An image processing apparatus includes a processor. The processor is configured to: obtain a presumption result by presuming an operation state of a user who performs an operation while the user observes an image obtained by picking up an image of a subject； perform processing for correcting a specular reflection region included in the image obtained by picking up the image of the subject； and when detecting, based on the presumption result, that a first operation related to search for a desired object in the subject is performed, perform control for causing the image in which the specular reflection region is maintained to be outputted as an observation image, and when detecting that a second operation related to discrimination of the desired object found in the subject is performed, perform control for causing the image in which the specular reflection region is corrected to be outputted as an observation image.
