An image processing apparatus comprises: an image input section via which a medical image picked up of a mucous surface of a living body is inputted; a feature value calculating section that calculates a specific feature value with respect to each pixel or each region in the medical image; a structure region extracting section that extracts a desired structural object from the picked up medical image as a structure region; a basic shape matching section that matches the each pixel or the each region in the structure region with a plurality of predetermined basic shapes based on the calculated feature value; a structural object region dividing section that divides the structural object into regions for each of the predetermined basic shapes based on a matching result of the basic shape matching section.