Modified PCA Transformation with LWT for High-Resolution based Image Fusion

In this paper, we have adopted the combined approach to fuse images with spatial-domain and frequency-domain approach which has the advantages of both domains. The frequency-domain transformation is done with wavelet scheme, while modified principal component analysis (PCA) is used for spatial-domain transformation. Spatial-domain image fusion methods generally have poor performance because they produce spatial distortion in the fused image. The frequency domain methods have high computational complexity and provide great robustness. In this paper, we have proposed a method which is called modified LWT–PCA. The proposed method focuses on PCA transformation combined with frequency components obtained from LWT method to retain high resolution of image. Later, inverse PCA is performed to retirve the final image. Traditional discrete wavelet transform based on convolution requires massive computation and storage space. Wavelet transform based on lifting scheme can solve these computational complexity problems. Comparing to other multiscale transforms, wavelet transform provides better fused image. It has been observed that high correlation exists between the replaced components. The higher-resolution data ensures that the spectral information of the original image is maintained. We have obtained higher variance where gray level scattering is more, which is elaborated using experimental results. Other quantitative and qualitative results are presented in this paper which show that proposed method is better than other methods in literature.