An image processing apparatus includes a processor comprising hardware. The processor is configured to: acquire a movement amount of a capsule endoscope in a movement direction of the capsule endoscope, based on information transmitted from the capsule endoscope including an imaging sensor and determine whether to associate a first image captured by the imaging sensor with a second image, which is captured by the imaging sensor and is captured at a time different from a time in which the imaging sensor captures the first image, based on an imaging distance of the imaging sensor in the movement direction, and the movement amount.
