An image processing device includes a processor; and a memory which stores a plurality of instructions, which when executed by the processor, cause the processor to execute: obtaining a first image in which a user is included, a second image which is imaged in an imaging condition different from that of the first image, a third image which is continuously imaged at a different point of time from that of the first image, and in the same imaging condition as that of the first image, and a fourth image which is continuously imaged at a different point of time from that of the second image, and in the same imaging condition as that of the second image; extracting a first feature amount of a user which is included in the first image, a second feature amount of the user which is included in the second image, a third feature amount.