Affiliation:
1. Research scholar, Computer Science Engineering, SRM Institute of Science and Technology, Tamilnadu, India
2. Computer Science Engineering, SRM Institute of Science and Technology, Tamilnadu, India
Abstract
The technique of integrating images from two or more sensors that were taken from the same place or the same object is known as image fusion. The goal is to get more spectral and spatial information from the combined image as a whole than from the individual images. It is required to fuse the images in order to improve the spatial and spectral quality of both panchromatic and multispectral images. This study introduces a novel method for fusing remote sensing images that combines L0 smoothing, NSCT (Non-subsampled Contourlet Transform), SR (Sparse Representation), and MAR (Max absolute rule). The multispectral and panchromatic images are initially divided into lower and higher frequency components using the L0 smoothing filter as the method of fusion. The fusion process is then carried out, utilising a technique that combines NSCT and SR to fuse low-frequency components. Similar to this, the Max-absolute fusion rule is used to fuse high-frequency components. In conclusion, the disintegration of fused low-frequency and high-frequency data yields the final image. Our method yields an enhanced outcome in terms of the correlation coefficient, Entropy, spatial frequency, and fusion of mutual information for both the term of picture quality enhancement and visual evaluation. This suggested approach produces superior outcomes after execution. This study makes use of the Landsat-7ETM+, IKONOS, and Quick Bird datasets. Different satellites are used to take each image. There have been two examples of each image used. In comparison to previous Traditional Methods, the proposed image fusion techniques’ output has a quality that is more than 20% higher.
Subject
Artificial Intelligence,General Engineering,Statistics and Probability
Reference25 articles.
1. A new multi-spectral feature level image fusion method for human interpretation;Leviner;Infrared Physics & Technology,2009
2. Joseph D. and Jemima T. , Jebaseeli, A Survey Of Fusion Of Remote Sensing Images To Avoid Spectral Distortion, International Journal of Engineering Research & Technology (IJERT) 1(8) (2012), October –2012 ISSN: 2278-0181..
3. Edge detection in multispectral images;Cumani;CVGIP: Graphical Models and Image Processing,1991
4. A note on the gradient of a multi-image;Di Zenzo;Comput Vision Graphics Image Processing,1986
5. Anisotropic diffusion of multivalued images with applications to color filtering;Sapiro;IEEE Trans Image Processing,1996
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献