Research on image fusion algorithm based on K-means clustering and NSCT

Xinsai Wang; Weiqiang Feng; Xiaoer Feng

doi:10.1117/12.2587643

12 March 2021 Research on image fusion algorithm based on K-means clustering and NSCT

Xinsai Wang, Weiqiang Feng, Xiaoer Feng

Proceedings Volume 11763, Seventh Symposium on Novel Photoelectronic Detection Technology and Applications; 1176393 (2021) https://doi.org/10.1117/12.2587643
Event: Seventh Symposium on Novel Photoelectronic Detection Technology and Application 2020, 2020, Kunming, China

Abstract

Traditional NSCT-based image fusion algorithms usually first perform NSCT transformation on the original image, and then perform the fusion of different scale coefficients, without specific analysis of the original image. In this regard, an image fusion algorithm based on K-means clustering is proposed. First use the K-means algorithm clustering to classify images, and then perform NSCT decomposition on the segmented images to obtain low-frequency and high-frequency subband coefficients. According to the characteristics of the segmented image, an adaptive weighted fusion method is used to fuse the coefficients. Finally, the fusion coefficients are inversely transformed by NSCT to obtain the final fusion image. Experimental results show that the algorithm is more effective in preserving image texture information and improving contrast, and the objective quality evaluation results are also better.

Citation Download Citation

Xinsai Wang, Weiqiang Feng, and Xiaoer Feng "Research on image fusion algorithm based on K-means clustering and NSCT", Proc. SPIE 11763, Seventh Symposium on Novel Photoelectronic Detection Technology and Applications, 1176393 (12 March 2021); https://doi.org/10.1117/12.2587643

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