Multimodal image fusion based on global-regional-local rule in NSST domain
- PDF / 3,941,160 Bytes
- 27 Pages / 439.37 x 666.142 pts Page_size
- 72 Downloads / 190 Views
Multimodal image fusion based on global-regional-local rule in NSST domain Zhancheng Zhang 1 & Xinxing Xi 2,3 & Xiaoqing Luo 2,3 & Yuting Jiang 2,3 & Jing Dong 4 & Xiaojun Wu 2,3 Received: 30 September 2019 / Revised: 5 August 2020 / Accepted: 18 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
An accurate representation of the source image is vital in image fusion processing. However, among most of the traditional multi-scale decomposition based image fusion methods, they fail to accurately interpret the source images, only capturing local information without considering the regional and global information. To overcome this drawback, a novel image fusion method based on the global-regional-local rule is proposed in the nonsubsampled shearlet transform (NSST) domain. First, the source paired images are decomposed into the low-pass subbands and high-pass subbands with the NSST transformation. Second, for comprehensively representing the statistical correlation of source image, three-level statistical models, that is, global contextual hidden Markov model (G-CHMM), regional contextual hidden Markov model (R-CHMM), and local contextual hidden Markov model (L-CHMM) are established for the high-pass subbands. In the R-CHMM, a novel feature vector is extracted for getting the region map of source image by the fuzzy cluster method (FCM). Third, to get accurate active measures of the source image, a global-regional-local fusion rule based on the statistical characteristics extracted from global-regional-local CHMM is designed, which is used to fuse the high-pass subbands. The low-pass subbands are fused with the choose-max rule based on the local gradient measure. Finally, the fused image is obtained by the inverse NSST. Experimental results on serials of infrared and visible images, medical images and multi-focus images demonstrate the advantage of the proposed method in terms of detail preserving. Keywords Global . Regional . Local . Correlation . Contextual hidden Markov model . Image fusion
* Xiaoqing Luo [email protected] Extended author information available on the last page of the article
Multimedia Tools and Applications
1 Introduction Image fusion technology refers to generate a comprehensive image including all useful information from different source images, which is helpful for image processing [20]. At present, image fusion technology has been widely used in many fields, including remote sensing image analysis and processing, automatic recognition, computer vision, medical image processing, and so on. In the medical imaging field, multi-modal medical image fusion is to get a clear image with high spatial resolution and containing both anatomical morphological information and organ functional metabolism information which can help a doctor make a diagnosis. Besides, image fusion technology can merge the images captured from the same scene but with different focus parameters into a clear all-focus image. It can also integrate the infrared and visible images into
Data Loading...
