Polarization image fusion method based on traditional wavelet decomposition and its improvement

Gao Yang; Yang Zhou; Kuan Lu; Hong Chang

doi:10.1117/12.2553012

31 January 2020 Polarization image fusion method based on traditional wavelet decomposition and its improvement

Gao Yang, Yang Zhou, Kuan Lu, Hong Chang

Proceedings Volume 11427, Second Target Recognition and Artificial Intelligence Summit Forum; 114273F (2020) https://doi.org/10.1117/12.2553012
Event: Second Target Recognition and Artificial Intelligence Summit Forum, 2019, Changchun, China

Abstract

Aiming at the problems of polarization imaging detection technology in image fusion, an improved image fusion method based on traditional wavelet decomposition is proposed. Firstly, the fusion method of wavelet function and wavelet decomposition is analyzed. Secondly, the problems in the fusion method are improved from wavelet base and filtering and denoising. In order to verify the effectiveness of the improved method, the real images is used for image fusion, and the fusion and improvement results are evaluated by using information entropy and edge definition. The results show that the improved image fusion method significantly improves the sharpness of the fused image, and the high frequency loss is suppressed to a certain extent.

Citation Download Citation

Gao Yang, Yang Zhou, Kuan Lu, and Hong Chang "Polarization image fusion method based on traditional wavelet decomposition and its improvement", Proc. SPIE 11427, Second Target Recognition and Artificial Intelligence Summit Forum, 114273F (31 January 2020); https://doi.org/10.1117/12.2553012

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