Abstract: In an image included in a moving image, a specific area is registered as a reference area, and a specific hue range of the reference area is set as a first feature amount based on the distribution of hues of pixels in the reference area. When the occupation ratio of pixels having hues included in a second feature amount, obtained by expanding the hue range of the first feature amount in a surrounding area larger than the reference area, is smaller than a predetermined ratio, an area having a high degree of correlation is identified from an image using the second feature amount in the subsequent matching process. When the occupation ratio is equal to or larger than the predetermined ratio, an area having a high degree of correlation is identified from an image using the first feature amount in the subsequent matching process.

Abstract: A technique is disclosed for reducing noise in a medical image, wherein plural anisotropic areas continuous with a pixel-of-interest contained in the medical image are set with the pixel-of-interest being centered a statistical amount of pixel values of pixels constituting each anisotropic area is calculated with respect to each of the plural anisotropic areas, and either an anisotropic area having the minimum statistical amount out of the plural anisotropic areas is determined and an anisotropic shape filter in the same direction as the anisotropic area concerned is constructed, or an anisotropic area having the maximum statistical amount out of the plural anisotropic areas is determined and an anisotropic shape filter is constructed by clockwise or counterclockwise rotating the anisotropic area concerned around the pixel-of-interest by 90° .