View in EDS

Advancing neural aesthetic assessment of artistic images based on bundle features integration.

Saved in:
Bibliographic Details
Title: Advancing neural aesthetic assessment of artistic images based on bundle features integration.
Authors: Yan, Simin1 (AUTHOR), Xu, Shuchang2 (AUTHOR) xusc@hznu.edu.cn, Lei, Aiping3 (AUTHOR), Zhang, Sanyuan1 (AUTHOR)
Source: Visual Computer. Jun2025, Vol. 41 Issue 8, p5447-5459. 13p.
Subjects: Artificial neural networks, Convolutional neural networks, Art theory, Artificial intelligence, Image processing
Abstract: The aesthetic assessment of images is a popular research topic due to its practical applications in various fields such as image recommendation, image ranking, and image search. Currently, most research on image aesthetic assessment relies on large-scale photography datasets, such as AVA and AADB, primarily composed of photos taken by users in real-world scenarios. Few studies specifically focus on the automatic aesthetic assessment of artistic images. Artistic images are more complex, diverse, and abstract compared to photographic images. In this paper, we propose a convolutional neural network model to automatically generate aesthetic scores for input artistic images. Unlike previous research, this study explores artistic theories and introduces the analysis of aesthetic features in artistic images from three dimensions: color, brightness, and contour. These features are integrated to generate an overall aesthetic score. We utilize our own large-scale dataset of artistic images for aesthetic assessment, consisting of over 7,000 artistic images, each accompanied by corresponding average aesthetic scores assigned by users. We compare our model with state-of-the-art image aesthetic assessment models, demonstrating the effectiveness of our approach. Code is available at: https://github.com/ysmyan/aiaa [ABSTRACT FROM AUTHOR]
Copyright of Visual Computer is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 185238288
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Advancing neural aesthetic assessment of artistic images based on bundle features integration.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yan%2C+Simin%22">Yan, Simin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Shuchang%22">Xu, Shuchang</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> xusc@hznu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Lei%2C+Aiping%22">Lei, Aiping</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Sanyuan%22">Zhang, Sanyuan</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Visual+Computer%22">Visual Computer</searchLink>. Jun2025, Vol. 41 Issue 8, p5447-5459. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Art+theory%22">Art theory</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The aesthetic assessment of images is a popular research topic due to its practical applications in various fields such as image recommendation, image ranking, and image search. Currently, most research on image aesthetic assessment relies on large-scale photography datasets, such as AVA and AADB, primarily composed of photos taken by users in real-world scenarios. Few studies specifically focus on the automatic aesthetic assessment of artistic images. Artistic images are more complex, diverse, and abstract compared to photographic images. In this paper, we propose a convolutional neural network model to automatically generate aesthetic scores for input artistic images. Unlike previous research, this study explores artistic theories and introduces the analysis of aesthetic features in artistic images from three dimensions: color, brightness, and contour. These features are integrated to generate an overall aesthetic score. We utilize our own large-scale dataset of artistic images for aesthetic assessment, consisting of over 7,000 artistic images, each accompanied by corresponding average aesthetic scores assigned by users. We compare our model with state-of-the-art image aesthetic assessment models, demonstrating the effectiveness of our approach. Code is available at: https://github.com/ysmyan/aiaa [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Visual Computer is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=185238288
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00371-024-03732-5
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 5447
    Subjects:
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Art theory
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Image processing
        Type: general
    Titles:
      – TitleFull: Advancing neural aesthetic assessment of artistic images based on bundle features integration.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yan, Simin
      – PersonEntity:
          Name:
            NameFull: Xu, Shuchang
      – PersonEntity:
          Name:
            NameFull: Lei, Aiping
      – PersonEntity:
          Name:
            NameFull: Zhang, Sanyuan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 01782789
          Numbering:
            – Type: volume
              Value: 41
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: Visual Computer
              Type: main
ResultId 1