To enable accurate stitching of images in generating a panoramic image by performing position adjustment of an image group with few characters, an image processing device includes: a calculation unit that calculates degrees of correlation between a plurality of images a second calculation unit that calculates character amounts of a plurality of images and an order determination unit that determines an order of performing position adjustment of the plurality of images for generating a panoramic image generated by stitching the plurality of images based on calculation results of the calculation unit and the second calculation unit.