A computer image feature extraction algorithm based on distributed K-means algorithm

Zhenmin Dai; Wang Ling; Daiwei Xie

doi:10.1117/12.3026778

27 March 2024 A computer image feature extraction algorithm based on distributed K-means algorithm

Zhenmin Dai, Wang Ling, Daiwei Xie

Proceedings Volume 13105, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023); 131054E (2024) https://doi.org/10.1117/12.3026778
Event: 3rd International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023), 2023, Qingdao, China

Abstract

In order to understand computer image feature extraction algorithms, a research on computer image feature extraction algorithm based on distributed K-means algorithm has been proposed. The feature extraction of images, as the key, fundamentally determines the accuracy of image recognition. With the advent of the big data era, feature learning methods represented by deep learning models have demonstrated their powerful capabilities in image feature extraction tasks. Secondly, through layer by layer training, deep learning models can extract deep features of images in a highly autonomous manner, and have achieved the best results in the current research stage. Although deep learning models have extremely powerful learning abilities, the complexity of their model structure and the overhead involved in training also hinder their training. Based on clustering algorithms, a hierarchical image feature extraction model is constructed to improve the accuracy of image classification.

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

Citation Download Citation

Zhenmin Dai, Wang Ling, and Daiwei Xie "A computer image feature extraction algorithm based on distributed K-means algorithm", Proc. SPIE 13105, International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2023), 131054E (27 March 2024); https://doi.org/10.1117/12.3026778

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