Image Fusion Method of Guiding Filter Based on PCA and NSCT
Aiming at the problems of severe loss of edge details and spatial distortion in infrared and visible image fusion,in this paper,an image fusion method based on Principal Component Analysis(PCA)and non-subsampled contourlet transform(NSCT)is proposed.Firstly,the first principal component information of the infrared image and the spatial detail information of the visible image is extracted by PCA transform and weighted least square filter respectively,and the results are injected into the first principal component information,the results are transformed by NSCT with the visible images,and the high and low frequency imag-es are fused by the guided filtering and the local Pierre-Simon Laplace energy method respectively,then PCA inverse transform is used to get the fused image.The experimental results show that the fused image texture is clear,the texture details of the dark region are enhanced,and the fusion method is better than the traditional image fusion method in 5 objective evaluation indexes.
infrared and visible imageimage fusionPCANSCTguided filtering
国家科技期刊平台
NSTL
万方数据
