An image processing apparatus includes: a detecting unit configured to detect images of interest including regions of interest that are estimated as an object to be detected, from a group of a series of images acquired by sequentially imaging a lumen of a living body; a global similarity calculating unit configured to calculate a global similarity that is a similarity between regions including at least regions other than the regions of interest, between the images of interest different from one another; an image-of-interest group extracting unit configured to extract an image-of-interest group including identical regions of interest, in accordance with comparison between a threshold and the global similarity or a determination parameter based on the global similarity; and a representative image extracting unit configured to extract a representative image from the image-of-interest group.