Research on image classification based on extreme learning machine and convolutional neural network

Changxu Sun; Rui Zhang

doi:10.1117/12.2684991

19 October 2023 Research on image classification based on extreme learning machine and convolutional neural network

Changxu Sun, Rui Zhang

Proceedings Volume 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023); 127095Y (2023) https://doi.org/10.1117/12.2684991
Event: Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 2023, Nanjing, China

Abstract

In image classification and recognition, in order to obtain higher classification accuracy, it is necessary to extract more accurate and more expressive features of image semantic information. This paper proposes an improved image classification model based on convolutional neural network. By improving and optimizing AlexNet from both the network architecture and the internal structure, we can further improve the expression ability of features. By introducing the extreme learning machine in the full connection layer, not only the classification ability and classification time of the network are improved, but also the structure has better data processing ability.

Citation Download Citation

Changxu Sun and Rui Zhang "Research on image classification based on extreme learning machine and convolutional neural network", Proc. SPIE 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 127095Y (19 October 2023); https://doi.org/10.1117/12.2684991

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available