Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You and Your Team.

Learn More →

Performance enhanced hyperspectral and multispectral image fusion technique using ripplet type-II transform and deep neural networks for multimedia applications

Performance enhanced hyperspectral and multispectral image fusion technique using ripplet type-II... Multispectral and hyper spectral image fusion aspires to improve the spectral information and spatial details. Previous fusion algorithms have concentrated on spectral information and spatial details, but those fused images have missed its sharpening. This paper is introduced the ripple type-II (RT-II) transform and deep neural network (DNN). RT -II transform can be decomposed both multispectral and hyper spectral images, then DNN are used for recognize the complementary features and sharpened the decomposed images. Then applied the fused rules for fuse the both images and applied inverse RT -II transform to get fused image. In this paper, the proposed method gets better entropy, standard deviation (SD), Correlation Coefficient (CC), Edge-Dependent Fusion Quality Index (EDFQI), Edge Based Similarity Measure (EBSM), Structural similarity (SSIM) as compared with other methods. The best way of analyzing the concepts of date and image fusion methods is to perform fusion based analysis in multimedia based tools.so that an end user can understand easily. The aspects like video, sound, text, animation, graphics have been elucidated by means of multimedia tools. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Multimedia Tools and Applications Springer Journals

Performance enhanced hyperspectral and multispectral image fusion technique using ripplet type-II transform and deep neural networks for multimedia applications

Loading next page...
 
/lp/springer_journal/performance-enhanced-hyperspectral-and-multispectral-image-fusion-CFOaiVaXQg
Publisher
Springer Journals
Copyright
Copyright © Springer Science+Business Media, LLC, part of Springer Nature 2018
Subject
Computer Science; Multimedia Information Systems; Computer Communication Networks; Data Structures, Cryptology and Information Theory; Special Purpose and Application-Based Systems
ISSN
1380-7501
eISSN
1573-7721
DOI
10.1007/s11042-018-6174-3
Publisher site
See Article on Publisher Site

Abstract

Multispectral and hyper spectral image fusion aspires to improve the spectral information and spatial details. Previous fusion algorithms have concentrated on spectral information and spatial details, but those fused images have missed its sharpening. This paper is introduced the ripple type-II (RT-II) transform and deep neural network (DNN). RT -II transform can be decomposed both multispectral and hyper spectral images, then DNN are used for recognize the complementary features and sharpened the decomposed images. Then applied the fused rules for fuse the both images and applied inverse RT -II transform to get fused image. In this paper, the proposed method gets better entropy, standard deviation (SD), Correlation Coefficient (CC), Edge-Dependent Fusion Quality Index (EDFQI), Edge Based Similarity Measure (EBSM), Structural similarity (SSIM) as compared with other methods. The best way of analyzing the concepts of date and image fusion methods is to perform fusion based analysis in multimedia based tools.so that an end user can understand easily. The aspects like video, sound, text, animation, graphics have been elucidated by means of multimedia tools.

Journal

Multimedia Tools and ApplicationsSpringer Journals

Published: Feb 5, 2020

References