Hybrid Image Fusion Method Based On Discrete Wavelet Transform (DWT), Principal Component Analysis (PCA) and Guided Filter

Image fusion is the process of integrating the features of multiple images into a single image. The final image represents all important features from each source image. A number of imaging modalities are available which provide diverse information. CT (Computed Tomography) scan gives the information about bones whereas MR (Magnetic Resonance) provide information about soft tissues. There is a requirement of image fusion as the single image does not satisfy sufficient clinical requirements. In this paper, a hybrid approach using Discrete Wavelet Transform (DWT), Principal Component Analysis (PCA) and Guided filter has been proposed. Medical images usually contain noise and are not well contrasted. The proposed method enhances the source images in contrast and reduces noise using wavelet de-noising removal mechanism. Guided filter has been used in fusion process to preserve the information about the edges. The proposed method improves the results of multi-modal medical images both visually and metrically.