A tentative eigenprojection matrix (#12-a) is provisionally generated from a studying image group (#10) including a pair of a high quality image and a low quality image, and a tentative projection core tensor (#12-b) defining a correspondence between the low quality image and an intermediate eigenspace and a correspondence between the high quality image and the intermediate eigenspace is created. A first sub-core tensor is created from the tentative projection core tensor based on a first setting (#12-c), and the studying image group is projected based on the tentative eigenprojection matrix and the first sub-core tensor (#15-a) to calculate an intermediate eigenspace coefficient vector (#15-b). A representative intermediate eigenspace coefficient vector (#15-c) is obtained from the coefficient vector group according to the number of studying representatives, an eigenprojection matrix (#17) and a projection core tensor (#18) are recreated based on the determined representative studying image group (#15-d), and the matrix and the tensor are used in a restoration step. This can reduce the redundancy of a studying image set, reduce processing load of projection conversion, speed up a process, and suppress a memory size.