Abstract
Image fusion is the process by which two or more images are combined into a single image retaining the important features from each of the original images. It aims at the integration of complementary data to enhance the information apparent in the images as well as to increase the reliability of the interpretation. The successful fusion of images acquired from different modalities or instruments is of great importance in many applications such as medical imaging, microscopic imaging, remote sensing, computer vision, and robotics. In the present work, four different image fusion techniques were implemented and applied to computed tomography (CT) and magnetic resonance imaging (MRI). These are the Laplacian pyramid, the wavelet transform, the computationally efficient pixel-level image fusion (CEMIF) method, and the multi-focus technique based on spatial frequency. Fusion results were evaluated according to three measures of performance; the entropy, the cross entropy and the spatial frequency. Image fusion techniques were applied to facilitate detection of hepatic lesions and acute intra-cerebral hemorrhage by fusing MRI and CT images at the same level. The fused images had led to higher detection accuracy than using either CT or MR images.