IDEAS home Printed from https://ideas.repec.org/a/igg/jsir00/v14y2023i2p1-15.html
   My bibliography  Save this article

A Multi-Feature Fusion Model Based on Denoising Convolutional Neural Network and Attention Mechanism for Image Classification

Author

Listed:
  • Jingsi Zhang

    (Faculty of Robot Science and Engineering, Northeastern University, Shenyang, Northeastern University, China)

  • Xiaosheng Yu

    (Faculty of Robot Science and Engineering, Northeastern University, Shenyang, Northeastern University, China)

  • Xiaoliang Lei

    (Faculty of Robot Science and Engineering, Northeastern University, Shenyang, Northeastern University, China)

  • Chengdong Wu

    (Faculty of Robot Science and Engineering, Northeastern University, Shenyang, Northeastern University, China)

Abstract

Spatial location features extracted by denoising convolutional neural network. At this time, an attention mechanism is introduced into denoising convolutional neural network. The dual attention model of local area is presented from two dimensions of channel and space—channel attention mechanism weights channel and spatial attention mechanism weights location. A variety of machine learning methods are used to classify and train different features. Multi-semantic features and heterogeneous features are fused by adaptive weighted fusion algorithm. Finally, the data sets Cifar-10, STL-10, Cifar-100 and GHIM-1OK are verified on the proposed method. Compared with a single semantic feature, the accuracy is improved by 10%-15%. Compared with several advanced algorithms, the performance has a significant advantage, which proves the complementarity of heterogeneous features and multi-network semantic features and the effectiveness of the adaptive weighted fusion algorithm.

Suggested Citation

  • Jingsi Zhang & Xiaosheng Yu & Xiaoliang Lei & Chengdong Wu, 2023. "A Multi-Feature Fusion Model Based on Denoising Convolutional Neural Network and Attention Mechanism for Image Classification," International Journal of Swarm Intelligence Research (IJSIR), IGI Global, vol. 14(2), pages 1-15, May.
    • Handle: RePEc:igg:jsir00:v:14:y:2023:i:2:p:1-15
    as

    Download full text from publisher

    File URL: http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJSIR.324074
    Download Restriction: no
    ---><---

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:igg:jsir00:v:14:y:2023:i:2:p:1-15. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Journal Editor (email available below). General contact details of provider: https://www.igi-global.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.