Journal
NEURAL COMPUTING & APPLICATIONS
Volume 33, Issue 14, Pages 8157-8167Publisher
SPRINGER LONDON LTD
DOI: 10.1007/s00521-020-04930-7
Keywords
Convolutional neural network; Image classification; Activation function; Improved algorithm
Categories
Funding
- National Key R&D Program of China [2017YFB0503604, 2017YFB0503801]
- China Postdoctoral Science Foundation
- FDCT [017/2018/A]
- Cross-and Multi-Dimension Electronic Fence System Project
- Project of Macao Foundation
Ask authors/readers for more resources
A new convolution kernel proposed in this study can detect corresponding features with different transformations by actively changing the positions of connections, improving the image classification effect. Replacing a traditional convolution kernel with a complex one significantly enhances network performance.
Image classification method is currently the more popular image technology, but it still has certain problems in practice. In order to improve the image classification effect, this study proposes a new convolution kernel, which can effectively detect the corresponding features with different transformations by actively transforming the relative positions of the connections in the convolution kernel. Moreover, in a network, replacing a traditional convolution kernel with a complex convolution kernel can significantly improve network performance. In order to verify the performance of the image classification method proposed in this study, the performance comparison of the algorithm was performed by setting a control experiment. The research results show that the proposed method has certain effects and can provide theoretical reference for subsequent related research.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available