A image processing apparatus includes an image extraction unit that extracts first and second feature images representing first and second feature, respectively from a first image group acquired by sequentially capturing images of inside of a subject, and that further extracts third and fourth feature images representing first and second feature, respectively from a second image group acquired before the first image group, a feature data acquiring unit that acquires first and second feature data characterizing a movement of the capsule endoscope between the first and second feature images and between the third and the fourth feature images, respectively, a comparing unit that compares the first feature data with the second feature data, and a display control unit that performs, with respect to the first image group, display control based on a result of the comparison by the comparing unit.
