Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

---

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

Full-Text [PDF 799 kb]   (4611 Downloads)    

Add your comments about this article : Your username or Email:

---