Shahdoosti, Hamid Reza, Ghassemian, Hesan (2011). Multispectral and Panchromatic Image Fusion by Combining Spectral PCA and Spatial PCA Methods. , 11(3), 19-27.
Hamid Reza Shahdoosti; Hesan Ghassemian. "Multispectral and Panchromatic Image Fusion by Combining Spectral PCA and Spatial PCA Methods". , 11, 3, 2011, 19-27.
Shahdoosti, Hamid Reza, Ghassemian, Hesan (2011). 'Multispectral and Panchromatic Image Fusion by Combining Spectral PCA and Spatial PCA Methods', , 11(3), pp. 19-27.
Shahdoosti, Hamid Reza, Ghassemian, Hesan Multispectral and Panchromatic Image Fusion by Combining Spectral PCA and Spatial PCA Methods. , 2011; 11(3): 19-27.

Multispectral and Panchromatic Image Fusion by Combining Spectral PCA and Spatial PCA Methods

The Modares Journal of Electrical Engineering
Article 3, Volume 11, Issue 3, 2011, Pages 19-27    PDF (799 K)
Authors
Hamid Reza Shahdoosti* 1; Hesan Ghassemian2
1Ph.D. Student, Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran, hamidreza.
2Professor, Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran,
Abstract
An ideal fusion method preserves the spectral information in fused image without spatial distortion. The PCA is believed to be a well-known pan-sharpening approach and being widely used for its efficiency and high spatial resolution. However, it can distort the spectral characteristics of multispectral images. The current paper tries to present a new fusion method based on the same concept. In the conventional standard PCA method, PCA transform is applied to spectral bands of multispectral images, but we applied the PCA transform to pixel blocks instead. Since PCA coefficients are extracted from statistical properties of the image, it is more consistent with type and texture of remotely sensed image compared to other kernels such as wavelets. After that, a new hybrid algorithm is proposed which uses both the spatial PCA and the spectral PCA method to improve the quality of the merged images. Visual and statistical analyses show that the proposed algorithm clearly improves the merging quality in terms of RASE, ERGAS, SAM, correlation coefficient and UIQI; compared to fusion methods such as IHS, Brovey, PCA, HPF, and HPM.
Keywords
Principal Component Analysis (PCA) Transform; Image-Fusion; Multispectral Images; Spatial Information; Spectral Information
Statistics
Article View: 111
PDF Download: 63
Statistics
Number of Journals45
Number of Issues2,171
Number of Articles24,674
Article View24,395,647
PDF Download17,535,418