQDt8hT4sSxfZymTcBhQnRI5RQljrO1grRqE7Y_f895dlptaAIkDo0qN3YS_16dl5f3QcgHWZU2sVqxKjclA_22ZjrXDYsbFWubNwo-Q7EJeXqqZjP9xdfY3AzlBGTbqqsrvfqvqKENYLvQ2b_APQ4KDfAdoMMWsMP2j8B_tQ1ojnU0hNayk6XpN9H8p3PNaXpnGov6wTyAP08BkY1cUktA1aJLONpmp6vp5WAL6ZYu12Vt18zd8eoIVNwu3O8WoyOfXXc-K3SIl9t5Mz666cyDdfrCtufmot-K5vce20EIx2ZvjOBi6zSFFrIQJbN1SUJTo2RZgtV4wqrLsezLrRUcjQmLA7u5dGmhuDhIeK6x2tONzNhTN7AbF9S4OIdd75M9LoVWE7J3-Ol49nl8nSRjjJsPJ-Kjp9DR7-aRfq-h7GgdZ0_II_-4QA8R81Nyz7bPyONQioP6lfk5OffU6Q51OlCnSJ0O1OkOdYrUqadOHTWK1Okt6tRTf0G-nRyfHX1kvoYGMylXHSul5S7cWaa1MNxIbeAaq0pltUwbbmyZwpoty8TkQxbPNLOmjFXW2DKB_7BI0pdk0i5b-4pQFYMym4hawRN8JoSoQJExiTWNVbXJS7FPkjBvhfEJ5l2dkx9F8CRcFG6uCzfXBc71PonGPitMr3Ln3iLgKLyCiIpfAdJzR7_X_9jvDXm4FfK3ZNKte_uOPDC_uvlm_d4L2TWc8o6O |
| 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=Refined+Multi-Focus+image+fusion+using+Multi-Scale+neural+network+with+SpSwin+Autoencoder-based+matting&rft.jtitle=Expert+systems+with+applications&rft.au=Jiang%2C+Shengchuan&rft.au=Yu%2C+Shanchuan&rft.date=2025-06-01&rft.pub=Elsevier+Ltd&rft.issn=0957-4174&rft.volume=276&rft_id=info:doi/10.1016%2Fj.eswa.2025.126980&rft.externalDocID=S0957417425006025 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0957-4174&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0957-4174&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0957-4174&client=summon |