Problems occurring due to a difference in point of view between cameras in compositing a panoramic image by using multiple images taken by the cameras are solved. An image processing device includes an image data receiving unit 101, a panoramic image generating unit 102, a designation receiving unit 103, and a single photographic image selecting unit 105. The image data receiving unit 101 receives data of a first still image and a second still image. The panoramic image generating unit 102 projects the first still image and the second still image on a projection sphere to generate a composited image. The designation receiving unit 103 receives designation of a specific position in the panoramic image. The single photographic image selecting unit 105 selects one of the first still image and the second still image, which contains the designated position received by the designation receiving unit 103.