A defective nozzle estimation device that estimates a defective nozzle of a plurality of ink jet heads of a printing device that prints a printed matter on a print medium by jetting inks from nozzles of the ink jet heads on the basis of print source data, the plurality of ink jet heads jetting inks of different colors from the nozzles, the defective nozzle estimation device comprising:
- at least one processor;
- and
- at least one memory that stores a command to be executed by the at least one processor,
- wherein the at least one processor
- acquires a position of an image defect of the printed matter caused by the defective nozzle in imaging data based on a captured image in which the printed matter is imaged by a scanner,
- acquires a first pixel value at the position of the image defect of the imaging data,
- acquires a second pixel value at a position corresponding to the position of the image defect of reference data, which is the print source data or reference imaging data based on a reference captured image in which a reference printed matter is imaged by the scanner, and
- estimates at least one defective nozzle candidate, which is a cause of the image defect of the printed matter, from the first pixel value and the second pixel value using a learning model.