JOURNAL ARTICLE

A novel image classification in new media art design based on a visual neural network.

  • Published In: Journal of Computational Methods in Sciences & Engineering (Sage Publications Inc.), 2025, v. 25, n. 6. P. 5663 1 of 3

  • Database: Academic Search Ultimate 2 of 3

  • Authored By: Pei, Shiya 3 of 3

Abstract

The article focuses on an improved image classification method for emotional style recognition in new media artworks, including anime, using an enhanced ResNet101 neural network integrated with an attention mechanism and a focal loss function. A novel dataset of 8,000 new media artworks categorized into eight emotional styles was established to train and evaluate the model. The proposed improvements address limitations in global feature extraction and class imbalance, resulting in higher accuracy, precision, and recall compared to baseline models such as ResNet101 and Xception. Experimental results demonstrate that the method effectively automates the classification process, reducing manual labor and enhancing the dissemination of new media art online. Future work aims to expand the dataset and refine classification granularity to adapt to evolving artistic styles.

Additional Information

  • Source:Journal of Computational Methods in Sciences & Engineering (Sage Publications Inc.). 2025/11, Vol. 25, Issue 6, p5663
  • Document Type:Article
  • Subject Area:Social Sciences and Humanities
  • Publication Date:2025
  • ISSN:1472-7978
  • DOI:10.1177/14727978251348630
  • Accession Number:188762394
  • Copyright Statement:Copyright of Journal of Computational Methods in Sciences & Engineering (Sage Publications Inc.) is the property of Sage Publications Inc. 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.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.