An image processing apparatus according to the present invention includes: a basic shape matching section that extracts, as a structure region, an arbitrary structural object included in an image obtained by picking up an image of a mucosal surface of a living body and matches each pixel or each region in the extracted structure region with any of plural types of predetermined basic shapes； a structural object region dividing section that divides the structural object into regions according to respective basic shapes included in the plural types of predetermined basic shapes, based on a result of the matching by the basic shape matching section； and a feature value calculating section that calculates a feature value according to at least one of a frequency of appearance of each basic shape in a result of the region division by the structural object region dividing section and a positional relationship between basic shapes of one or more types in the result of the region division, based on the result of the region division.
