Performance evaluation of image fusion using the Multi-Wavelet and Curvelet transforms

Image fusion refers to the process of combining the relevant information from two or more images into a single highly informative image. The resulting fused image contains more information than the input images. In this paper, an algorithm for fusing two different modality medical images based on the Multi-Wavelet Transform (MWT) and Curvelet transform using different fusion techniques was implemented and results are analyzed using different quantitative measures. The images obtained from different medical imaging techniques such as Computer Tomography (CT) and Magnetic Resonance (MR) images are fused into a new image to improve the information content for diagnosis. In the present fusion algorithm, the input images from two different modalities such as CT and MR are initially registered and then transform namely Multi-Wavelet transform and Curvelet transform are applied on the input images. Finally the resultant images are fused using various fusion techniques. Fusion results are evaluated and compared according to four measures of performance - the Entropy (H), Root Mean Square Error (RMSE), Peak Signal to Noise Ratio (PSNR) and Correlation Coefficient (CC).