Generation of an inappropriate image portion in an orthographic image due to occlusion is prevented. An image processing device includes an image data receiving part that receives image data of multiple photographed images taken by photographing an object from different positions, a coordinate designating part that receives designation of a specific position in the object, and an optimum-condition satisfying image selecting part that selects a photographed image that is taken from a direction in a specific range relative to the specific position, from among the multiple photographed images. The selected photographed image is used to obtain pixel information of the specific position.