An image processing device includes: an image sequence acquisition section (200) that acquires an image sequence that includes a plurality of constituent images and a processing section (100) that performs an image summarization process that deletes some of the plurality of constituent images included in the image sequence to generate a summary image sequence, the processing section (100) detecting an observation target area from each of the plurality of constituent images, selecting a reference image and a determination target image from the plurality of constituent images, calculating deformation information about a deformation estimation target area included in the reference image and the deformation estimation target area included in the determination target image, and determining whether or not the determination target image can be deleted based on the observation target area included in the reference image, the observation target area included in the determination target image, and the deformation information.
