Domain-specific image classification based on improved residual networks

Yanan Sun; Zhi Wang; Xinjie Zhu

doi:10.1117/12.2662634

16 December 2022 Domain-specific image classification based on improved residual networks

Yanan Sun, Zhi Wang, Xinjie Zhu

Proceedings Volume 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022); 125003D (2022) https://doi.org/10.1117/12.2662634
Event: 5th International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 2022, Chongqing, China

Abstract

Aiming at the problems of high target similarity and strong camouflage in the domain-specific, and the traditional image classification technology is difficult to achieve accurate classification, it is proposed to use the deep neural network Resnet50 as the feature extraction network, and combine the attention mechanism and improve it, which can improve the ability of learning effective features; and use depthwise separable convolution to replace standard convolution, which can reduce computational parameters and save computational space. It is verified by experiments that the accuracy of the improved algorithm in this paper is 0.71% higher than that of the Resnet50 prototype, and 0.39 % higher than that of the Resnet50 +SE algorithm model in the image classification of the domain-specific.

Citation Download Citation

Yanan Sun, Zhi Wang, and Xinjie Zhu "Domain-specific image classification based on improved residual networks", Proc. SPIE 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 125003D (16 December 2022); https://doi.org/10.1117/12.2662634

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