Multi-modal medical image fusion using 2DPCA

Principal Component Analysis is a dimension reduction technique that is widely used in the area of image fusion, classification and face recognition. It cannot be applied on two-dimensional images directly, instead, two-dimensional images must be transformed into one-dimensional vectors prior to applying PCA. Vectorization of images losses the relationships between rows and columns, that may lead to the calculation of misleading principal components. Two-dimensional PCA rectifies this problem by directly dealing with two-dimensional images without prior requirements of vectorization. In this paper, we proposed a novel multi-modal medical image fusion algorithm that is based on two-dimensional PCA. Experiments are conducted to fuse three image-sets of multi-modal images of the brain. Fusion results of proposed algorithms are compared with fusion results of PCA based image fusion algorithm by using seven widely used image quality assessment matrices. The comparison shows the superiority of proposed algorithm over existing PCA based image fusion algorithm.