Academic Journal
Προβολή σε EDS

Enhancing Scene Text Recognition with Encoder–Decoder Interactive Model.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Enhancing Scene Text Recognition with Encoder–Decoder Interactive Model.
Συγγραφείς: Mu, Yongbin1,2,3,4 (AUTHOR), Maimaiti, Mieradilijiang1,2,3,4 (AUTHOR), Xu, Miaomiao1,2,3,4 (AUTHOR), Li, Wenkai1,2,3,4 (AUTHOR), Silamu, Wushour1,2,3,4 (AUTHOR) wushour@xju.edu.cn
Πηγή: Sensors (14248220). Dec2025, Vol. 25 Issue 24, p7684. 20p.
Θεματικοί όροι: *Text recognition, *Benchmark testing (Engineering), *Artificial neural networks
Περίληψη: Scene text recognition has significant application value in autonomous driving, smart retail, and assistive devices. However, due to challenges such as multi-scale variations, distortions, and complex backgrounds, existing methods such as CRNN, ViT, and PARSeq, while showing good performance, still have room for improvement in feature extraction and semantic modeling capabilities. To address these issues, this paper proposes a novel scene text recognition model named the Encoder–Decoder Interactive Model (EDIM). Based on an encoder–decoder framework, EDIM introduces a Multi-scale Dilated Fusion Attention (MSFA) module in the encoder to enhance multi-scale feature representation. In the decoder, a Sequential Encoder–Decoder Context Fusion (SeqEDCF) mechanism is designed to enable efficient semantic interaction between the encoder and decoder. The effectiveness of the proposed method is validated on six regular and irregular benchmark test sets, as well as various subsets of the Union14M-L dataset. Experimental results demonstrate that EDIM outperforms state-of-the-art (SOTA) methods across multiple metrics, achieving significant performance gains, especially in recognizing irregular and distorted text. [ABSTRACT FROM AUTHOR]
Βάση Δεδομένων: Academic Search Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:asx&genre=article&issn=14248220&ISBN=&volume=25&issue=24&date=20251215&spage=7684&pages=7684-7703&title=Sensors (14248220)&atitle=Enhancing%20Scene%20Text%20Recognition%20with%20Encoder%E2%80%93Decoder%20Interactive%20Model.&aulast=Mu%2C%20Yongbin&id=DOI:10.3390/s25247684
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: asx
DbLabel: Academic Search Index
An: 190469874
RelevancyScore: 1393
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1393.09643554688
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Enhancing Scene Text Recognition with Encoder–Decoder Interactive Model.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Mu%2C+Yongbin%22">Mu, Yongbin</searchLink><relatesTo>1,2,3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Maimaiti%2C+Mieradilijiang%22">Maimaiti, Mieradilijiang</searchLink><relatesTo>1,2,3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Miaomiao%22">Xu, Miaomiao</searchLink><relatesTo>1,2,3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Wenkai%22">Li, Wenkai</searchLink><relatesTo>1,2,3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Silamu%2C+Wushour%22">Silamu, Wushour</searchLink><relatesTo>1,2,3,4</relatesTo> (AUTHOR)<i> wushour@xju.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Sensors+%2814248220%29%22">Sensors (14248220)</searchLink>. Dec2025, Vol. 25 Issue 24, p7684. 20p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Text+recognition%22">Text recognition</searchLink><br />*<searchLink fieldCode="DE" term="%22Benchmark+testing+%28Engineering%29%22">Benchmark testing (Engineering)</searchLink><br />*<searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Scene text recognition has significant application value in autonomous driving, smart retail, and assistive devices. However, due to challenges such as multi-scale variations, distortions, and complex backgrounds, existing methods such as CRNN, ViT, and PARSeq, while showing good performance, still have room for improvement in feature extraction and semantic modeling capabilities. To address these issues, this paper proposes a novel scene text recognition model named the Encoder–Decoder Interactive Model (EDIM). Based on an encoder–decoder framework, EDIM introduces a Multi-scale Dilated Fusion Attention (MSFA) module in the encoder to enhance multi-scale feature representation. In the decoder, a Sequential Encoder–Decoder Context Fusion (SeqEDCF) mechanism is designed to enable efficient semantic interaction between the encoder and decoder. The effectiveness of the proposed method is validated on six regular and irregular benchmark test sets, as well as various subsets of the Union14M-L dataset. Experimental results demonstrate that EDIM outperforms state-of-the-art (SOTA) methods across multiple metrics, achieving significant performance gains, especially in recognizing irregular and distorted text. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=asx&AN=190469874
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/s25247684
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 20
        StartPage: 7684
    Subjects:
      – SubjectFull: Text recognition
        Type: general
      – SubjectFull: Benchmark testing (Engineering)
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
    Titles:
      – TitleFull: Enhancing Scene Text Recognition with Encoder–Decoder Interactive Model.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Mu, Yongbin
      – PersonEntity:
          Name:
            NameFull: Maimaiti, Mieradilijiang
      – PersonEntity:
          Name:
            NameFull: Xu, Miaomiao
      – PersonEntity:
          Name:
            NameFull: Li, Wenkai
      – PersonEntity:
          Name:
            NameFull: Silamu, Wushour
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 12
              Text: Dec2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 14248220
          Numbering:
            – Type: volume
              Value: 25
            – Type: issue
              Value: 24
          Titles:
            – TitleFull: Sensors (14248220)
              Type: main
ResultId 1