Research on infrared image classification algorithm based on improved KNN

Qingqing Wang; Jianzhuang Du

doi:10.1117/12.3017810

15 January 2024 Research on infrared image classification algorithm based on improved KNN

Qingqing Wang, Jianzhuang Du

Proceedings Volume 12983, Second International Conference on Electrical, Electronics, and Information Engineering (EEIE 2023); 129831P (2024) https://doi.org/10.1117/12.3017810
Event: Second International Conference on Electrical, Electronics, and Information Engineering (EEIE 2023), 2023, Wuhan, China

Abstract

This paper focused on the improved KNN infrared image classification algorithm. In the process of image feature extraction, particle swarm optimization (PSO) was introduced to solve the problem that the iterative speed of objective function optimization was relatively slow in the traditional ICA algorithm. In this way, the global optimal solution could be found quickly when the objective function was optimized, which greatly reduced the computational complexity of ICA algorithm. In order to solve the ambiguity problem of KNN classification in image classification, error correcting coding theory was introduced, which was combined with KNN classification algorithm to classify multi class objects. Experiments showed that the improved algorithm in this paper had obvious optimization in classification, strong anti error classification ability and high accuracy.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Qingqing Wang and Jianzhuang Du "Research on infrared image classification algorithm based on improved KNN", Proc. SPIE 12983, Second International Conference on Electrical, Electronics, and Information Engineering (EEIE 2023), 129831P (15 January 2024); https://doi.org/10.1117/12.3017810

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