An Improved SVR Image Fusion Algorithm Base on Low-pass Filter and Histogram Matching

To avoid the spectral distortion of SVR(synthetic variable ratio) algorithm,we propose an improved algorithm by using a low-pass filter and histogram matching performance,which is hence named SVR based on low-pass filter and histogram matching(SVRFM) algorithm.Two subsets from the IKONOS image of Fuzhou,representing different land cover types were used as test data.The spectral fidelity and the ability of gaining high frequency information were assessed by using visual and statistical analysis.The fused images were compared with those fused using the SVR,wavelet transform,pansharp,ehlers and Gram-Schmidt algorithms,respectively.The results show that the spectral fidelity of the SVRFM algorithm is generally better than the five algorithms compared.